@Article{info:doi/10.2196/57018,
author="Cook, Diane
and Walker, Aiden
and Minor, Bryan
and Luna, Catherine
and Tomaszewski Farias, Sarah
and Wiese, Lisa
and Weaver, Raven
and Schmitter-Edgecombe, Maureen",
title="Understanding the Relationship Between Ecological Momentary Assessment Methods, Sensed Behavior, and Responsiveness: Cross-Study Analysis",
journal="JMIR Mhealth Uhealth",
year="2025",
month="Apr",
day="10",
volume="13",
pages="e57018",
keywords="ecological momentary assessment",
keywords="smart home",
keywords="smartwatch",
keywords="cognitive assessment",
keywords="well-being",
keywords="monitoring",
keywords="monitoring behavior",
keywords="machine learning",
keywords="artificial intelligence",
keywords="app",
keywords="wearables",
keywords="sensor",
keywords="effectiveness",
keywords="accuracy",
abstract="Background: Ecological momentary assessment (EMA) offers an effective method to collect frequent, real-time data on an individual's well-being. However, challenges exist in response consistency, completeness, and accuracy. Objective: This study examines EMA response patterns and their relationship with sensed behavior for data collected from diverse studies. We hypothesize that EMA response rate (RR) will vary with prompt time of day, number of questions, and behavior context. In addition, we postulate that response quality will decrease over the study duration and that relationships will exist between EMA responses, participant demographics, behavior context, and study purpose. Methods: Data from 454 participants in 9 clinical studies were analyzed, comprising 146,753 EMA mobile prompts over study durations ranging from 2 weeks to 16 months. Concurrently, sensor data were collected using smartwatch or smart home sensors. Digital markers, such as activity level, time spent at home, and proximity to activity transitions (change points), were extracted to provide context for the EMA responses. All studies used the same data collection software and EMA interface but varied in participant groups, study length, and the number of EMA questions and tasks. We analyzed RR, completeness, quality, alignment with sensor-observed behavior, impact of study design, and ability to model the series of responses. Results: The average RR was 79.95\%. Of those prompts that received a response, the proportion of fully completed response and task sessions was 88.37\%. Participants were most responsive in the evening (82.31\%) and on weekdays (80.43\%), although results varied by study demographics. While overall RRs were similar for weekday and weekend prompts, older adults were more responsive during the week (an increase of 0.27), whereas younger adults responded less during the week (a decrease of 3.25). RR was negatively correlated with the number of EMA questions (r=?0.433, P<.001). Additional correlations were observed between RR and sensor-detected activity level (r=0.045, P<.001), time spent at home (r=0.174, P<.001), and proximity to change points (r=0.124, P<.001). Response quality showed a decline over time, with careless responses increasing by 0.022 (P<.001) and response variance decreasing by 0.363 (P<.001). The within-study dynamic time warping distance between response sequences averaged 14.141 (SD 11.957), compared with the 33.246 (SD 4.971) between-study average distance. ARIMA (Autoregressive Integrated Moving Average) models fit the aggregated time series with high log-likelihood values, indicating strong model fit with low complexity. Conclusions: EMA response patterns are significantly influenced by participant demographics and study parameters. Tailoring EMA prompt strategies to specific participant characteristics can improve RRs and quality. Findings from this analysis suggest that timing EMA prompts close to detected activity transitions and minimizing the duration of EMA interactions may improve RR. Similarly, strategies such as gamification may be introduced to maintain participant engagement and retain response variance. ",
doi="10.2196/57018",
url="https://mhealth.jmir.org/2025/1/e57018"
}


@Article{info:doi/10.2196/68704,
author="Remaki, Adam
and Ung, Jacques
and Pages, Pierre
and Wajsburt, Perceval
and Liu, Elise
and Faure, Guillaume
and Petit-Jean, Thomas
and Tannier, Xavier
and G{\'e}rardin, Christel",
title="Improving Phenotyping of Patients With Immune-Mediated Inflammatory Diseases Through Automated Processing of Discharge Summaries: Multicenter Cohort Study",
journal="JMIR Med Inform",
year="2025",
month="Apr",
day="9",
volume="13",
pages="e68704",
keywords="secondary use of clinical data for research and surveillance",
keywords="clinical informatics",
keywords="clinical data warehouse",
keywords="electronic health record",
keywords="data science",
keywords="artificial intelligence",
keywords="AI",
keywords="natural language processing",
keywords="ontologies",
keywords="classifications",
keywords="coding",
keywords="tools",
keywords="programs and algorithms",
keywords="immune-mediated inflammatory diseases",
abstract="Background: Valuable insights gathered by clinicians during their inquiries and documented in textual reports are often unavailable in the structured data recorded in electronic health records (EHRs). Objective: This study aimed to highlight that mining unstructured textual data with natural language processing techniques complements the available structured data and enables more comprehensive patient phenotyping. A proof-of-concept for patients diagnosed with specific autoimmune diseases is presented, in which the extraction of information on laboratory tests and drug treatments is performed. Methods: We collected EHRs available in the clinical data warehouse of the Greater Paris University Hospitals from 2012 to 2021 for patients hospitalized and diagnosed with 1 of 4 immune-mediated inflammatory diseases: systemic lupus erythematosus, systemic sclerosis, antiphospholipid syndrome, and Takayasu arteritis. Then, we built, trained, and validated natural language processing algorithms on 103 discharge summaries selected from the cohort and annotated by a clinician. Finally, all discharge summaries in the cohort were processed with the algorithms, and the extracted data on laboratory tests and drug treatments were compared with the structured data. Results: Named entity recognition followed by normalization yielded F1-scores of 71.1 (95\% CI 63.6-77.8) for the laboratory tests and 89.3 (95\% CI 85.9-91.6) for the drugs. Application of the algorithms to 18,604 EHRs increased the detection of antibody results and drug treatments. For instance, among patients in the systemic lupus erythematosus cohort with positive antinuclear antibodies, the rate increased from 18.34\% (752/4102) to 71.87\% (2949/4102), making the results more consistent with the literature. Conclusions: While challenges remain in standardizing laboratory tests, particularly with abbreviations, this work, based on secondary use of clinical data, demonstrates that automated processing of discharge summaries enriched the information available in structured data and facilitated more comprehensive patient profiling. ",
doi="10.2196/68704",
url="https://medinform.jmir.org/2025/1/e68704"
}


@Article{info:doi/10.2196/63090,
author="Kriara, Lito
and Dondelinger, Frank
and Capezzuto, Luca
and Bernasconi, Corrado
and Lipsmeier, Florian
and Galati, Adriano
and Lindemann, Michael",
title="Investigating Measurement Equivalence of Smartphone Sensor--Based Assessments: Remote, Digital, Bring-Your-Own-Device Study",
journal="J Med Internet Res",
year="2025",
month="Apr",
day="3",
volume="27",
pages="e63090",
keywords="Floodlight Open",
keywords="multiple sclerosis",
keywords="smartphone",
keywords="sensors",
keywords="mobile phone",
keywords="wearable electronic devices",
keywords="digital health",
keywords="equivalence",
keywords="device equivalence",
keywords="cognition",
keywords="gait",
keywords="upper extremity function",
keywords="hand motor function",
keywords="balance",
keywords="digital biomarker",
keywords="variability",
keywords="mHealth",
keywords="mobile health",
keywords="autoimmune disease",
keywords="motor",
keywords="digital assessment",
abstract="Background: Floodlight Open is a global, open-access, fully remote, digital-only study designed to understand the drivers and barriers in deployment and persistence of use of a smartphone app for measuring functional impairment in a naturalistic setting and broad study population. Objective: This study aims to assess measurement equivalence properties of the Floodlight Open app across operating system (OS) platforms, OS versions, and smartphone device models. Methods: Floodlight Open enrolled adult participants with and without self-declared multiple sclerosis (MS). The study used the Floodlight Open app, a ``bring-your-own-device'' (BYOD) solution that remotely measured MS-related functional ability via smartphone sensor--based active tests. Measurement equivalence was assessed in all evaluable participants by comparing the performance on the 6 active tests (ie, tests requiring active input from the user) included in the app across OS platforms (iOS vs Android), OS versions (iOS versions 11-15 and separately Android versions 8-10; comparing each OS version with the other OS versions pooled together), and device models (comparing each device model with all remaining device models pooled together). The tests in scope were Information Processing Speed, Information Processing Speed Digit-Digit (measuring reaction speed), Pinching Test (PT), Static Balance Test, U-Turn Test, and 2-Minute Walk Test. Group differences were assessed by permutation test for the mean difference after adjusting for age, sex, and self-declared MS disease status. Results: Overall, 1976 participants using 206 different device models were included in the analysis. Differences in test performance between subgroups were very small or small, with percent differences generally being ?5\% on the Information Processing Speed, Information Processing Speed Digit-Digit, U-Turn Test, and 2-Minute Walk Test; <20\% on the PT; and <30\% on the Static Balance Test. No statistically significant differences were observed between OS platforms other than on the PT (P<.001). Similarly, differences across iOS or Android versions were nonsignificant after correcting for multiple comparisons using false discovery rate correction (all adjusted P>.05). Comparing the different device models revealed a statistically significant difference only on the PT for 4 out of 17 models (adjusted P?.001-.03). Conclusions: Consistent with the hypothesis that smartphone sensor--based measurements obtained with different devices are equivalent, this study showed no evidence of a systematic lack of measurement equivalence across OS platforms, OS versions, and device models on 6 active tests included in the Floodlight Open app. These results are compatible with the use of smartphone-based tests in a bring-your-own-device setting, but more formal tests of equivalence would be needed. ",
doi="10.2196/63090",
url="https://www.jmir.org/2025/1/e63090"
}


@Article{info:doi/10.2196/67632,
author="Li, Jiaying
and He, Rendong
and Hsu, Erh-Chi
and Li, Junxin",
title="Network Analysis of Key Instrumental Activities of Daily Living and Cognitive Domains for Targeted Intervention in US Older Adults Without Dementia: Cross-Sectional Study",
journal="JMIR Aging",
year="2025",
month="Mar",
day="19",
volume="8",
pages="e67632",
keywords="cognition function",
keywords="older adults",
keywords="intervention targets",
keywords="elder",
keywords="elderly",
keywords="cognitive impairment",
keywords="stimulating activity",
keywords="instrumental activities of daily living",
keywords="IADL",
keywords="daily living activity",
keywords="cognitive domain",
keywords="non-demented",
keywords="cognitive network",
keywords="holistic cognition",
keywords="holistic cognition function",
keywords="network comparison",
keywords="central variables",
keywords="bridge variables",
keywords="network analysis",
abstract="Background: Cognitive impairment in older adults reduces independence and raises health care costs but can be mitigated through stimulating activities. Based on network theory, intricate relationships within and between clusters of instrumental activities of daily living (IADLs) and cognitive domains suggest the existence of central IADLs and cognitive domains, as well as bridge IADLs. Modifying these can significantly enhance daily living activities and cognitive functions holistically. Objective: This study aims to identify central IADLs (key activities within the IADL network), central cognitive domains (key domains within the cognitive network), and bridge IADLs (linking IADL and cognitive networks). These insights will inform targeted interventions to effectively improve IADL and cognitive well-being in older adults. Methods: A cross-sectional analysis of adults aged 65 years and older in the United States focused on 5 IADLs and 6 cognitive domains from the National Health and Aging Trends Study (NHATS). Network analysis identified central and bridge variables. Nonparametric and case-dropping bootstrap methods checked network stability. Network comparison tests assessed sex differences with Benjamini-Hochberg adjustments. Results: Of the 2239 participants, 56.4\% were female (n=976). We computed and tested 3 networks: IADL, cognition, and bridge-with correlation stability coefficients of 0.67, 0.75, and 0.44, respectively (all>0.25). Meal preparation was identified as the central IADL, with a centrality index of 3.87, which was significantly higher than that of other IADLs (all P<.05). Visual attention emerged as the central cognition domain, with a centrality index of 0.86, which was significantly higher than that of other cognition domains (all P<.05). Shopping was determined to be the bridge IADL, with a centrality index of 0.41, which was significantly higher than that of other IADLs (all P<.05). Notably, gender differences emerged in the IADL network, with stronger associations between laundry and meal preparation in females (1.69 vs males: 0.74; P=.001) and higher centrality in meal preparation among females (difference=1.99; P=.007). Conclusions: While broad enhancements in all IADL and cognitive domains are beneficial, targeting meal preparation, visual attention, and shopping may leverage their within-network influence to yield a more pronounced improvement in holistic IADL, holistic cognition, and holistic cognition function through IADL interventions among older adults. Notably, meal preparation interventions may be less effective in males, requiring tailored approaches. ",
doi="10.2196/67632",
url="https://aging.jmir.org/2025/1/e67632"
}


@Article{info:doi/10.2196/67840,
author="Lu, Zhen
and Dong, Binhua
and Cai, Hongning
and Tian, Tian
and Wang, Junfeng
and Fu, Leiwen
and Wang, Bingyi
and Zhang, Weijie
and Lin, Shaomei
and Tuo, Xunyuan
and Wang, Juntao
and Yang, Tianjie
and Huang, Xinxin
and Zheng, Zheng
and Xue, Huifeng
and Xu, Shuxia
and Liu, Siyang
and Sun, Pengming
and Zou, Huachun",
title="Identifying Data-Driven Clinical Subgroups for Cervical Cancer Prevention With Machine Learning: Population-Based, External, and Diagnostic Validation Study",
journal="JMIR Public Health Surveill",
year="2025",
month="Mar",
day="19",
volume="11",
pages="e67840",
keywords="cervical cancer",
keywords="human papillomavirus",
keywords="screening",
keywords="machine learning",
keywords="cervical tumor",
keywords="cancer",
keywords="carcinoma",
keywords="tumor",
keywords="malignant",
keywords="ML",
keywords="phenomapping strategy",
keywords="logistic regression",
keywords="regression",
keywords="population-based",
keywords="validation study",
keywords="cancer prevention",
keywords="validity",
keywords="usability",
keywords="algorithm",
keywords="surveillance",
keywords="electronic health record",
keywords="EHR",
abstract="Background: Cervical cancer remains a major global health issue. Personalized, data-driven cervical cancer prevention (CCP) strategies tailored to phenotypic profiles may improve prevention and reduce disease burden. Objective: This study aimed to identify subgroups with differential cervical precancer or cancer risks using machine learning, validate subgroup predictions across datasets, and propose a computational phenomapping strategy to enhance global CCP efforts. Methods: We explored the data-driven CCP subgroups by applying unsupervised machine learning to a deeply phenotyped, population-based discovery cohort. We extracted CCP-specific risks of cervical intraepithelial neoplasia (CIN) and cervical cancer through weighted logistic regression analyses providing odds ratio (OR) estimates and 95\% CIs. We trained a supervised machine learning model and developed pathways to classify individuals before evaluating its diagnostic validity and usability on an external cohort. Results: This study included 551,934 women (median age, 49 years) in the discovery cohort and 47,130 women (median age, 37 years) in the external cohort. Phenotyping identified 5 CCP subgroups, with CCP4 showing the highest carcinoma prevalence. CCP2--4 had significantly higher risks of CIN2+ (CCP2: OR 2.07 [95\% CI: 2.03?2.12], CCP3: 3.88 [3.78?3.97], and CCP4: 4.47 [4.33?4.63]) and CIN3+ (CCP2: 2.10 [2.05?2.14], CCP3: 3.92 [3.82?4.02], and CCP4: 4.45 [4.31?4.61]) compared to CCP1 (P<.001), consistent with the direction of results observed in the external cohort. The proposed triple strategy was validated as clinically relevant, prioritizing high-risk subgroups (CCP3-4) for colposcopies and scaling human papillomavirus screening for CCP1-2. Conclusions: This study underscores the potential of leveraging machine learning algorithms and large-scale routine electronic health records to enhance CCP strategies. By identifying key determinants of CIN2+/CIN3+ risk and classifying 5 distinct subgroups, our study provides a robust, data-driven foundation for the proposed triple strategy. This approach prioritizes tailored prevention efforts for subgroups with varying risks, offering a novel and scalable tool to complement existing cervical cancer screening guidelines. Future work should focus on independent external and prospective validation to maximize the global impact of this strategy. ",
doi="10.2196/67840",
url="https://publichealth.jmir.org/2025/1/e67840"
}


@Article{info:doi/10.2196/63962,
author="Paz-Arbaizar, Leire
and Lopez-Castroman, Jorge
and Art{\'e}s-Rodr{\'i}guez, Antonio
and Olmos, M. Pablo
and Ram{\'i}rez, David",
title="Emotion Forecasting: A Transformer-Based Approach",
journal="J Med Internet Res",
year="2025",
month="Mar",
day="18",
volume="27",
pages="e63962",
keywords="affect",
keywords="emotional valence",
keywords="machine learning",
keywords="mental disorder",
keywords="monitoring",
keywords="mood",
keywords="passive data",
keywords="Patient Health Questionnaire-9",
keywords="PHQ-9",
keywords="psychological distress",
keywords="time-series forecasting",
abstract="Background: Monitoring the emotional states of patients with psychiatric problems has always been challenging due to the noncontinuous nature of clinical assessments, the effect of the health care environment, and the inherent subjectivity of evaluation instruments. However, mental states in psychiatric disorders exhibit substantial variability over time, making real-time monitoring crucial for preventing risky situations and ensuring appropriate treatment. Objective: This study aimed to leverage new technologies and deep learning techniques to enable more objective, real-time monitoring of patients. This was achieved by passively monitoring variables such as step count, patient location, and sleep patterns using mobile devices. We aimed to predict patient self-reports and detect sudden variations in their emotional valence, identifying situations that may require clinical intervention. Methods: Data for this project were collected using the Evidence-Based Behavior (eB2) app, which records both passive and self-reported variables daily. Passive data refer to behavioral information gathered via the eB2 app through sensors embedded in mobile devices and wearables. These data were obtained from studies conducted in collaboration with hospitals and clinics that used eB2. We used hidden Markov models (HMMs) to address missing data and transformer deep neural networks for time-series forecasting. Finally, classification algorithms were applied to predict several variables, including emotional state and responses to the Patient Health Questionnaire-9. Results: Through real-time patient monitoring, we demonstrated the ability to accurately predict patients' emotional states and anticipate changes over time. Specifically, our approach achieved high accuracy (0.93) and a receiver operating characteristic (ROC) area under the curve (AUC) of 0.98 for emotional valence classification. For predicting emotional state changes 1 day in advance, we obtained an ROC AUC of 0.87. Furthermore, we demonstrated the feasibility of forecasting responses to the Patient Health Questionnaire-9, with particularly strong performance for certain questions. For example, in question 9, related to suicidal ideation, our model achieved an accuracy of 0.9 and an ROC AUC of 0.77 for predicting the next day's response. Moreover, we illustrated the enhanced stability of multivariate time-series forecasting when HMM preprocessing was combined with a transformer model, as opposed to other time-series forecasting methods, such as recurrent neural networks or long short-term memory cells. Conclusions: The stability of multivariate time-series forecasting improved when HMM preprocessing was combined with a transformer model, as opposed to other time-series forecasting methods (eg, recurrent neural network and long short-term memory), leveraging the attention mechanisms to capture longer time dependencies and gain interpretability. We showed the potential to assess the emotional state of a patient and the scores of psychiatric questionnaires from passive variables in advance. This allows real-time monitoring of patients and hence better risk detection and treatment adjustment. ",
doi="10.2196/63962",
url="https://www.jmir.org/2025/1/e63962"
}


@Article{info:doi/10.2196/63622,
author="Aledavood, Talayeh
and Luong, Nguyen
and Baryshnikov, Ilya
and Darst, Richard
and Heikkil{\"a}, Roope
and Holm{\'e}n, Joel
and Ik{\"a}heimonen, Arsi
and Martikkala, Annasofia
and Riihim{\"a}ki, Kirsi
and Saleva, Outi
and Triana, Maria Ana
and Isomets{\"a}, Erkki",
title="Multimodal Digital Phenotyping Study in Patients With Major Depressive Episodes and Healthy Controls (Mobile Monitoring of Mood): Observational Longitudinal Study",
journal="JMIR Ment Health",
year="2025",
month="Feb",
day="21",
volume="12",
pages="e63622",
keywords="digital health",
keywords="mental disorders",
keywords="depression",
keywords="digital phenotyping",
keywords="smartphones",
keywords="mobile devices",
keywords="multisensor",
keywords="mobile phone",
abstract="Background: Mood disorders are among the most common mental health conditions worldwide. Wearables and consumer-grade personal digital devices create digital traces that can be collected, processed, and analyzed, offering a unique opportunity to quantify and monitor individuals with mental disorders in their natural living environments. Objective: This study comprised (1) 3 subcohorts of patients with a major depressive episode, either with major depressive disorder, bipolar disorder, or concurrent borderline personality disorder, and (2) a healthy control group. We investigated whether differences in behavioral patterns could be observed at the group level, that is, patients versus healthy controls. We studied the volume and temporal patterns of smartphone screen and app use, communication, sleep, mobility, and physical activity. We investigated whether patients or controls exhibited more homogenous temporal patterns of activity when compared with other individuals in the same group. We examined which variables were associated with the severity of depression. Methods: In total, 188 participants were recruited to complete a 2-phase study. In the first 2 weeks, data from bed sensors, actigraphy, smartphones, and 5 sets of daily questions were collected. In the second phase, which lasted up to 1 year, only passive smartphone data and biweekly 9-item Patient Health Questionnaire data were collected. Survival analysis, statistical tests, and linear mixed models were performed. Results: Survival analysis showed no statistically significant difference in adherence. Most participants did not stay in the study for 1 year. Weekday location variance showed lower values for patients (control: mean --10.04, SD 2.73; patient: mean --11.91, SD 2.50; Mann-Whitney U [MWU] test P=.004). Normalized entropy of location was lower among patients (control: mean 2.10, SD 1.38; patient: mean 1.57, SD 1.10; MWU test P=.05). The temporal communication patterns of controls were more diverse compared to those of patients (MWU test P<.001). In contrast, patients exhibited more varied temporal patterns of smartphone use compared to the controls. We found that the duration of incoming calls ($\beta$=--0.08, 95\% CI --0.12 to --0.04; P<.001) and the SD of activity magnitude ($\beta$=--2.05, 95\% CI --4.18 to --0.20; P=.02) over the 14 days before the 9-item Patient Health Questionnaire records were negatively associated with depression severity. Conversely, the duration of outgoing calls showed a positive association with depression severity ($\beta$=0.05, 95\% CI 0.00-0.09; P=.02). Conclusions: Our work shows the important features for future analyses of behavioral markers of mood disorders. However, among outpatients with mild to moderate depressive disorders, the group-level differences from healthy controls in any single modality remain relatively modest. Therefore, future studies need to combine data from multiple modalities to detect more subtle differences and identify individualized signatures. The high dropout rates for longer study periods remain a challenge and limit the generalizability. ",
doi="10.2196/63622",
url="https://mental.jmir.org/2025/1/e63622"
}


@Article{info:doi/10.2196/62851,
author="Fu, Yao
and Huang, Zongyao
and Deng, Xudong
and Xu, Linna
and Liu, Yang
and Zhang, Mingxing
and Liu, Jinyi
and Huang, Bin",
title="Artificial Intelligence in Lymphoma Histopathology: Systematic Review",
journal="J Med Internet Res",
year="2025",
month="Feb",
day="14",
volume="27",
pages="e62851",
keywords="lymphoma",
keywords="artificial intelligence",
keywords="bias",
keywords="histopathology",
keywords="tumor",
keywords="hematological",
keywords="lymphatic disease",
keywords="public health",
keywords="pathologists",
keywords="pathology",
keywords="immunohistochemistry",
keywords="diagnosis",
keywords="prognosis",
abstract="Background: Artificial intelligence (AI) shows considerable promise in the areas of lymphoma diagnosis, prognosis, and gene prediction. However, a comprehensive assessment of potential biases and the clinical utility of AI models is still needed. Objective: Our goal was to evaluate the biases of published studies using AI models for lymphoma histopathology and assess the clinical utility of comprehensive AI models for diagnosis or prognosis. Methods: This study adhered to the Systematic Review Reporting Standards. A comprehensive literature search was conducted across PubMed, Cochrane Library, and Web of Science from their inception until August 30, 2024. The search criteria included the use of AI for prognosis involving human lymphoma tissue pathology images, diagnosis, gene mutation prediction, etc. The risk of bias was evaluated using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Information for each AI model was systematically tabulated, and summary statistics were reported. The study is registered with PROSPERO (CRD42024537394) and follows the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 reporting guidelines. Results: The search identified 3565 records, with 41 articles ultimately meeting the inclusion criteria. A total of 41 AI models were included in the analysis, comprising 17 diagnostic models, 10 prognostic models, 2 models for detecting ectopic gene expression, and 12 additional models related to diagnosis. All studies exhibited a high or unclear risk of bias, primarily due to limited analysis and incomplete reporting of participant recruitment. Most high-risk models (10/41) predominantly assigned high-risk classifications to participants. Almost all the articles presented an unclear risk of bias in at least one domain, with the most frequent being participant selection (16/41) and statistical analysis (37/41). The primary reasons for this were insufficient analysis of participant recruitment and a lack of interpretability in outcome analyses. In the diagnostic models, the most frequently studied lymphoma subtypes were diffuse large B-cell lymphoma, follicular lymphoma, chronic lymphocytic leukemia, and mantle cell lymphoma, while in the prognostic models, the most common subtypes were diffuse large B-cell lymphoma, follicular lymphoma, chronic lymphocytic leukemia, and Hodgkin lymphoma. In the internal validation results of all models, the area under the receiver operating characteristic curve (AUC) ranged from 0.75 to 0.99 and accuracy ranged from 68.3\% to 100\%. In models with external validation results, the AUC ranged from 0.93 to 0.99. Conclusions: From a methodological perspective, all models exhibited biases. The enhancement of the accuracy of AI models and the acceleration of their clinical translation hinge on several critical aspects. These include the comprehensive reporting of data sources, the diversity of datasets, the study design, the transparency and interpretability of AI models, the use of cross-validation and external validation, and adherence to regulatory guidance and standardized processes in the field of medical AI. ",
doi="10.2196/62851",
url="https://www.jmir.org/2025/1/e62851"
}


@Article{info:doi/10.2196/59015,
author="Shimada, Hiroyuki
and Doi, Takehiko
and Tsutsumimoto, Kota
and Makino, Keitaro
and Harada, Kenji
and Tomida, Kouki
and Morikawa, Masanori
and Makizako, Hyuma",
title="A New Computer-Based Cognitive Measure for Early Detection of Dementia Risk (Japan Cognitive Function Test): Validation Study",
journal="J Med Internet Res",
year="2025",
month="Feb",
day="14",
volume="27",
pages="e59015",
keywords="cognition",
keywords="neurocognitive test",
keywords="dementia",
keywords="Alzheimer disease",
keywords="aged",
keywords="MMSE",
keywords="cognitive impairment",
keywords="Mini-Mental State Examination",
keywords="monitoring",
keywords="eHealth",
abstract="Background: The emergence of disease-modifying treatment options for Alzheimer disease is creating a paradigm shift in strategies to identify patients with mild symptoms in primary care settings. Systematic reviews on digital cognitive tests reported that most showed diagnostic performance comparable with that of paper-and-pencil tests for mild cognitive impairment and dementia. However, most studies have small sample sizes, with fewer than 100 individuals, and are based on case-control or cross-sectional designs. Objective: This study aimed to examine the predictive validity of the Japanese Cognitive Function Test (J-Cog), a new computerized cognitive battery test, for dementia development. Methods: We randomly assigned 2520 older adults (average age 72.7, SD 6.7 years) to derivation and validation groups to determine and validate cutoff points for the onset of dementia. The Mini-Mental State Examination (MMSE) was used for comparison purposes. The J-Cog consists of 12 tasks that assess orientation, designation, attention and calculation, mental rotation, verbal fluency, sentence completion, working memory, logical reasoning, attention, common knowledge, word memory recall, and episodic memory recall. The onset of dementia was monitored for 60 months. In the derivation group, receiver operating characteristic curves were plotted to determine the MMSE and J-Cog cutoff points that best discriminated between the groups with and without dementia. In the validation group, Cox proportional regression models were developed to predict the associations of the group classified using the cutoff points of the J-Cog or MMSE with dementia incidence. Harrell C-statistic was estimated to summarize how well a predicted risk score described an observed sequence of events. The Akaike information criterion was calculated for relative goodness of fit, where lower absolute values indicate a better model fit. Results: Significant hazard ratios (HRs) for dementia incidence were found using the MMSE cutoff between 23 and 24 point (HR 1.93, 95\% CI 1.13-3.27) and the J-Cog cutoff between 43 and 44 points (HR 2.42, 95\% CI 1.50-3.93). In the total validation group, the C-statistic was above 0.8 for all cutoff points. Akaike information criterion with MMSE cutoff between 23 and 24 points as a reference showed a poor fit for MMSE cutoff between 28 and 29 points, and a good fit for the J-Cog cutoff between 43 and 44 points. Conclusions: The J-Cog has higher accuracy in predicting the development of dementia than the MMSE and has advantages for use in the community as a test of cognitive function, which can be administered by nonprofessionals. ",
doi="10.2196/59015",
url="https://www.jmir.org/2025/1/e59015"
}


@Article{info:doi/10.2196/64624,
author="Rubaiat, Rahmina
and Templeton, Michael John
and Schneider, L. Sandra
and De Silva, Upeka
and Madanian, Samaneh
and Poellabauer, Christian",
title="Exploring Speech Biosignatures for Traumatic Brain Injury and Neurodegeneration: Pilot Machine Learning Study",
journal="JMIR Neurotech",
year="2025",
month="Feb",
day="12",
volume="4",
pages="e64624",
keywords="speech biosignatures",
keywords="speech feature analysis",
keywords="amyotrophic lateral sclerosis",
keywords="ALS",
keywords="neurodegenerative disease",
keywords="Parkinson's disease",
keywords="detection",
keywords="speech",
keywords="neurological",
keywords="traumatic brain injury",
keywords="concussion",
keywords="mobile device",
keywords="digital health",
keywords="machine learning",
keywords="mobile health",
keywords="diagnosis",
keywords="mobile phone",
abstract="Background: Speech features are increasingly linked to neurodegenerative and mental health conditions, offering the potential for early detection and differentiation between disorders. As interest in speech analysis grows, distinguishing between conditions becomes critical for reliable diagnosis and assessment. Objective: This pilot study explores speech biosignatures in two distinct neurodegenerative conditions: (1) mild traumatic brain injuries (eg, concussions) and (2) Parkinson disease (PD) as the neurodegenerative condition. Methods: The study included speech samples from 235 participants (97 concussed and 94 age-matched healthy controls, 29 PD and 15 healthy controls) for the PaTaKa test and 239 participants (91 concussed and 104 healthy controls, 29 PD and 15 healthy controls) for the Sustained Vowel (/ah/) test. Age-matched healthy controls were used. Young age-matched controls were used for concussion and respective age-matched controls for neurodegenerative participants (15 healthy samples for both tests). Data augmentation with noise was applied to balance small datasets for neurodegenerative and healthy controls. Machine learning models (support vector machine, decision tree, random forest, and Extreme Gradient Boosting) were employed using 37 temporal and spectral speech features. A 5-fold stratified cross-validation was used to evaluate classification performance. Results: For the PaTaKa test, classifiers performed well, achieving F1-scores above 0.9 for concussed versus healthy and concussed versus neurodegenerative classifications across all models. Initial tests using the original dataset for neurodegenerative versus healthy classification yielded very poor results, with F1-scores below 0.2 and accuracy under 30\% (eg, below 12 out of 44 correctly classified samples) across all models. This underscored the need for data augmentation, which significantly improved performance to 60\%?70\% (eg, 26?31 out of 44 samples) accuracy. In contrast, the Sustained Vowel test showed mixed results; F1-scores remained high (more than 0.85 across all models) for concussed versus neurodegenerative classifications but were significantly lower for concussed versus healthy (0.59?0.62) and neurodegenerative versus healthy (0.33?0.77), depending on the model. Conclusions: This study highlights the potential of speech features as biomarkers for neurodegenerative conditions. The PaTaKa test exhibited strong discriminative ability, especially for concussed versus neurodegenerative and concussed versus healthy tasks, whereas challenges remain for neurodegenerative versus healthy classification. These findings emphasize the need for further exploration of speech-based tools for differential diagnosis and early identification in neurodegenerative health. ",
doi="10.2196/64624",
url="https://neuro.jmir.org/2025/1/e64624"
}


@Article{info:doi/10.2196/48775,
author="Bhavnani, K. Suresh
and Zhang, Weibin
and Bao, Daniel
and Raji, Mukaila
and Ajewole, Veronica
and Hunter, Rodney
and Kuo, Yong-Fang
and Schmidt, Susanne
and Pappadis, R. Monique
and Smith, Elise
and Bokov, Alex
and Reistetter, Timothy
and Visweswaran, Shyam
and Downer, Brian",
title="Subtyping Social Determinants of Health in the ``All of Us'' Program: Network Analysis and Visualization Study",
journal="J Med Internet Res",
year="2025",
month="Feb",
day="11",
volume="27",
pages="e48775",
keywords="social determinants of health",
keywords="All of Us",
keywords="bipartite networks",
keywords="financial resources",
keywords="health care",
keywords="health outcomes",
keywords="precision medicine",
keywords="decision support",
keywords="health industry",
keywords="clinical implications",
keywords="machine learning methods",
abstract="Background: Social determinants of health (SDoH), such as financial resources and housing stability, account for between 30\% and 55\% of people's health outcomes. While many studies have identified strong associations between specific SDoH and health outcomes, little is known about how SDoH co-occur to form subtypes critical for designing targeted interventions. Such analysis has only now become possible through the All of Us program. Objective: This study aims to analyze the All of Us dataset for addressing two research questions: (1) What are the range of and responses to survey questions related to SDoH? and (2) How do SDoH co-occur to form subtypes, and what are their risks for adverse health outcomes? Methods: For question 1, an expert panel analyzed the range of and responses to SDoH questions across 6 surveys in the full All of Us dataset (N=372,397; version 6). For question 2, due to systematic missingness and uneven granularity of questions across the surveys, we selected all participants with valid and complete SDoH data and used inverse probability weighting to adjust their imbalance in demographics. Next, an expert panel grouped the SDoH questions into SDoH factors to enable more consistent granularity. To identify the subtypes, we used bipartite modularity maximization for identifying SDoH biclusters and measured their significance and replicability. Next, we measured their association with 3 outcomes (depression, delayed medical care, and emergency room visits in the last year). Finally, the expert panel inferred the subtype labels, potential mechanisms, and targeted interventions. Results: The question 1 analysis identified 110 SDoH questions across 4 surveys covering all 5 domains in Healthy People 2030. As the SDoH questions varied in granularity, they were categorized by an expert panel into 18 SDoH factors. The question 2 analysis (n=12,913; d=18) identified 4 biclusters with significant biclusteredness (Q=0.13; random-Q=0.11; z=7.5; P<.001) and significant replication (real Rand index=0.88; random Rand index=0.62; P<.001). Each subtype had significant associations with specific outcomes and had meaningful interpretations and potential targeted interventions. For example, the Socioeconomic barriers subtype included 6 SDoH factors (eg, not employed and food insecurity) and had a significantly higher odds ratio (4.2, 95\% CI 3.5-5.1; P<.001) for depression when compared to other subtypes. The expert panel inferred implications of the results for designing interventions and health care policies based on SDoH subtypes. Conclusions: This study identified SDoH subtypes that had statistically significant biclusteredness and replicability, each of which had significant associations with specific adverse health outcomes and with translational implications for targeted SDoH interventions and health care policies. However, the high degree of systematic missingness requires repeating the analysis as the data become more complete by using our generalizable and scalable machine learning code available on the All of Us workbench. ",
doi="10.2196/48775",
url="https://www.jmir.org/2025/1/e48775",
url="http://www.ncbi.nlm.nih.gov/pubmed/39932771"
}


@Article{info:doi/10.2196/59161,
author="Lee, Kyungmi
and Azuero, Andres
and Engler, Sally
and Kumar, Sidharth
and Puga, Frank
and Wright, A. Alexi
and Kamal, Arif
and Ritchie, S. Christine
and Demiris, George
and Bakitas, A. Marie
and Odom, Nicholas J.",
title="Exploring the Relationship Between Smartphone GPS Patterns and Quality of Life in Patients With Advanced Cancer and Their Family Caregivers: Longitudinal Study",
journal="JMIR Form Res",
year="2025",
month="Feb",
day="7",
volume="9",
pages="e59161",
keywords="cancer",
keywords="digital phenotyping",
keywords="global positioning system",
keywords="quality of life",
keywords="smartphone",
keywords="mobile phone",
keywords="family caregiver",
abstract="Background: Patients with advanced cancer and their family caregivers often experience poor quality of life (QOL). Self-report measures are commonly used to quantify QOL of family caregivers but may have limitations such as recall bias and social desirability bias. Variables derived from passively obtained smartphone GPS data are a novel approach to measuring QOL that may overcome these limitations and enable detection of early signs of mental and physical health (PH) deterioration. Objective: This study explored the feasibility of a digital phenotyping approach by assessing participant adherence and examining correlations between smartphone GPS data and QOL levels among family caregivers and patients with advanced cancer. Methods: This was a secondary analysis involving 7 family caregivers and 4 patients with advanced cancer that assessed correlations between GPS sensor data captured by a personally owned smartphone and QOL self-report measures over 12 weeks through linear correlation coefficients. QOL as measured by the Patient-Reported Outcomes Measurement Information System (PROMIS) Global Health 10 was collected at baseline, 6, and 12 weeks. Using a Beiwe smartphone app, GPS data were collected and processed into variables including total distance, time spent at home, transition time, and number of significant locations. Results: The study identified relevant temporal correlations between QOL and smartphone GPS data across specific time periods. For instance, in terms of PH, associations were observed with the total distance traveled (12 and 13 wk, with r ranging 0.37 to 0.38), time spent at home (?4 to ?2 wk, with r ranging from ?0.41 to ?0.49), and transition time (?4 to ?2 wk, with r ranging ?0.38 to ?0.47). Conclusions: This research offers insights into using passively obtained smartphone GPS data as a novel approach for assessing and monitoring QOL among family caregivers and patients with advanced cancer, presenting potential advantages over traditional self-report measures. The observed correlations underscore the potential of this method to detect early signs of deteriorating mental health and PH, providing opportunities for timely intervention and support. ",
doi="10.2196/59161",
url="https://formative.jmir.org/2025/1/e59161"
}


@Article{info:doi/10.2196/56185,
author="Yang, Zixu
and Heaukulani, Creighton
and Sim, Amelia
and Buddhika, Thisum
and Abdul Rashid, Amirah Nur
and Wang, Xuancong
and Zheng, Shushan
and Quek, Feng Yue
and Basu, Sutapa
and Lee, Wei Kok
and Tang, Charmaine
and Verma, Swapna
and Morris, T. Robert J.
and Lee, Jimmy",
title="Utility of Digital Phenotyping Based on Wrist Wearables and Smartphones in Psychosis: Observational Study",
journal="JMIR Mhealth Uhealth",
year="2025",
month="Feb",
day="5",
volume="13",
pages="e56185",
keywords="schizophrenia",
keywords="psychosis",
keywords="digital phenotyping",
keywords="wrist wearables",
keywords="mobile phone",
abstract="Background: Digital phenotyping provides insights into an individual's digital behaviors and has potential clinical utility. Objective: In this observational study, we explored digital biomarkers collected from wrist-wearable devices and smartphones and their associations with clinical symptoms and functioning in patients with schizophrenia. Methods: We recruited 100 outpatients with schizophrenia spectrum disorder, and we collected various digital data from commercially available wrist wearables and smartphones over a 6-month period. In this report, we analyzed the first week of digital data on heart rate, sleep, and physical activity from the wrist wearables and travel distance, sociability, touchscreen tapping speed, and screen time from the smartphones. We analyzed the relationships between these digital measures and patient baseline measurements of clinical symptoms assessed with the Positive and Negative Syndrome Scale, Brief Negative Symptoms Scale, and Calgary Depression Scale for Schizophrenia, as well as functioning as assessed with the Social and Occupational Functioning Assessment Scale. Linear regression was performed for each digital and clinical measure independently, with the digital measures being treated as predictors. Results: Digital data were successfully collected from both the wearables and smartphones throughout the study, with 91\% of the total possible data successfully collected from the wearables and 82\% from the smartphones during the first week of the trial---the period under analysis in this report. Among the clinical outcomes, negative symptoms were associated with the greatest number of digital measures (10 of the 12 studied here), followed by overall measures of psychopathology symptoms, functioning, and positive symptoms, which were each associated with at least 3 digital measures. Cognition and cognitive/disorganization symptoms were each associated with 1 or 2 digital measures. Conclusions: We found significant associations between nearly all digital measures and a wide range of symptoms and functioning in a community sample of individuals with schizophrenia. These findings provide insights into the digital behaviors of individuals with schizophrenia and highlight the potential of using commercially available wrist wearables and smartphones for passive monitoring in schizophrenia. International Registered Report Identifier (IRRID): RR2-10.1136/bmjopen-2020-046552 ",
doi="10.2196/56185",
url="https://mhealth.jmir.org/2025/1/e56185"
}


@Article{info:doi/10.2196/69320,
author="Ahn, Seon Ji
and Jeong, InJi
and Park, Sehwan
and Lee, Jooho
and Jeon, Minjeong
and Lee, Sangil
and Do, Gangho
and Jung, Dooyoung
and Park, Young Jin",
title="App-Based Ecological Momentary Assessment of Problematic Smartphone Use During Examination Weeks in University Students: 6-Week Observational Study",
journal="J Med Internet Res",
year="2025",
month="Feb",
day="5",
volume="27",
pages="e69320",
keywords="problematic smartphone use",
keywords="PSU",
keywords="ecological momentary assessment",
keywords="EMA",
keywords="GPS tracking",
keywords="digital phenotypes",
keywords="psychosocial measures",
keywords="university students",
keywords="academic stress",
keywords="mobile health",
keywords="mHealth",
keywords="mobile phone",
abstract="Background: The increasing prevalence of problematic smartphone use (PSU) among university students is raising concerns, particularly as excessive smartphone engagement is linked to negative outcomes such as mental health issues, academic underperformance, and sleep disruption. Despite the severity of PSU, its association with behaviors such as physical activity, mobility, and sociability has received limited research attention. Ecological momentary assessment (EMA), including passive data collection through digital phenotyping indicators, offers an objective approach to explore these behavioral patterns. Objective: This study aimed to examine associations between self-reported psychosocial measures; app-based EMA data, including daily behavioral indicators from GPS location tracking; and PSU in university students during the examination period. Methods: A 6-week observational study involving 243 university students was conducted using app-based EMA on personal smartphones to collect data on daily behaviors and psychosocial factors related to smartphone overuse. PSU was assessed using the Korean Smartphone Addiction Proneness Scale. Data collected from the Big4+ app, including self-reports on mood, sleep, and appetite, as well as passive sensor data (GPS location, acceleration, and steps) were used to evaluate overall health. Logistic regression analysis was conducted to identify factors that significantly influenced smartphone overuse, providing insights into daily behavior and mental health patterns. Results: In total, 23\% (56/243) of the students exhibited PSU. The regression analysis revealed significant positive associations between PSU and several factors, including depression (Patient Health Questionnaire-9; odds ratio [OR] 8.48, 95\% CI 1.95-36.87; P=.004), social interaction anxiety (Social Interaction Anxiety Scale; OR 4.40, 95\% CI 1.59-12.15; P=.004), sleep disturbances (General Sleep Disturbance Scale; OR 3.44, 95\% CI 1.15-10.30; P=.03), and longer sleep duration (OR 3.11, 95\% CI 1.14-8.48; P=.03). Conversely, a significant negative association was found between PSU and time spent at home (OR 0.35, 95\% CI 0.13-0.94; P=.04). Conclusions: This study suggests that negative self-perceptions of mood and sleep, along with patterns of increased mobility identified through GPS data, increase the risk of PSU, particularly during periods of academic stress. Combining psychosocial assessments with EMA data offers valuable insights for managing PSU during high-stress periods, such as examinations, and provides new directions for future research. ",
doi="10.2196/69320",
url="https://www.jmir.org/2025/1/e69320"
}


@Article{info:doi/10.2196/55308,
author="Terhorst, Yannik
and Messner, Eva-Maria
and Opoku Asare, Kennedy
and Montag, Christian
and Kannen, Christopher
and Baumeister, Harald",
title="Investigating Smartphone-Based Sensing Features for Depression Severity Prediction: Observation Study",
journal="J Med Internet Res",
year="2025",
month="Jan",
day="30",
volume="27",
pages="e55308",
keywords="smart sensing",
keywords="digital phenotyping",
keywords="depression",
keywords="observation study",
keywords="smartphone",
keywords="mHealth",
keywords="mobile health",
keywords="app",
keywords="mental health",
keywords="symptoms",
keywords="assessments",
abstract="Background: Unobtrusively collected objective sensor data from everyday devices like smartphones provide a novel paradigm to infer mental health symptoms. This process, called smart sensing, allows a fine-grained assessment of various features (eg, time spent at home based on the GPS sensor). Based on its prevalence and impact, depression is a promising target for smart sensing. However, currently, it is unclear which sensor-based features should be used in depression severity prediction and if they hold an incremental benefit over established fine-grained assessments like the ecological momentary assessment (EMA). Objective: The aim of this study was to investigate various features based on the smartphone screen, app usage, and call sensor alongside EMA to infer depression severity. Bivariate, cluster-wise, and cluster-combined analyses were conducted to determine the incremental benefit of smart sensing features compared to each other and EMA in parsimonious regression models for depression severity. Methods: In this exploratory observational study, participants were recruited from the general population. Participants needed to be 18 years of age, provide written informed consent, and own an Android-based smartphone. Sensor data and EMA were collected via the INSIGHTS app. Depression severity was assessed using the 8-item Patient Health Questionnaire. Missing data were handled by multiple imputations. Correlation analyses were conducted for bivariate associations; stepwise linear regression analyses were used to find the best prediction models for depression severity. Models were compared by adjusted R2. All analyses were pooled across the imputed datasets according to Rubin's rule. Results: A total of 107 participants were included in the study. Ages ranged from 18 to 56 (mean 22.81, SD 7.32) years, and 78\% of the participants identified as female. Depression severity was subclinical on average (mean 5.82, SD 4.44; Patient Health Questionnaire score ?10: 18.7\%). Small to medium correlations were found for depression severity and EMA (eg, valence: r=--0.55, 95\% CI --0.67 to --0.41), and there were small correlations with sensing features (eg, screen duration: r=0.37, 95\% CI 0.20 to 0.53). EMA features could explain 35.28\% (95\% CI 20.73\% to 49.64\%) of variance and sensing features (adjusted R2=20.45\%, 95\% CI 7.81\% to 35.59\%). The best regression model contained EMA and sensing features (R2=45.15\%, 95\% CI 30.39\% to 58.53\%). Conclusions: Our findings underline the potential of smart sensing and EMA to infer depression severity as isolated paradigms and when combined. Although these could become important parts of clinical decision support systems for depression diagnostics and treatment in the future, confirmatory studies are needed before they can be applied to routine care. Furthermore, privacy, ethical, and acceptance issues need to be addressed. ",
doi="10.2196/55308",
url="https://www.jmir.org/2025/1/e55308",
url="http://www.ncbi.nlm.nih.gov/pubmed/39883512"
}


@Article{info:doi/10.2196/60521,
author="Smits Serena, Ricardo
and Hinterwimmer, Florian
and Burgkart, Rainer
and von Eisenhart-Rothe, Rudiger
and Rueckert, Daniel",
title="The Use of Artificial Intelligence and Wearable Inertial Measurement Units in Medicine: Systematic Review",
journal="JMIR Mhealth Uhealth",
year="2025",
month="Jan",
day="29",
volume="13",
pages="e60521",
keywords="artificial intelligence",
keywords="accelerometer",
keywords="gyroscope",
keywords="IMUs",
keywords="time series data",
keywords="wearable",
keywords="systematic review",
keywords="patient care",
keywords="machine learning",
keywords="data collection",
abstract="Background: Artificial intelligence (AI) has already revolutionized the analysis of image, text, and tabular data, bringing significant advances across many medical sectors. Now, by combining with wearable inertial measurement units (IMUs), AI could transform health care again by opening new opportunities in patient care and medical research. Objective: This systematic review aims to evaluate the integration of AI models with wearable IMUs in health care, identifying current applications, challenges, and future opportunities. The focus will be on the types of models used, the characteristics of the datasets, and the potential for expanding and enhancing the use of this technology to improve patient care and advance medical research. Methods: This study examines this synergy of AI models and IMU data by using a systematic methodology, following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, to explore 3 core questions: (1) Which medical fields are most actively researching AI and IMU data? (2) Which models are being used in the analysis of IMU data within these medical fields? (3) What are the characteristics of the datasets used for in this fields? Results: The median dataset size is of 50 participants, which poses significant limitations for AI models given their dependency on large datasets for effective training and generalization. Furthermore, our analysis reveals the current dominance of machine learning models in 76\% on the surveyed studies, suggesting a preference for traditional models like linear regression, support vector machine, and random forest, but also indicating significant growth potential for deep learning models in this area. Impressively, 93\% of the studies used supervised learning, revealing an underuse of unsupervised learning, and indicating an important area for future exploration on discovering hidden patterns and insights without predefined labels or outcomes. In addition, there was a preference for conducting studies in clinical settings (77\%), rather than in real-life scenarios, a choice that, along with the underapplication of the full potential of wearable IMUs, is recognized as a limitation in terms of practical applicability. Furthermore, the focus of 65\% of the studies on neurological issues suggests an opportunity to broaden research scope to other clinical areas such as musculoskeletal applications, where AI could have significant impacts. Conclusions: In conclusion, the review calls for a collaborative effort to address the highlighted challenges, including improvements in data collection, increasing dataset sizes, a move that inherently pushes the field toward the adoption of more complex deep learning models, and the expansion of the application of AI models on IMU data methodologies across various medical fields. This approach aims to enhance the reliability, generalizability, and clinical applicability of research findings, ultimately improving patient outcomes and advancing medical research. ",
doi="10.2196/60521",
url="https://mhealth.jmir.org/2025/1/e60521"
}


@Article{info:doi/10.2196/63809,
author="Thomas, Julia
and Lucht, Antonia
and Segler, Jacob
and Wundrack, Richard
and Mich{\'e}, Marcel
and Lieb, Roselind
and Kuchinke, Lars
and Meinlschmidt, Gunther",
title="An Explainable Artificial Intelligence Text Classifier for Suicidality Prediction in Youth Crisis Text Line Users: Development and Validation Study",
journal="JMIR Public Health Surveill",
year="2025",
month="Jan",
day="29",
volume="11",
pages="e63809",
keywords="deep learning",
keywords="explainable artificial intelligence (XAI)",
keywords="large language model (LLM)",
keywords="machine learning",
keywords="neural network",
keywords="prevention",
keywords="risk monitoring",
keywords="suicide",
keywords="transformer model",
keywords="suicidality",
keywords="suicidal ideation",
keywords="self-murder",
keywords="self-harm",
keywords="youth",
keywords="adolescent",
keywords="adolescents",
keywords="public health",
keywords="language model",
keywords="language models",
keywords="chat protocols",
keywords="crisis helpline",
keywords="help-seeking behaviors",
keywords="German",
keywords="Shapley",
keywords="decision-making",
keywords="mental health",
keywords="health informatics",
keywords="mobile phone",
abstract="Background: Suicide represents a critical public health concern, and machine learning (ML) models offer the potential for identifying at-risk individuals. Recent studies using benchmark datasets and real-world social media data have demonstrated the capability of pretrained large language models in predicting suicidal ideation and behaviors (SIB) in speech and text. Objective: This study aimed to (1) develop and implement ML methods for predicting SIBs in a real-world crisis helpline dataset, using transformer-based pretrained models as a foundation; (2) evaluate, cross-validate, and benchmark the model against traditional text classification approaches; and (3) train an explainable model to highlight relevant risk-associated features. Methods: We analyzed chat protocols from adolescents and young adults (aged 14-25 years) seeking assistance from a German crisis helpline. An ML model was developed using a transformer-based language model architecture with pretrained weights and long short-term memory layers. The model predicted suicidal ideation (SI) and advanced suicidal engagement (ASE), as indicated by composite Columbia-Suicide Severity Rating Scale scores. We compared model performance against a classical word-vector-based ML model. We subsequently computed discrimination, calibration, clinical utility, and explainability information using a Shapley Additive Explanations value-based post hoc estimation model. Results: The dataset comprised 1348 help-seeking encounters (1011 for training and 337 for testing). The transformer-based classifier achieved a macroaveraged area under the curve (AUC) receiver operating characteristic (ROC) of 0.89 (95\% CI 0.81-0.91) and an overall accuracy of 0.79 (95\% CI 0.73-0.99). This performance surpassed the word-vector-based baseline model (AUC-ROC=0.77, 95\% CI 0.64-0.90; accuracy=0.61, 95\% CI 0.61-0.80). The transformer model demonstrated excellent prediction for nonsuicidal sessions (AUC-ROC=0.96, 95\% CI 0.96-0.99) and good prediction for SI and ASE, with AUC-ROCs of 0.85 (95\% CI 0.97-0.86) and 0.87 (95\% CI 0.81-0.88), respectively. The Brier Skill Score indicated a 44\% improvement in classification performance over the baseline model. The Shapley Additive Explanations model identified language features predictive of SIBs, including self-reference, negation, expressions of low self-esteem, and absolutist language. Conclusions: Neural networks using large language model--based transfer learning can accurately identify SI and ASE. The post hoc explainer model revealed language features associated with SI and ASE. Such models may potentially support clinical decision-making in suicide prevention services. Future research should explore multimodal input features and temporal aspects of suicide risk. ",
doi="10.2196/63809",
url="https://publichealth.jmir.org/2025/1/e63809"
}


@Article{info:doi/10.2196/62914,
author="Scribano Parada, Paz Mar{\'i}a de la
and Gonz{\'a}lez Palau, F{\'a}tima
and Valladares Rodr{\'i}guez, Sonia
and Rincon, Mariano
and Rico Barroeta, Jos{\'e} Maria
and Garc{\'i}a Rodriguez, Marta
and Bueno Aguado, Yolanda
and Herrero Blanco, Ana
and D{\'i}az-L{\'o}pez, Estela
and Bachiller Mayoral, Margarita
and Losada Dur{\'a}n, Raquel",
title="Preclinical Cognitive Markers of Alzheimer Disease and Early Diagnosis Using Virtual Reality and Artificial Intelligence: Literature Review",
journal="JMIR Med Inform",
year="2025",
month="Jan",
day="28",
volume="13",
pages="e62914",
keywords="dementia",
keywords="Alzheimer disease",
keywords="mild cognitive impairment",
keywords="virtual reality",
keywords="artificial intelligence",
keywords="early detection",
keywords="qualitative review",
keywords="literature review",
keywords="AI",
abstract="Background: This review explores the potential of virtual reality (VR) and artificial intelligence (AI) to identify preclinical cognitive markers of Alzheimer disease (AD). By synthesizing recent studies, it aims to advance early diagnostic methods to detect AD before significant symptoms occur. Objective: Research emphasizes the significance of early detection in AD during the preclinical phase, which does not involve cognitive impairment but nevertheless requires reliable biomarkers. Current biomarkers face challenges, prompting the exploration of cognitive behavior indicators beyond episodic memory. Methods: Using PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we searched Scopus, PubMed, and Google Scholar for studies on neuropsychiatric disorders utilizing conversational data. Results: Following an analysis of 38 selected articles, we highlight verbal episodic memory as a sensitive preclinical AD marker, with supporting evidence from neuroimaging and genetic profiling. Executive functions precede memory decline, while processing speed is a significant correlate. The potential of VR remains underexplored, and AI algorithms offer a multidimensional approach to early neurocognitive disorder diagnosis. Conclusions: Emerging technologies like VR and AI show promise for preclinical diagnostics, but thorough validation and regulation for clinical safety and efficacy are necessary. Continued technological advancements are expected to enhance early detection and management of AD. ",
doi="10.2196/62914",
url="https://medinform.jmir.org/2025/1/e62914"
}


@Article{info:doi/10.2196/51689,
author="Sahandi Far, Mehran
and Fischer, M. Jona
and Senge, Svea
and Rathmakers, Robin
and Meissner, Thomas
and Schneble, Dominik
and Narava, Mamaka
and Eickhoff, B. Simon
and Dukart, Juergen",
title="Cross-Platform Ecological Momentary Assessment App (JTrack-EMA+): Development and Usability Study",
journal="J Med Internet Res",
year="2025",
month="Jan",
day="28",
volume="27",
pages="e51689",
keywords="digital biomarkers",
keywords="mobile health",
keywords="remote monitoring",
keywords="smartphone",
keywords="mobile phone",
keywords="monitoring",
keywords="biomarker",
keywords="ecological momentary assessment",
keywords="application",
keywords="costly",
keywords="user experience",
keywords="data management",
keywords="mobility",
abstract="Background: Traditional in-clinic methods of collecting self-reported information are costly, time-consuming, subjective, and often limited in the quality and quantity of observation. However, smartphone-based ecological momentary assessments (EMAs) provide complementary information to in-clinic visits by collecting real-time, frequent, and longitudinal data that are ecologically valid. While these methods are promising, they are often prone to various technical obstacles. However, despite the potential of smartphone-based EMAs, they face technical obstacles that impact adaptability, availability, and interoperability across devices and operating systems. Deficiencies in these areas can contribute to selection bias by excluding participants with unsupported devices or limited digital literacy, increase development and maintenance costs, and extend deployment timelines. Moreover, these limitations not only impede the configurability of existing solutions but also hinder their adoption for addressing diverse clinical challenges. Objective: The primary aim of this research was to develop a cross-platform EMA app that ensures a uniform user experience and core features across various operating systems. Emphasis was placed on maximizing the integration and adaptability to various study designs, all while maintaining strict adherence to security and privacy protocols. JTrack-EMA+ was designed and implemented per the FAIR (findable, accessible, interpretable, and reusable) principles in both its architecture and data management layers, thereby reducing the burden of integration for clinicians and researchers. Methods: JTrack-EMA+ was built using the Flutter framework, enabling it to run seamlessly across different platforms. This platform comprises two main components. JDash (Research Centre J{\"u}lich, Institute of Neuroscience and Medicine, Brain and Behaviour [INM-7]) is an online management tool created using Python (Python Software Foundation) with the Django (Django Software Foundation) framework. This online dashboard offers comprehensive study management tools, including assessment design, user administration, data quality control, and a reminder casting center. The JTrack-EMA+ app supports a wide range of question types, allowing flexibility in assessment design. It also has configurable assessment logic and the ability to include supplementary materials for a richer user experience. It strongly commits to security and privacy and complies with the General Data Protection Regulations to safeguard user data and ensure confidentiality. Results: We investigated our platform in a pilot study with 480 days of follow-up to assess participants' compliance. The 6-month average compliance was 49.3\%, significantly declining (P=.004) from 66.7\% in the first month to 42\% in the sixth month. Conclusions: The JTrack-EMA+ platform prioritizes platform-independent architecture, providing an easy entry point for clinical researchers to deploy EMA in their respective clinical studies. Remote and home-based assessments of EMA using this platform can provide valuable insights into patients' daily lives, particularly in a population with limited mobility or inconsistent access to health care services. ",
doi="10.2196/51689",
url="https://www.jmir.org/2025/1/e51689"
}


@Article{info:doi/10.2196/67478,
author="Yeom, Won Ji
and Kim, Hyungju
and Pack, Pil Seung
and Lee, Heon-Jeong
and Cheong, Taesu
and Cho, Chul-Hyun",
title="Exploring the Psychological and Physiological Insights Through Digital Phenotyping by Analyzing the Discrepancies Between Subjective Insomnia Severity and Activity-Based Objective Sleep Measures: Observational Cohort Study",
journal="JMIR Ment Health",
year="2025",
month="Jan",
day="27",
volume="12",
pages="e67478",
keywords="insomnia",
keywords="wearable devices",
keywords="sleep quality",
keywords="subjective assessment",
keywords="digital phenotyping",
keywords="psychological factors",
keywords="mobile phone",
abstract="Background: Insomnia is a prevalent sleep disorder affecting millions worldwide, with significant impacts on daily functioning and quality of life. While traditionally assessed through subjective measures such as the Insomnia Severity Index (ISI), the advent of wearable technology has enabled continuous, objective sleep monitoring in natural environments. However, the relationship between subjective insomnia severity and objective sleep parameters remains unclear. Objective: This study aims to (1) explore the relationship between subjective insomnia severity, as measured by ISI scores, and activity-based objective sleep parameters obtained through wearable devices; (2) determine whether subjective perceptions of insomnia align with objective measures of sleep; and (3) identify key psychological and physiological factors contributing to the severity of subjective insomnia complaints. Methods: A total of 250 participants, including both individuals with and without insomnia aged 19-70 years, were recruited from March 2023 to November 2023. Participants were grouped based on ISI scores: no insomnia, mild, moderate, and severe insomnia. Data collection involved subjective assessments through self-reported questionnaires and objective measurements using wearable devices (Fitbit Inspire 3) that monitored sleep parameters, physical activity, and heart rate. The participants also used a smartphone app for ecological momentary assessment, recording daily alcohol consumption, caffeine intake, exercise, and stress. Statistical analyses were used to compare groups on subjective and objective measures. Results: Results indicated no significant differences in general sleep structure (eg, total sleep time, rapid eye movement sleep time, and light sleep time) among the insomnia groups (mild, moderate, and severe) as classified by ISI scores (all P>.05). Interestingly, the no insomnia group had longer total awake times and lower sleep quality compared with the insomnia groups. Among the insomnia groups, no significant differences were observed regarding sleep structure (all P>.05), suggesting similar sleep patterns regardless of subjective insomnia severity. There were significant differences among the insomnia groups in stress levels, dysfunctional beliefs about sleep, and symptoms of restless leg syndrome (all P?.001), with higher severity associated with higher scores in these factors. Contrary to expectations, no significant differences were observed in caffeine intake (P=.42) and alcohol consumption (P=.07) between the groups. Conclusions: The findings demonstrate a discrepancy between subjective perceptions of insomnia severity and activity-based objective sleep parameters, suggesting that factors beyond sleep duration and quality may contribute to subjective sleep complaints. Psychological factors, such as stress, dysfunctional sleep beliefs, and symptoms of restless legs syndrome, appear to play significant roles in the perception of insomnia severity. These results highlight the importance of considering both subjective and objective assessments in the evaluation and treatment of insomnia and suggest potential avenues for personalized treatment strategies that address both psychological and physiological aspects of sleep disturbances. Trial Registration: Clinical Research Information Service KCT0009175; https://cris.nih.go.kr/cris/search/detailSearch.do?seq=26133 ",
doi="10.2196/67478",
url="https://mental.jmir.org/2025/1/e67478"
}


@Article{info:doi/10.2196/63004,
author="De Silva, Upeka
and Madanian, Samaneh
and Olsen, Sharon
and Templeton, Michael John
and Poellabauer, Christian
and Schneider, L. Sandra
and Narayanan, Ajit
and Rubaiat, Rahmina",
title="Clinical Decision Support Using Speech Signal Analysis: Systematic Scoping Review of Neurological Disorders",
journal="J Med Internet Res",
year="2025",
month="Jan",
day="13",
volume="27",
pages="e63004",
keywords="digital health",
keywords="health informatics",
keywords="digital biomarker",
keywords="speech analytics",
keywords="artificial intelligence",
keywords="machine learning",
abstract="Background: Digital biomarkers are increasingly used in clinical decision support for various health conditions. Speech features as digital biomarkers can offer insights into underlying physiological processes due to the complexity of speech production. This process involves respiration, phonation, articulation, and resonance, all of which rely on specific motor systems for the preparation and execution of speech. Deficits in any of these systems can cause changes in speech signal patterns. Increasing efforts are being made to develop speech-based clinical decision support systems. Objective: This systematic scoping review investigated the technological revolution and recent digital clinical speech signal analysis trends to understand the key concepts and research processes from clinical and technical perspectives. Methods: A systematic scoping review was undertaken in 6 databases guided by a set of research questions. Articles that focused on speech signal analysis for clinical decision-making were identified, and the included studies were analyzed quantitatively. A narrower scope of studies investigating neurological diseases were analyzed using qualitative content analysis. Results: A total of 389 articles met the initial eligibility criteria, of which 72 (18.5\%) that focused on neurological diseases were included in the qualitative analysis. In the included studies, Parkinson disease, Alzheimer disease, and cognitive disorders were the most frequently investigated conditions. The literature explored the potential of speech feature analysis in diagnosis, differentiating between, assessing the severity and monitoring the treatment of neurological conditions. The common speech tasks used were sustained phonations, diadochokinetic tasks, reading tasks, activity-based tasks, picture descriptions, and prompted speech tasks. From these tasks, conventional speech features (such as fundamental frequency, jitter, and shimmer), advanced digital signal processing--based speech features (such as wavelet transformation--based features), and spectrograms in the form of audio images were analyzed. Traditional machine learning and deep learning approaches were used to build predictive models, whereas statistical analysis assessed variable relationships and reliability of speech features. Model evaluations primarily focused on analytical validations. A significant research gap was identified: the need for a structured research process to guide studies toward potential technological intervention in clinical settings. To address this, a research framework was proposed that adapts a design science research methodology to guide research studies systematically. Conclusions: The findings highlight how data science techniques can enhance speech signal analysis to support clinical decision-making. By combining knowledge from clinical practice, speech science, and data science within a structured research framework, future research may achieve greater clinical relevance. ",
doi="10.2196/63004",
url="https://www.jmir.org/2025/1/e63004",
url="http://www.ncbi.nlm.nih.gov/pubmed/39804693"
}


@Article{info:doi/10.2196/56679,
author="Zawada, J. Stephanie
and Ganjizadeh, Ali
and Conte, Marco Gian
and Demaerschalk, M. Bart
and Erickson, J. Bradley",
title="Exploring Remote Monitoring of Poststroke Mood With Digital Sensors by Assessment of Depression Phenotypes and Accelerometer Data in UK Biobank: Cross-Sectional Analysis",
journal="JMIR Neurotech",
year="2025",
month="Jan",
day="10",
volume="4",
pages="e56679",
keywords="depression",
keywords="cerebrovascular disease",
keywords="remote monitoring",
keywords="stroke",
keywords="accelerometers",
keywords="mobile phone",
abstract="Background: Interest in using digital sensors to monitor patients with prior stroke for depression, a risk factor for poor outcomes, has grown rapidly; however, little is known about behavioral phenotypes related to future mood symptoms and if patients with and without previously diagnosed depression experience similar phenotypes. Objective: This study aimed to assess the feasibility of using digital sensors to monitor mood in patients with prior stroke with a prestroke depression diagnosis (DD) and controls. We examined relationships between physical activity behaviors and self-reported depression frequency. Methods: In the UK Biobank wearable accelerometer cohort, we retrospectively identified patients who had previously suffered a stroke (N=1603) and conducted cross-sectional analyses with those who completed a subsequent depression survey follow-up. Sensitivity analyses assessed a general population cohort excluding previous stroke participants and 2 incident cohorts: incident stroke (IS) and incident cerebrovascular disease (IC). Results: In controls, the odds of being in a higher depressed mood frequency category decreased by 23\% for each minute spent in moderate?to?vigorous physical activity (odds ratio 0.77, 95\% CI 0.69?0.87; P<.001). This association persisted in both general cohorts and in the IC control cohort. Conclusions: Although moderate?to?vigorous physical activity was linked with less frequent depressed mood in patients with prior stroke without DD, this finding did not persist in DDs. Thus, accelerometer-mood monitoring may provide clinically useful insights about future mood in patients with prior stroke without DDs. Considering the finding in the IC cohort and the lack of findings in the IS cohorts, accelerometer-mood monitoring may also be appropriately applied to observing broader cerebrovascular disease pathogenesis. ",
doi="10.2196/56679",
url="https://neuro.jmir.org/2025/1/e56679"
}


@Article{info:doi/10.2196/60109,
author="Singh, Tavleen
and Roberts, Kirk
and Fujimoto, Kayo
and Wang, Jing
and Johnson, Constance
and Myneni, Sahiti",
title="Toward Personalized Digital Experiences to Promote Diabetes Self-Management: Mixed Methods Social Computing Approach",
journal="JMIR Diabetes",
year="2025",
month="Jan",
day="7",
volume="10",
pages="e60109",
keywords="digital health communities",
keywords="diabetes self-management",
keywords="behavior change",
keywords="affiliation exposure",
keywords="social networks",
keywords="deep learning",
abstract="Background: Type 2 diabetes affects nearly 34.2 million adults and is the seventh leading cause of death in the United States. Digital health communities have emerged as avenues to provide social support to individuals engaging in diabetes self-management (DSM). The analysis of digital peer interactions and social connections can improve our understanding of the factors underlying behavior change, which can inform the development of personalized DSM interventions. Objective: Our objective is to apply our methodology using a mixed methods approach to (1) characterize the role of context-specific social influence patterns in DSM and (2) derive interventional targets that enhance individual engagement in DSM. Methods: Using the peer messages from the American Diabetes Association support community for DSM (n={\textasciitilde}73,000 peer interactions from 2014 to 2021), (1) a labeled set of peer interactions was generated (n=1501 for the American Diabetes Association) through manual annotation, (2) deep learning models were used to scale the qualitative codes to the entire datasets, (3) the validated model was applied to perform a retrospective analysis, and (4) social network analysis techniques were used to portray large-scale patterns and relationships among the communication dimensions (content and context) embedded in peer interactions. Results: The affiliation exposure model showed that exposure to community users through sharing interactive communication style speech acts had a positive association with the engagement of community users. Our results also suggest that pre-existing users with type 2 diabetes were more likely to stay engaged in the community when they expressed patient-reported outcomes and progress themes (communication content) using interactive communication style speech acts (communication context). It indicates the potential for targeted social network interventions in the form of structural changes based on the user's context and content exchanges with peers, which can exert social influence to modify user engagement behaviors. Conclusions: In this study, we characterize the role of social influence in DSM as observed in large-scale social media datasets. Implications for multicomponent digital interventions are discussed. ",
doi="10.2196/60109",
url="https://diabetes.jmir.org/2025/1/e60109"
}


@Article{info:doi/10.2196/55635,
author="Lee, Ting-Yi
and Chen, Ching-Hsuan
and Chen, I-Ming
and Chen, Hsi-Chung
and Liu, Chih-Min
and Wu, Shu-I
and Hsiao, Kate Chuhsing
and Kuo, Po-Hsiu",
title="Dynamic Bidirectional Associations Between Global Positioning System Mobility and Ecological Momentary Assessment of Mood Symptoms in Mood Disorders: Prospective Cohort Study",
journal="J Med Internet Res",
year="2024",
month="Dec",
day="6",
volume="26",
pages="e55635",
keywords="ecological momentary assessment",
keywords="digital phenotyping",
keywords="GPS mobility",
keywords="bipolar disorder",
keywords="major depressive disorder",
keywords="GPS",
keywords="global positioning system",
keywords="mood disorders",
keywords="assessment",
keywords="depression",
keywords="anxiety",
keywords="digital phenotype",
keywords="smartphone app",
keywords="technology",
keywords="behavioral changes",
keywords="patient",
keywords="monitoring",
abstract="Background: Although significant research has explored the digital phenotype in mood disorders, the time-lagged and bidirectional relationship between mood and global positioning system (GPS) mobility remains relatively unexplored. Leveraging the widespread use of smartphones, we examined correlations between mood and behavioral changes, which could inform future scalable interventions and personalized mental health monitoring. Objective: This study aims to investigate the bidirectional time lag relationships between passive GPS data and active ecological momentary assessment (EMA) data collected via smartphone app technology. Methods: Between March 2020 and May 2022, we recruited 45 participants (mean age 42.3 years, SD 12.1 years) who were followed up for 6 months: 35 individuals diagnosed with mood disorders referred by psychiatrists and 10 healthy control participants. This resulted in a total of 5248 person-days of data. Over 6 months, we collected 2 types of smartphone data: passive data on movement patterns with nearly 100,000 GPS data points per individual and active data through EMA capturing daily mood levels, including fatigue, irritability, depressed, and manic mood. Our study is limited to Android users due to operating system constraints. Results: Our findings revealed a significant negative correlation between normalized entropy (r=--0.353; P=.04) and weekly depressed mood as well as between location variance (r=--0.364; P=.03) and depressed mood. In participants with mood disorders, we observed bidirectional time-lagged associations. Specifically, changes in homestay were positively associated with fatigue ($\beta$=0.256; P=.03), depressed mood ($\beta$=0.235; P=.01), and irritability ($\beta$=0.149; P=.03). A decrease in location variance was significantly associated with higher depressed mood the following day ($\beta$=--0.015; P=.009). Conversely, an increase in depressed mood was significantly associated with reduced location variance the next day ($\beta$=--0.869; P<.001). These findings suggest a dynamic interplay between mood symptoms and mobility patterns. Conclusions: This study demonstrates the potential of utilizing active EMA data to assess mood levels and passive GPS data to analyze mobility behaviors, with implications for managing disease progression in patients. Monitoring location variance and homestay can provide valuable insights into this process. The daily use of smartphones has proven to be a convenient method for monitoring patients' conditions. Interventions should prioritize promoting physical movement while discouraging prolonged periods of staying at home. ",
doi="10.2196/55635",
url="https://www.jmir.org/2024/1/e55635"
}


@Article{info:doi/10.2196/49927,
author="Kaminsky, Zachary
and McQuaid, J. Robyn
and Hellemans, GC Kim
and Patterson, R. Zachary
and Saad, Mysa
and Gabrys, L. Robert
and Kendzerska, Tetyana
and Abizaid, Alfonso
and Robillard, Rebecca",
title="Machine Learning--Based Suicide Risk Prediction Model for Suicidal Trajectory on Social Media Following Suicidal Mentions: Independent Algorithm Validation",
journal="J Med Internet Res",
year="2024",
month="Dec",
day="5",
volume="26",
pages="e49927",
keywords="suicide",
keywords="prediction",
keywords="social media",
keywords="machine learning",
keywords="suicide risk model",
keywords="validation",
keywords="natural language processing",
keywords="suicide risk",
keywords="Twitter",
keywords="suicidal ideation",
keywords="suicidal mention",
abstract="Background: Previous efforts to apply machine learning--based natural language processing to longitudinally collected social media data have shown promise in predicting suicide risk. Objective: Our primary objective was to externally validate our previous machine learning algorithm, the Suicide Artificial Intelligence Prediction Heuristic (SAIPH), against external survey data in 2 independent cohorts. A second objective was to evaluate the efficacy of SAIPH as an indicator of changing suicidal ideation (SI) over time. The tertiary objective was to use SAIPH to evaluate factors important for improving or worsening suicidal trajectory on social media following suicidal mention. Methods: Twitter (subsequently rebranded as X) timeline data from a student survey cohort and COVID-19 survey cohort were scored using SAIPH and compared to SI questions on the Beck Depression Inventory and the Self-Report version of the Quick Inventory of Depressive Symptomatology in 159 and 307 individuals, respectively. SAIPH was used to evaluate changing SI trajectory following suicidal mentions in 2 cohorts collected using the Twitter application programming interface. Results: An interaction of the mean SAIPH score derived from 12 days of Twitter data before survey completion and the average number of posts per day was associated with quantitative SI metrics in each cohort (student survey cohort interaction $\beta$=.038, SD 0.014; F4,94=3.3, P=.01; and COVID-19 survey cohort interaction $\beta$=.0035, SD 0.0016; F4,493=2.9, P=.03). The slope of average daily SAIPH scores was associated with the change in SI scores within longitudinally followed individuals when evaluating periods of 2 weeks or less ($\rho$=0.27, P=.04). Using SAIPH as an indicator of changing SI, we evaluated SI trajectory in 2 cohorts with suicidal mentions, which identified that those with responses within 72 hours exhibit a significant negative association of the SAIPH score with time in the 3 weeks following suicidal mention ($\rho$=--0.52, P=.02). Conclusions: Taken together, our results not only validate the association of SAIPH with perceived stress, SI, and changing SI over time but also generate novel methods to evaluate the effects of social media interactions on changing suicidal trajectory. ",
doi="10.2196/49927",
url="https://www.jmir.org/2024/1/e49927"
}


@Article{info:doi/10.2196/56874,
author="Ik{\"a}heimonen, Arsi
and Luong, Nguyen
and Baryshnikov, Ilya
and Darst, Richard
and Heikkil{\"a}, Roope
and Holmen, Joel
and Martikkala, Annasofia
and Riihim{\"a}ki, Kirsi
and Saleva, Outi
and Isomets{\"a}, Erkki
and Aledavood, Talayeh",
title="Predicting and Monitoring Symptoms in Patients Diagnosed With Depression Using Smartphone Data: Observational Study",
journal="J Med Internet Res",
year="2024",
month="Dec",
day="3",
volume="26",
pages="e56874",
keywords="data analysis",
keywords="digital phenotyping",
keywords="digital behavioral data",
keywords="depression symptoms",
keywords="depression monitoring",
keywords="mHealth",
keywords="mobile health",
keywords="smartphone",
keywords="mobile phone",
abstract="Background: Clinical diagnostic assessments and the outcome monitoring of patients with depression rely predominantly on interviews by professionals and the use of self-report questionnaires. The ubiquity of smartphones and other personal consumer devices has prompted research into the potential of data collected via these devices to serve as digital behavioral markers for indicating the presence and monitoring of the outcome of depression. Objective: This paper explores the potential of using behavioral data collected with smartphones to detect and monitor depression symptoms in patients diagnosed with depression. Specifically, it investigates whether this data can accurately classify the presence of depression, as well as monitor the changes in depressive states over time. Methods: In a prospective cohort study, we collected smartphone behavioral data for up to 1 year. The study consists of observations from 164 participants, including healthy controls (n=31) and patients diagnosed with various depressive disorders: major depressive disorder (MDD; n=85), MDD with comorbid borderline personality disorder (n=27), and major depressive episodes with bipolar disorder (n=21). Data were labeled based on depression severity using 9-item Patient Health Questionnaire (PHQ-9) scores. We performed statistical analysis and used supervised machine learning on the data to classify the severity of depression and observe changes in the depression state over time. Results: Our correlation analysis revealed 32 behavioral markers associated with the changes in depressive state. Our analysis classified patients who are depressed with an accuracy of 82\% (95\% CI 80\%-84\%) and change in the presence of depression with an accuracy of 75\% (95\% CI 72\%-76\%). Notably, the most important smartphone features for classifying depression states were screen-off events, battery charge levels, communication patterns, app usage, and location data. Similarly, for predicting changes in depression state, the most important features were related to location, battery level, screen, and accelerometer data patterns. Conclusions: The use of smartphone digital behavioral markers to supplement clinical evaluations may aid in detecting the presence and changes in severity of symptoms of depression, particularly if combined with intermittent use of self-report of symptoms. ",
doi="10.2196/56874",
url="https://www.jmir.org/2024/1/e56874"
}


@Article{info:doi/10.2196/58927,
author="Liu, Zhongling
and Li, Jinkai
and Zhang, Yuanyuan
and Wu, Dan
and Huo, Yanyan
and Yang, Jianxin
and Zhang, Musen
and Dong, Chuanfei
and Jiang, Luhui
and Sun, Ruohan
and Zhou, Ruoyin
and Li, Fei
and Yu, Xiaodan
and Zhu, Daqian
and Guo, Yao
and Chen, Jinjin",
title="Auxiliary Diagnosis of Children With Attention-Deficit/Hyperactivity Disorder Using Eye-Tracking and Digital Biomarkers: Case-Control Study",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Nov",
day="29",
volume="12",
pages="e58927",
keywords="attention deficit disorder with hyperactivity",
keywords="eye-tracking",
keywords="auxiliary diagnosis",
keywords="digital biomarker",
keywords="antisaccade",
keywords="machine learning",
abstract="Background: Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in school-aged children. The lack of objective biomarkers for ADHD often results in missed diagnoses or misdiagnoses, which lead to inappropriate or delayed interventions. Eye-tracking technology provides an objective method to assess children's neuropsychological behavior. Objective: The aim of this study was to develop an objective and reliable auxiliary diagnostic system for ADHD using eye-tracking technology. This system would be valuable for screening for ADHD in schools and communities and may help identify objective biomarkers for the clinical diagnosis of ADHD. Methods: We conducted a case-control study of children with ADHD and typically developing (TD) children. We designed an eye-tracking assessment paradigm based on the core cognitive deficits of ADHD and extracted various digital biomarkers that represented participant behaviors. These biomarkers and developmental patterns were compared between the ADHD and TD groups. Machine learning (ML) was implemented to validate the ability of the extracted eye-tracking biomarkers to predict ADHD. The performance of the ML models was evaluated using 5-fold cross-validation. Results: We recruited 216 participants, of whom 94 (43.5\%) were children with ADHD and 122 (56.5\%) were TD children. The ADHD group showed significantly poorer performance (for accuracy and completion time) than the TD group in the prosaccade, antisaccade, and delayed saccade tasks. In addition, there were substantial group differences in digital biomarkers, such as pupil diameter fluctuation, regularity of gaze trajectory, and fixations on unrelated areas. Although the accuracy and task completion speed of the ADHD group increased over time, their eye-movement patterns remained irregular. The TD group with children aged 5 to 6 years outperformed the ADHD group with children aged 9 to 10 years, and this difference remained relatively stable over time, which indicated that the ADHD group followed a unique developmental pattern. The ML model was effective in discriminating the groups, achieving an area under the curve of 0.965 and an accuracy of 0.908. Conclusions: The eye-tracking biomarkers proposed in this study effectively identified differences in various aspects of eye-movement patterns between the ADHD and TD groups. In addition, the ML model constructed using these digital biomarkers achieved high accuracy and reliability in identifying ADHD. Our system can facilitate early screening for ADHD in schools and communities and provide clinicians with objective biomarkers as a reference. ",
doi="10.2196/58927",
url="https://mhealth.jmir.org/2024/1/e58927",
url="http://www.ncbi.nlm.nih.gov/pubmed/39477792"
}


@Article{info:doi/10.2196/54597,
author="Deady, Matthew
and Duncan, Raymond
and Sonesen, Matthew
and Estiandan, Renier
and Stimpert, Kelly
and Cho, Sylvia
and Beers, Jeffrey
and Goodness, Brian
and Jones, Daniel Lance
and Forshee, Richard
and Anderson, A. Steven
and Ezzeldin, Hussein",
title="A Computable Phenotype Algorithm for Postvaccination Myocarditis/Pericarditis Detection Using Real-World Data: Validation Study",
journal="J Med Internet Res",
year="2024",
month="Nov",
day="25",
volume="26",
pages="e54597",
keywords="adverse event",
keywords="vaccine safety",
keywords="interoperability",
keywords="computable phenotype",
keywords="postmarket surveillance system",
keywords="fast healthcare interoperability resources",
keywords="FHIR",
keywords="real-world data",
keywords="validation study",
keywords="Food and Drug Administration",
keywords="electronic health records",
keywords="COVID-19 vaccine",
abstract="Background: Adverse events (AEs) associated with vaccination have traditionally been evaluated by epidemiological studies. More recently, they have gained attention due to the emergency use authorization of several COVID-19 vaccines. As part of its responsibility to conduct postmarket surveillance, the US Food and Drug Administration continues to monitor several AEs of interest to ensure the safety of vaccines, including those for COVID-19. Objective: This study is part of the Biologics Effectiveness and Safety Initiative, which aims to improve the US Food and Drug Administration's postmarket surveillance capabilities while minimizing the burden of collecting clinical data on suspected postvaccination AEs. The objective of this study was to enhance active surveillance efforts through a pilot platform that can receive automatically reported AE cases through a health care data exchange. Methods: We detected cases by sharing and applying computable phenotype algorithms to real-world data in health care providers' electronic health records databases. Using the fast healthcare interoperability resources standard for secure data transmission, we implemented a computable phenotype algorithm on a new health care system. The study focused on the algorithm's positive predictive value, validated through clinical records, assessing both the time required for implementation and the accuracy of AE detection. Results: The algorithm required 200-250 hours to implement and optimize. Of the 6,574,420 clinical encounters across 694,151 patients, 30 cases were identified as potential myocarditis/pericarditis. Of these, 26 cases were retrievable, and 24 underwent clinical validation. In total, 14 cases were confirmed as definite or probable myocarditis/pericarditis, yielding a positive predictive value of 58.3\% (95\% CI 37.3\%-76.9\%). These findings underscore the algorithm's capability for real-time detection of AEs, though they also highlight variability in performance across different health care systems. Conclusions: The study advocates for the ongoing refinement and application of distributed computable phenotype algorithms to enhance AE detection capabilities. These tools are crucial for comprehensive postmarket surveillance and improved vaccine safety monitoring. The outcomes suggest the need for further optimization to achieve more consistent results across diverse health care settings. ",
doi="10.2196/54597",
url="https://www.jmir.org/2024/1/e54597"
}


@Article{info:doi/10.2196/59974,
author="Hackett, Katherine
and Xu, Shiyun
and McKniff, Moira
and Paglia, Lido
and Barnett, Ian
and Giovannetti, Tania",
title="Mobility-Based Smartphone Digital Phenotypes for Unobtrusively Capturing Everyday Cognition, Mood, and Community Life-Space in Older Adults: Feasibility, Acceptability, and Preliminary Validity Study",
journal="JMIR Hum Factors",
year="2024",
month="Nov",
day="22",
volume="11",
pages="e59974",
keywords="digital phenotyping",
keywords="digital biomarkers",
keywords="monitoring",
keywords="mHealth",
keywords="cognition",
keywords="mobility",
keywords="life space",
keywords="depression",
keywords="location data",
keywords="Alzheimer disease",
keywords="aging",
keywords="mobile phone",
abstract="Background: Current methods of monitoring cognition in older adults are insufficient to address the growing burden of Alzheimer disease and related dementias (AD/ADRD). New approaches that are sensitive, scalable, objective, and reflective of meaningful functional outcomes are direly needed. Mobility trajectories and geospatial life space patterns reflect many aspects of cognitive and functional integrity and may be useful proxies of age-related cognitive decline. Objective: We investigated the feasibility, acceptability, and preliminary validity of a 1-month smartphone digital phenotyping protocol to infer everyday cognition, function, and mood in older adults from passively obtained GPS data. We also sought to clarify intrinsic and extrinsic factors associated with mobility phenotypes for consideration in future studies. Methods: Overall, 37 adults aged between 63 and 85 years with healthy cognition (n=31, 84\%), mild cognitive impairment (n=5, 13\%), and mild dementia (n=1, 3\%) used an open-source smartphone app (mindLAMP) to unobtrusively capture GPS trajectories for 4 weeks. GPS data were processed into interpretable features across categories of activity, inactivity, routine, and location diversity. Monthly average and day-to-day intraindividual variability (IIV) metrics were calculated for each feature to test a priori hypotheses from a neuropsychological framework. Validation measures collected at baseline were compared against monthly GPS features to examine construct validity. Feasibility and acceptability outcomes included retention, comprehension of study procedures, technical difficulties, and satisfaction ratings at debriefing. Results: All (37/37, 100\%) participants completed the 4-week monitoring period without major technical adverse events, 100\% (37/37) reported satisfaction with the explanation of study procedures, and 97\% (36/37) reported no feelings of discomfort. Participants' scores on the comprehension of consent quiz were 97\% on average and associated with education and race. Technical issues requiring troubleshooting were infrequent, though 41\% (15/37) reported battery drain. Moderate to strong correlations (r?0.3) were identified between GPS features and validators. Specifically, individuals with greater activity and more location diversity demonstrated better cognition, less functional impairment, less depression, more community participation, and more geospatial life space on objective and subjective validation measures. Contrary to predictions, greater IIV and less routine in mobility habits were also associated with positive outcomes. Many demographic and technology-related factors were not associated with GPS features; however, income, being a native English speaker, season of study participation, and occupational status were related to GPS features. Conclusions: Theoretically informed digital phenotypes of mobility are feasibly captured from older adults' personal smartphones and relate to clinically meaningful measures including cognitive test performance, reported functional decline, mood, and community activity. Future studies should consider the impact of intrinsic and extrinsic factors when interpreting mobility phenotypes. Overall, smartphone digital phenotyping is a promising method to unobtrusively capture relevant risk and resilience factors in the context of aging and AD/ADRD and should continue to be investigated in large, diverse samples. ",
doi="10.2196/59974",
url="https://humanfactors.jmir.org/2024/1/e59974"
}


@Article{info:doi/10.2196/55734,
author="Meng, Jian
and Niu, Xiaoyu
and Luo, Can
and Chen, Yueyue
and Li, Qiao
and Wei, Dongmei",
title="Development and Validation of a Machine Learning--Based Early Warning Model for Lichenoid Vulvar Disease: Prediction Model Development Study",
journal="J Med Internet Res",
year="2024",
month="Nov",
day="22",
volume="26",
pages="e55734",
keywords="female",
keywords="lichenoid vulvar disease",
keywords="risk factors",
keywords="evidence-based medicine",
keywords="early warning model",
abstract="Background: Given the complexity and diversity of lichenoid vulvar disease (LVD) risk factors, it is crucial to actively explore these factors and construct personalized warning models using relevant clinical variables to assess disease risk in patients. Yet, to date, there has been insufficient research, both nationwide and internationally, on risk factors and warning models for LVD. In light of these gaps, this study represents the first systematic exploration of the risk factors associated with LVD. Objective: The risk factors of LVD in women were explored and a medically evidence-based warning model was constructed to provide an early alert tool for the high-risk target population. The model can be applied in the clinic to identify high-risk patients and evaluate its accuracy and practicality in predicting LVD in women. Simultaneously, it can also enhance the diagnostic and treatment proficiency of medical personnel in primary community health service centers, which is of great significance in reducing overall health care spending and disease burden. Methods: A total of 2990 patients who attended West China Second Hospital of Sichuan University from January 2013 to December 2017 were selected as the study candidates and were divided into 1218 cases in the normal vulvovagina group (group 0) and 1772 cases in the lichenoid vulvar disease group (group 1) according to the results of the case examination. We investigated and collected routine examination data from patients for intergroup comparisons, included factors with significant differences in multifactorial analysis, and constructed logistic regression, random forests, gradient boosting machine (GBM), adaboost, eXtreme Gradient Boosting, and Categorical Boosting analysis models. The predictive efficacy of these six models was evaluated using receiver operating characteristic curve and area under the curve. Results: Univariate analysis revealed that vaginitis, urinary incontinence, humidity of the long-term residential environment, spicy dietary habits, regular intake of coffee or caffeinated beverages, daily sleep duration, diabetes mellitus, smoking history, presence of autoimmune diseases, menopausal status, and hypertension were all significant risk factors affecting female LVD. Furthermore, the area under the receiver operating characteristic curve, accuracy, sensitivity, and F1-score of the GBM warning model were notably higher than the other 5 predictive analysis models. The GBM analysis model indicated that menopausal status had the strongest impact on female LVD, showing a positive correlation, followed by the presence of autoimmune diseases, which also displayed a positive dependency. Conclusions: In accordance with evidence-based medicine, the construction of a predictive warning model for female LVD can be used to identify high-risk populations at an early stage, aiding in the formulation of effective preventive measures, which is of paramount importance for reducing the incidence of LVD in women. ",
doi="10.2196/55734",
url="https://www.jmir.org/2024/1/e55734"
}


@Article{info:doi/10.2196/62725,
author="Dwyer, Bridget
and Flathers, Matthew
and Burns, James
and Mikkelson, Jane
and Perlmutter, Elana
and Chen, Kelly
and Ram, Nanik
and Torous, John",
title="Assessing Digital Phenotyping for App Recommendations and Sustained Engagement: Cohort Study",
journal="JMIR Form Res",
year="2024",
month="Nov",
day="19",
volume="8",
pages="e62725",
keywords="engagement",
keywords="mental health",
keywords="digital phenotype",
keywords="pilot study",
keywords="phenotyping",
keywords="smartphone sensors",
keywords="anxiety",
keywords="sleep",
keywords="fitness",
keywords="depression",
keywords="qualitative",
keywords="app recommendation",
keywords="app use",
keywords="mobile phone",
abstract="Background: Low engagement with mental health apps continues to limit their impact. New approaches to help match patients to the right app may increase engagement by ensuring the app they are using is best suited to their mental health needs. Objective: This study aims to pilot how digital phenotyping, using data from smartphone sensors to infer symptom, behavioral, and functional outcomes, could be used to match people to mental health apps and potentially increase engagement Methods: After 1 week of collecting digital phenotyping data with the mindLAMP app (Beth Israel Deaconess Medical Center), participants were randomly assigned to the digital phenotyping arm, receiving feedback and recommendations based on those data to select 1 of 4 predetermined mental health apps (related to mood, anxiety, sleep, and fitness), or the control arm, selecting the same apps but without any feedback or recommendations. All participants used their selected app for 4 weeks with numerous metrics of engagement recorded, including objective screentime measures, self-reported engagement measures, and Digital Working Alliance Inventory scores. Results: A total of 82 participants enrolled in the study; 17 (21\%) dropped out of the digital phenotyping arm and 18 (22\%) dropped out from the control arm. Across both groups, few participants chose or were recommended the insomnia or fitness app. The majority (39/47, 83\%) used a depression or anxiety app. Engagement as measured by objective screen time and Digital Working Alliance Inventory scores were higher in the digital phenotyping arm. There was no correlation between self-reported and objective metrics of app use. Qualitative results highlighted the importance of habit formation in sustained app use. Conclusions: The results suggest that digital phenotyping app recommendation is feasible and may increase engagement. This approach is generalizable to other apps beyond the 4 apps selected for use in this pilot, and practical for real-world use given that the study was conducted without any compensation or external incentives that may have biased results. Advances in digital phenotyping will likely make this method of app recommendation more personalized and thus of even greater interest. ",
doi="10.2196/62725",
url="https://formative.jmir.org/2024/1/e62725"
}


@Article{info:doi/10.2196/60673,
author="Scaramozza, Matthew
and Ruet, Aur{\'e}lie
and Chiesa, A. Patrizia
and Ahamada, La{\"i}tissia
and Bartholom{\'e}, Emmanuel
and Carment, Lo{\"i}c
and Charre-Morin, Julie
and Cosne, Gautier
and Diouf, L{\'e}a
and Guo, C. Christine
and Juraver, Adrien
and Kanzler, M. Christoph
and Karatsidis, Angelos
and Mazz{\`a}, Claudia
and Penalver-Andres, Joaquin
and Ruiz, Marta
and Saubusse, Aurore
and Simoneau, Gabrielle
and Scotland, Alf
and Sun, Zhaonan
and Tang, Minao
and van Beek, Johan
and Zajac, Lauren
and Belachew, Shibeshih
and Brochet, Bruno
and Campbell, Nolan",
title="Sensor-Derived Measures of Motor and Cognitive Functions in People With Multiple Sclerosis Using Unsupervised Smartphone-Based Assessments: Proof-of-Concept Study",
journal="JMIR Form Res",
year="2024",
month="Nov",
day="8",
volume="8",
pages="e60673",
keywords="multiple sclerosis",
keywords="sensor-derived measure",
keywords="smartphone",
keywords="cognitive function",
keywords="motor function",
keywords="digital biomarkers",
keywords="mobile phone",
abstract="Background: Smartphones and wearables are revolutionizing the assessment of cognitive and motor function in neurological disorders, allowing for objective, frequent, and remote data collection. However, these assessments typically provide a plethora of sensor-derived measures (SDMs), and selecting the most suitable measure for a given context of use is a challenging, often overlooked problem. Objective: This analysis aims to develop and apply an SDM selection framework, including automated data quality checks and the evaluation of statistical properties, to identify robust SDMs that describe the cognitive and motor function of people with multiple sclerosis (MS). Methods: The proposed framework was applied to data from a cross-sectional study involving 85 people with MS and 68 healthy participants who underwent in-clinic supervised and remote unsupervised smartphone-based assessments. The assessment provided high-quality recordings from cognitive, manual dexterity, and mobility tests, from which 47 SDMs, based on established literature, were extracted using previously developed and publicly available algorithms. These SDMs were first separately and then jointly screened for bias and normality by 2 expert assessors. Selected SDMs were then analyzed to establish their reliability, using an intraclass correlation coefficient and minimal detectable change at 95\% CI. The convergence of selected SDMs with in-clinic MS functional measures and patient-reported outcomes was also evaluated. Results: A total of 16 (34\%) of the 47 SDMs passed the selection framework. All selected SDMs demonstrated moderate-to-good reliability in remote settings (intraclass correlation coefficient 0.5-0.85; minimal detectable change at 95\% CI 19\%-35\%). Selected SDMs extracted from the smartphone-based cognitive test demonstrated good-to-excellent correlation (Spearman correlation coefficient, |$\rho$|>0.75) with the in-clinic Symbol Digit Modalities Test and fair correlation with Expanded Disability Status Scale (EDSS) scores (0.25?|$\rho$|<0.5). SDMs extracted from the manual dexterity tests showed either fair correlation (0.25?|$\rho$|<0.5) or were not correlated (|$\rho$|<0.25) with the in-clinic 9-hole peg test and EDSS scores. Most selected SDMs from mobility tests showed fair correlation with the in-clinic timed 25-foot walk test and fair to moderate-to-good correlation (0.5<|$\rho$|?0.75) with EDSS scores. SDM correlations with relevant patient-reported outcomes varied by functional domain, ranging from not correlated (cognitive test SDMs) to good-to-excellent correlation (|$\rho$|>0.75) for mobility test SDMs. Overall, correlations were similar when smartphone-based tests were performed in a clinic or remotely. Conclusions: Reported results highlight that smartphone-based assessments are suitable tools to remotely obtain high-quality SDMs of cognitive and motor function in people with MS. The presented SDM selection framework promises to increase the interpretability and standardization of smartphone-based SDMs in people with MS, paving the way for their future use in interventional trials. ",
doi="10.2196/60673",
url="https://formative.jmir.org/2024/1/e60673"
}


@Article{info:doi/10.2196/58466,
author="Lin, Yu-Chun
and Yan, Huang-Ting
and Lin, Chih-Hsueh
and Chang, Hen-Hong",
title="Identifying and Estimating Frailty Phenotypes by Vocal Biomarkers: Cross-Sectional Study",
journal="J Med Internet Res",
year="2024",
month="Nov",
day="8",
volume="26",
pages="e58466",
keywords="frailty phenotypes",
keywords="older adults",
keywords="successful aging",
keywords="vocal biomarkers",
keywords="frailty",
keywords="phenotype",
keywords="vocal biomarker",
keywords="cross-sectional",
keywords="gerontology",
keywords="geriatrics",
keywords="older adult",
keywords="Taiwan",
keywords="energy-based",
keywords="hybrid-based",
keywords="sarcopenia",
abstract="Background: Researchers have developed a variety of indices to assess frailty. Recent research indicates that the human voice reflects frailty status. Frailty phenotypes are seldom discussed in the literature on the aging voice. Objective: This study aims to examine potential phenotypes of frail older adults and determine their correlation with vocal biomarkers. Methods: Participants aged ?60 years who visited the geriatric outpatient clinic of a teaching hospital in central Taiwan between 2020 and 2021 were recruited. We identified 4 frailty phenotypes: energy-based frailty, sarcopenia-based frailty, hybrid-based frailty--energy, and hybrid-based frailty--sarcopenia. Participants were asked to pronounce a sustained vowel ``/a/'' for approximately 1 second. The speech signals were digitized and analyzed. Four voice parameters---the average number of zero crossings (A1), variations in local peaks and valleys (A2), variations in first and second formant frequencies (A3), and spectral energy ratio (A4)---were used for analyzing changes in voice. Logistic regression was used to elucidate the prediction model. Results: Among 277 older adults, an increase in A1 values was associated with a lower likelihood of energy-based frailty (odds ratio [OR] 0.81, 95\% CI 0.68-0.96), whereas an increase in A2 values resulted in a higher likelihood of sarcopenia-based frailty (OR 1.34, 95\% CI 1.18-1.52). Respondents with larger A3 and A4 values had a higher likelihood of hybrid-based frailty--sarcopenia (OR 1.03, 95\% CI 1.002-1.06) and hybrid-based frailty--energy (OR 1.43, 95\% CI 1.02-2.01), respectively. Conclusions: Vocal biomarkers might be potentially useful in estimating frailty phenotypes. Clinicians can use 2 crucial acoustic parameters, namely A1 and A2, to diagnose a frailty phenotype that is associated with insufficient energy or reduced muscle function. The assessment of A3 and A4 involves a complex frailty phenotype. ",
doi="10.2196/58466",
url="https://www.jmir.org/2024/1/e58466"
}


@Article{info:doi/10.2196/58572,
author="Riad, Rachid
and Denais, Martin
and de Gennes, Marc
and Lesage, Adrien
and Oustric, Vincent
and Cao, Nga Xuan
and Mouchabac, St{\'e}phane
and Bourla, Alexis",
title="Automated Speech Analysis for Risk Detection of Depression, Anxiety, Insomnia, and Fatigue: Algorithm Development and Validation Study",
journal="J Med Internet Res",
year="2024",
month="Oct",
day="31",
volume="26",
pages="e58572",
keywords="speech analysis",
keywords="voice detection",
keywords="voice analysis",
keywords="speech biomarkers",
keywords="speech-based systems",
keywords="computer-aided diagnosis",
keywords="mental health symptom detection",
keywords="machine learning",
keywords="mental health",
keywords="fatigue",
keywords="anxiety",
keywords="depression",
abstract="Background: While speech analysis holds promise for mental health assessment, research often focuses on single symptoms, despite symptom co-occurrences and interactions. In addition, predictive models in mental health do not properly assess the limitations of speech-based systems, such as uncertainty, or fairness for a safe clinical deployment. Objective: We investigated the predictive potential of mobile-collected speech data for detecting and estimating depression, anxiety, fatigue, and insomnia, focusing on other factors than mere accuracy, in the general population. Methods: We included 865 healthy adults and recorded their answers regarding their perceived mental and sleep states. We asked how they felt and if they had slept well lately. Clinically validated questionnaires measuring depression, anxiety, insomnia, and fatigue severity were also used. We developed a novel speech and machine learning pipeline involving voice activity detection, feature extraction, and model training. We automatically modeled speech with pretrained deep learning models that were pretrained on a large, open, and free database, and we selected the best one on the validation set. Based on the best speech modeling approach, clinical threshold detection, individual score prediction, model uncertainty estimation, and performance fairness across demographics (age, sex, and education) were evaluated. We used a train-validation-test split for all evaluations: to develop our models, select the best ones, and assess the generalizability of held-out data. Results: The best model was Whisper M with a max pooling and oversampling method. Our methods achieved good detection performance for all symptoms, depression (Patient Health Questionnaire-9: area under the curve [AUC]=0.76; F1-score=0.49 and Beck Depression Inventory: AUC=0.78; F1-score=0.65), anxiety (Generalized Anxiety Disorder 7-item scale: AUC=0.77; F1-score=0.50), insomnia (Athens Insomnia Scale: AUC=0.73; F1-score=0.62), and fatigue (Multidimensional Fatigue Inventory total score: AUC=0.68; F1-score=0.88). The system performed well when it needed to abstain from making predictions, as demonstrated by low abstention rates in depression detection with the Beck Depression Inventory and fatigue, with risk-coverage AUCs below 0.4. Individual symptom scores were accurately predicted (correlations were all significant with Pearson strengths between 0.31 and 0.49). Fairness analysis revealed that models were consistent for sex (average disparity ratio [DR] 0.86, SD 0.13), to a lesser extent for education level (average DR 0.47, SD 0.30), and worse for age groups (average DR 0.33, SD 0.30). Conclusions: This study demonstrates the potential of speech-based systems for multifaceted mental health assessment in the general population, not only for detecting clinical thresholds but also for estimating their severity. Addressing fairness and incorporating uncertainty estimation with selective classification are key contributions that can enhance the clinical utility and responsible implementation of such systems. ",
doi="10.2196/58572",
url="https://www.jmir.org/2024/1/e58572"
}


@Article{info:doi/10.2196/59247,
author="Park, Jin-Hyuck",
title="Discriminant Power of Smartphone-Derived Keystroke Dynamics for Mild Cognitive Impairment Compared to a Neuropsychological Screening Test: Cross-Sectional Study",
journal="J Med Internet Res",
year="2024",
month="Oct",
day="30",
volume="26",
pages="e59247",
keywords="digital biomarker",
keywords="motor function",
keywords="digital device",
keywords="neuropsychological screening",
keywords="screening tools",
keywords="cognitive assessment",
keywords="mild cognitive impairment",
keywords="keystroke dynamics",
abstract="Background: Conventional neuropsychological screening tools for mild cognitive impairment (MCI) face challenges in terms of accuracy and practicality. Digital health solutions, such as unobtrusively capturing smartphone interaction data, offer a promising alternative. However, the potential of digital biomarkers as a surrogate for MCI screening remains unclear, with few comparisons between smartphone interactions and existing screening tools. Objective: This study aimed to investigate the effectiveness of smartphone-derived keystroke dynamics, captured via the Neurokeys keyboard app, in distinguishing patients with MCI from healthy controls (HCs). This study also compared the discriminant performance of these digital biomarkers against the Korean version of the Montreal Cognitive Assessment (MoCA-K), which is widely used for MCI detection in clinical settings. Methods: A total of 64 HCs and 47 patients with MCI were recruited. Over a 1-month period, participants generated 3530 typing sessions, with 2740 (77.6\%) analyzed for this study. Keystroke metrics, including hold time and flight time, were extracted. Receiver operating characteristics analysis was used to assess the sensitivity and specificity of keystroke dynamics in discriminating between HCs and patients with MCI. This study also explored the correlation between keystroke dynamics and MoCA-K scores. Results: Patients with MCI had significantly higher keystroke latency than HCs (P<.001). In particular, latency between key presses resulted in the highest sensitivity (97.9\%) and specificity (96.9\%). In addition, keystroke dynamics were significantly correlated with the MoCA-K (hold time: r=--.468; P<.001; flight time: r=--.497; P<.001), further supporting the validity of these digital biomarkers. Conclusions: These findings highlight the potential of smartphone-derived keystroke dynamics as an effective and ecologically valid tool for screening MCI. With higher sensitivity and specificity than the MoCA-K, particularly in measuring flight time, keystroke dynamics can serve as a noninvasive, scalable, and continuous method for early cognitive impairment detection. This novel approach could revolutionize MCI screening, offering a practical alternative to traditional tools in everyday settings. Trial Registration: Thai Clinical Trials Registry TCTR20220415002; https://www.thaiclinicaltrials.org/show/TCTR20220415002 ",
doi="10.2196/59247",
url="https://www.jmir.org/2024/1/e59247"
}


@Article{info:doi/10.2196/51269,
author="Liu, Qimin
and Ning, Emma
and Ross, K. Mindy
and Cladek, Andrea
and Kabir, Sarah
and Barve, Amruta
and Kennelly, Ellyn
and Hussain, Faraz
and Duffecy, Jennifer
and Langenecker, A. Scott
and Nguyen, M. Theresa
and Tulabandhula, Theja
and Zulueta, John
and Demos, P. Alexander
and Leow, Alex
and Ajilore, Olusola",
title="Digital Phenotypes of Mobile Keyboard Backspace Rates and Their Associations With Symptoms of Mood Disorder: Algorithm Development and Validation",
journal="J Med Internet Res",
year="2024",
month="Oct",
day="29",
volume="26",
pages="e51269",
keywords="keyboard typing",
keywords="passive sensing",
keywords="digital phenotyping",
keywords="mood disorder",
keywords="mixture model",
keywords="phenotypes",
keywords="mobile keyboard",
keywords="smartphone",
keywords="keyboard data",
keywords="monitoring",
keywords="clinical decision-making",
keywords="depression",
keywords="mania, mobile phone",
abstract="Background: Passive sensing through smartphone keyboard data can be used to identify and monitor symptoms of mood disorders with low participant burden. Behavioral phenotyping based on mobile keystroke data can aid in clinical decision-making and provide insights into the individual symptoms of mood disorders. Objective: This study aims to derive digital phenotypes based on smartphone keyboard backspace use among 128 community adults across 2948 observations using a Bayesian mixture model. Methods: Eligible study participants completed a virtual screening visit where all eligible participants were instructed to download the custom-built BiAffect smartphone keyboard (University of Illinois). The BiAffect keyboard unobtrusively captures keystroke dynamics. All eligible and consenting participants were instructed to use this keyboard exclusively for up to 4 weeks of the study in real life, and participants' compliance was checked at the 2 follow-up visits at week 2 and week 4. As part of the research protocol, every study participant underwent evaluations by a study psychiatrist during each visit. Results: We found that derived phenotypes were associated with not only the diagnoses and severity of depression and mania but also specific individual symptoms. Using a linear mixed-effects model with random intercepts accounting for the nested data structure from daily data, the backspace rates on the continuous scale did not differ between participants in the healthy control and in the mood disorders groups (P=.11). The 3-class model had mean backspace rates of 0.112, 0.180, and 0.268, respectively, with a SD of 0.048. In total, 3 classes, respectively, were estimated to comprise 37.5\% (n=47), 54.4\% (n=72), and 8.1\% (n=9) of the sample. We grouped individuals into Low, Medium, and High backspace rate groups. Individuals with unipolar mood disorder were predominantly in the Medium group (n=54), with some in the Low group (n=27) and a few in the High group (n=6). The Medium group, compared with the Low group, had significantly higher ratings of depression (b=2.32, P=.008). The High group was not associated with ratings of depression with (P=.88) or without (P=.27) adjustment for medication and diagnoses. The High group, compared with the Low group, was associated with both nonzero ratings (b=1.91, P=.02) and higher ratings of mania (b=1.46, P<.001). The High group, compared with the Low group, showed significantly higher odds of elevated mood (P=.03), motor activity (P=.04), and irritability (P<.05). Conclusions: This study demonstrates the promise of mobile typing kinematics in mood disorder research and practice. Monitoring a single mobile typing kinematic feature, that is, backspace rates, through passive sensing imposes a low burden on the participants. Based on real-life keystroke data, our derived digital phenotypes from this single feature can be useful for researchers and practitioners to distinguish between individuals with and those without mood disorder symptoms. ",
doi="10.2196/51269",
url="https://www.jmir.org/2024/1/e51269"
}


@Article{info:doi/10.2196/59623,
author="Cho, Minseo
and Park, Doeun
and Choo, Myounglee
and Kim, Jinwoo
and Han, Hyun Doug",
title="Development and Initial Evaluation of a Digital Phenotype Collection System for Adolescents: Proof-of-Concept Study",
journal="JMIR Form Res",
year="2024",
month="Oct",
day="24",
volume="8",
pages="e59623",
keywords="adolescents",
keywords="adolescent mental health",
keywords="smartphone apps",
keywords="self-monitoring",
keywords="qualitative research",
keywords="phenotypes",
keywords="proof of concept",
keywords="digital phenotyping",
keywords="phenotype data",
keywords="ecological momentary assessment",
abstract="Background: The growing concern on adolescent mental health calls for proactive early detection and intervention strategies. There is a recognition of the link between digital phenotypes and mental health, drawing attention to their potential use. However, the process of collecting digital phenotype data presents challenges despite its promising prospects. Objective: This study aims to develop and validate system concepts for collecting adolescent digital phenotypes that effectively manage inherent challenges in the process. Methods: In a formative investigation (N=34), we observed adolescent self-recording behaviors and conducted interviews to develop design goals. These goals were then translated into system concepts, which included planners resembling interfaces, simplified data input with tags, visual reports on behaviors and moods, and supportive ecological momentary assessment (EMA) prompts. A proof-of-concept study was conducted over 2 weeks (n=16), using tools that simulated the concepts to record daily activities and complete EMA surveys. The effectiveness of the system was evaluated through semistructured interviews, supplemented by an analysis of the frequency of records and responses. Results: The interview findings revealed overall satisfaction with the system concepts, emphasizing strong support for self-recording. Participants consistently maintained daily records throughout the study period, with no missing data. They particularly valued the recording procedures that aligned well with their self-recording goal of time management, facilitated by the interface design and simplified recording procedures. Visualizations during recording and subsequent report viewing further enhanced engagement by identifying missing data and encouraging deeper self-reflection. The average EMA compliance reached 72\%, attributed to a design that faithfully reflected adolescents' lives, with surveys scheduled at convenient times and supportive messages tailored to their daily routines. The high compliance rates observed and positive feedback from participants underscore the potential of our approach in addressing the challenges of collecting digital phenotypes among adolescents. Conclusions: Integrating observations of adolescents' recording behavior into the design process proved to be beneficial for developing an effective and highly compliant digital phenotype collection system. ",
doi="10.2196/59623",
url="https://formative.jmir.org/2024/1/e59623",
url="http://www.ncbi.nlm.nih.gov/pubmed/39446465"
}


@Article{info:doi/10.2196/51259,
author="Rashid, Zulqarnain
and Folarin, A. Amos
and Zhang, Yuezhou
and Ranjan, Yatharth
and Conde, Pauline
and Sankesara, Heet
and Sun, Shaoxiong
and Stewart, Callum
and Laiou, Petroula
and Dobson, B. Richard J.",
title="Digital Phenotyping of Mental and Physical Conditions: Remote Monitoring of Patients Through RADAR-Base Platform",
journal="JMIR Ment Health",
year="2024",
month="Oct",
day="23",
volume="11",
pages="e51259",
keywords="digital biomarkers",
keywords="mHealth",
keywords="mobile apps",
keywords="Internet of Things",
keywords="remote data collection",
keywords="wearables",
keywords="real-time monitoring",
keywords="platform",
keywords="biomarkers",
keywords="wearable",
keywords="smartphone",
keywords="data collection",
keywords="open-source platform",
keywords="RADAR-base",
keywords="phenotyping",
keywords="mobile phone",
keywords="IoT",
abstract="Background: The use of digital biomarkers through remote patient monitoring offers valuable and timely insights into a patient's condition, including aspects such as disease progression and treatment response. This serves as a complementary resource to traditional health care settings leveraging mobile technology to improve scale and lower latency, cost, and burden. Objective: Smartphones with embedded and connected sensors have immense potential for improving health care through various apps and mobile health (mHealth) platforms. This capability could enable the development of reliable digital biomarkers from long-term longitudinal data collected remotely from patients. Methods: We built an open-source platform, RADAR-base, to support large-scale data collection in remote monitoring studies. RADAR-base is a modern remote data collection platform built around Confluent's Apache Kafka to support scalability, extensibility, security, privacy, and quality of data. It provides support for study design and setup and active (eg, patient-reported outcome measures) and passive (eg, phone sensors, wearable devices, and Internet of Things) remote data collection capabilities with feature generation (eg, behavioral, environmental, and physiological markers). The back end enables secure data transmission and scalable solutions for data storage, management, and data access. Results: The platform has been used to successfully collect longitudinal data for various cohorts in a number of disease areas including multiple sclerosis, depression, epilepsy, attention-deficit/hyperactivity disorder, Alzheimer disease, autism, and lung diseases. Digital biomarkers developed through collected data are providing useful insights into different diseases. Conclusions: RADAR-base offers a contemporary, open-source solution driven by the community for remotely monitoring, collecting data, and digitally characterizing both physical and mental health conditions. Clinicians have the ability to enhance their insight through the use of digital biomarkers, enabling improved prevention, personalization, and early intervention in the context of disease management. ",
doi="10.2196/51259",
url="https://mental.jmir.org/2024/1/e51259"
}


@Article{info:doi/10.2196/59512,
author="Song, Meishu
and Yang, Zijiang
and Triantafyllopoulos, Andreas
and Zhang, Zixing
and Nan, Zhe
and Tang, Muxuan
and Takeuchi, Hiroki
and Nakamura, Toru
and Kishi, Akifumi
and Ishizawa, Tetsuro
and Yoshiuchi, Kazuhiro
and Schuller, Bj{\"o}rn
and Yamamoto, Yoshiharu",
title="Empowering Mental Health Monitoring Using a Macro-Micro Personalization Framework for Multimodal-Multitask Learning: Descriptive Study",
journal="JMIR Ment Health",
year="2024",
month="Oct",
day="18",
volume="11",
pages="e59512",
keywords="multimodal",
keywords="multitask",
keywords="daily mental health",
keywords="mental health",
keywords="monitoring",
keywords="macro",
keywords="micro",
keywords="framework",
keywords="personalization",
keywords="strategies",
keywords="prediction",
keywords="emotional state",
keywords="wristbands",
keywords="smartphone",
keywords="mobile phones",
keywords="physiological",
keywords="signals",
keywords="speech data",
keywords="",
abstract="Background: The field of mental health technology presently has significant gaps that need addressing, particularly in the domain of daily monitoring and personalized assessments. Current noninvasive devices such as wristbands and smartphones are capable of collecting a wide range of data, which has not yet been fully used for mental health monitoring. Objective: This study aims to introduce a novel dataset for personalized daily mental health monitoring and a new macro-micro framework. This framework is designed to use multimodal and multitask learning strategies for improved personalization and prediction of emotional states in individuals. Methods: Data were collected from 298 individuals using wristbands and smartphones, capturing physiological signals, speech data, and self-annotated emotional states. The proposed framework combines macro-level emotion transformer embeddings with micro-level personalization layers specific to each user. It also introduces a Dynamic Restrained Uncertainty Weighting method to effectively integrate various data types for a balanced representation of emotional states. Several fusion techniques, personalization strategies, and multitask learning approaches were explored. Results: The proposed framework was evaluated using the concordance correlation coefficient, resulting in a score of 0.503. This result demonstrates the framework's efficacy in predicting emotional states. Conclusions: The study concludes that the proposed multimodal and multitask learning framework, which leverages transformer-based techniques and dynamic task weighting strategies, is superior for the personalized monitoring of mental health. The study indicates the potential of transforming daily mental health monitoring into a more personalized app, opening up new avenues for technology-based mental health interventions. ",
doi="10.2196/59512",
url="https://mental.jmir.org/2024/1/e59512",
url="http://www.ncbi.nlm.nih.gov/pubmed/39422993"
}


@Article{info:doi/10.2196/56343,
author="Mollalo, Abolfazl
and Hamidi, Bashir
and Lenert, A. Leslie
and Alekseyenko, V. Alexander",
title="Application of Spatial Analysis on Electronic Health Records to Characterize Patient Phenotypes: Systematic Review",
journal="JMIR Med Inform",
year="2024",
month="Oct",
day="15",
volume="12",
pages="e56343",
keywords="clinical phenotypes",
keywords="electronic health records",
keywords="geocoding",
keywords="geographic information systems",
keywords="patient phenotypes",
keywords="spatial analysis",
abstract="Background: Electronic health records (EHRs) commonly contain patient addresses that provide valuable data for geocoding and spatial analysis, enabling more comprehensive descriptions of individual patients for clinical purposes. Despite the widespread use of EHRs in clinical decision support and interventions, no systematic review has examined the extent to which spatial analysis is used to characterize patient phenotypes. Objective: This study reviews advanced spatial analyses that used individual-level health data from EHRs within the United States to characterize patient phenotypes. Methods: We systematically evaluated English-language, peer-reviewed studies from the PubMed/MEDLINE, Scopus, Web of Science, and Google Scholar databases from inception to August 20, 2023, without imposing constraints on study design or specific health domains. Results: A substantial proportion of studies (>85\%) were limited to geocoding or basic mapping without implementing advanced spatial statistical analysis, leaving only 49 studies that met the eligibility criteria. These studies used diverse spatial methods, with a predominant focus on clustering techniques, while spatiotemporal analysis (frequentist and Bayesian) and modeling were less common. A noteworthy surge (n=42, 86\%) in publications was observed after 2017. The publications investigated a variety of adult and pediatric clinical areas, including infectious disease, endocrinology, and cardiology, using phenotypes defined over a range of data domains such as demographics, diagnoses, and visits. The primary health outcomes investigated were asthma, hypertension, and diabetes. Notably, patient phenotypes involving genomics, imaging, and notes were limited. Conclusions: This review underscores the growing interest in spatial analysis of EHR-derived data and highlights knowledge gaps in clinical health, phenotype domains, and spatial methodologies. We suggest that future research should focus on addressing these gaps and harnessing spatial analysis to enhance individual patient contexts and clinical decision support. ",
doi="10.2196/56343",
url="https://medinform.jmir.org/2024/1/e56343"
}


@Article{info:doi/10.2196/57439,
author="Karas, Marta
and Huang, Debbie
and Clement, Zachary
and Millner, J. Alexander
and Kleiman, M. Evan
and Bentley, H. Kate
and Zuromski, L. Kelly
and Fortgang, G. Rebecca
and DeMarco, Dylan
and Haim, Adam
and Donovan, Abigail
and Buonopane, J. Ralph
and Bird, A. Suzanne
and Smoller, W. Jordan
and Nock, K. Matthew
and Onnela, Jukka-Pekka",
title="Smartphone Screen Time Characteristics in People With Suicidal Thoughts: Retrospective Observational Data Analysis Study",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Oct",
day="11",
volume="12",
pages="e57439",
keywords="smartphone",
keywords="mobile apps",
keywords="mobile health",
keywords="screen time",
keywords="suicidal thoughts and behavior",
keywords="suicidal",
keywords="app",
keywords="observational data",
keywords="data analysis study",
keywords="monitor",
keywords="survey",
keywords="psychiatric",
keywords="screen",
keywords="mental health",
keywords="feasibility",
keywords="suicidal ideation",
keywords="mobile phone",
abstract="Background: Smartphone-based monitoring in natural settings provides opportunities to monitor mental health behaviors, including suicidal thoughts and behaviors. To date, most suicidal thoughts and behaviors research using smartphones has primarily relied on collecting so-called ``active'' data, requiring participants to engage by completing surveys. Data collected passively from smartphone sensors and logs may offer an objectively measured representation of an individual's behavior, including smartphone screen time. Objective: This study aims to present methods for identifying screen-on bouts and deriving screen time characteristics from passively collected smartphone state logs and to estimate daily smartphone screen time in people with suicidal thinking, providing a more reliable alternative to traditional self-report. Methods: Participants (N=126; median age 22, IQR 16-33 years) installed the Beiwe app (Harvard University) on their smartphones, which passively collected phone state logs for up to 6 months after discharge from an inpatient psychiatric unit (adolescents) or emergency department visit (adults). We derived daily screen time measures from these logs, including screen-on time, screen-on bout duration, screen-off bout duration, and screen-on bout count. We estimated the mean of these measures across age subgroups (adults and adolescents), phone operating systems (Android and iOS), and monitoring stages after the discharge (first 4 weeks vs subsequent weeks). We evaluated the sensitivity of daily screen time measures to changes in the parameters of the screen-on bout identification method. Additionally, we estimated the impact of a daylight time change on minute-level screen time using function-on-scalar generalized linear mixed-effects regression. Results: The median monitoring period was 169 (IQR 42?169) days. For adolescents and adults, mean daily screen-on time was 254.6 (95\% CI 231.4-277.7) and 271.0 (95\% CI 252.2-289.8) minutes, mean daily screen-on bout duration was 4.233 (95\% CI 3.565-4.902) and 4.998 (95\% CI 4.455-5.541) minutes, mean daily screen-off bout duration was 25.90 (95\% CI 20.09-31.71) and 26.90 (95\% CI 22.18-31.66) minutes, and mean daily screen-on bout count (natural logarithm transformed) was 4.192 (95\% CI 4.041-4.343) and 4.090 (95\% CI 3.968-4.213), respectively; there were no significant differences between smartphone operating systems (all P values were >.05). The daily measures were not significantly different for the first 4 weeks compared to the fifth week onward (all P values were >.05), except average screen-on bout in adults (P value = .018). Our sensitivity analysis indicated that in the screen-on bout identification method, the cap on an individual screen-on bout duration has a substantial effect on the resulting daily screen time measures. We observed time windows with a statistically significant effect of daylight time change on screen-on time (based on 95\% joint confidence intervals bands), plausibly attributable to sleep time adjustments related to clock changes. Conclusions: Passively collected phone logs offer an alternative to self-report measures for studying smartphone screen time characteristics in people with suicidal thinking. Our work demonstrates the feasibility of this approach, opening doors for further research on the associations between daily screen time, mental health, and other factors. ",
doi="10.2196/57439",
url="https://mhealth.jmir.org/2024/1/e57439"
}


@Article{info:doi/10.2196/55170,
author="Yi, Li
and Hart, E. Jaime
and Straczkiewicz, Marcin
and Karas, Marta
and Wilt, E. Grete
and Hu, R. Cindy
and Librett, Rachel
and Laden, Francine
and Chavarro, E. Jorge
and Onnela, Jukka-Pekka
and James, Peter",
title="Measuring Environmental and Behavioral Drivers of Chronic Diseases Using Smartphone-Based Digital Phenotyping: Intensive Longitudinal Observational mHealth Substudy Embedded in 2 Prospective Cohorts of Adults",
journal="JMIR Public Health Surveill",
year="2024",
month="Oct",
day="11",
volume="10",
pages="e55170",
keywords="big data",
keywords="daily mobility",
keywords="digital phenotyping",
keywords="ecological momentary assessment",
keywords="epidemiological monitoring",
keywords="health behavior",
keywords="smartphone apps and sensors",
keywords="mobile phone",
abstract="Background: Previous studies investigating environmental and behavioral drivers of chronic disease have often had limited temporal and spatial data coverage. Smartphone-based digital phenotyping mitigates the limitations of these studies by using intensive data collection schemes that take advantage of the widespread use of smartphones while allowing for less burdensome data collection and longer follow-up periods. In addition, smartphone apps can be programmed to conduct daily or intraday surveys on health behaviors and psychological well-being. Objective: The aim of this study was to investigate the feasibility and scalability of embedding smartphone-based digital phenotyping in large epidemiological cohorts by examining participant adherence to a smartphone-based data collection protocol in 2 ongoing nationwide prospective cohort studies. Methods: Participants (N=2394) of the Beiwe Substudy of the Nurses' Health Study 3 and Growing Up Today Study were followed over 1 year. During this time, they completed questionnaires every 10 days delivered via the Beiwe smartphone app covering topics such as emotions, stress and enjoyment, physical activity, access to green spaces, pets, diet (vegetables, meats, beverages, nuts and dairy, and fruits), sleep, and sitting. These questionnaires aimed to measure participants' key health behaviors to combine them with objectively assessed high-resolution GPS and accelerometer data provided by participants during the same period. Results: Between July 2021 and June 2023, we received 11.1 TB of GPS and accelerometer data from 2394 participants and 23,682 survey responses. The average follow-up time for each participant was 214 (SD 148) days. During this period, participants provided an average of 14.8 (SD 5.9) valid hours of GPS data and 13.2 (SD 4.8) valid hours of accelerometer data. Using a 10-hour cutoff, we found that 51.46\% (1232/2394) and 53.23\% (1274/2394) of participants had >50\% of valid data collection days for GPS and accelerometer data, respectively. In addition, each participant submitted an average of 10 (SD 11) surveys during the same period, with a mean response rate of 36\% across all surveys (SD 17\%; median 41\%). After initial processing of GPS and accelerometer data, we also found that participants spent an average of 14.6 (SD 7.5) hours per day at home and 1.6 (SD 1.6) hours per day on trips. We also recorded an average of 1046 (SD 1029) steps per day. Conclusions: In this study, smartphone-based digital phenotyping was used to collect intensive longitudinal data on lifestyle and behavioral factors in 2 well-established prospective cohorts. Our assessment of adherence to smartphone-based data collection protocols over 1 year suggests that adherence in our study was either higher or similar to most previous studies with shorter follow-up periods and smaller sample sizes. Our efforts resulted in a large dataset on health behaviors that can be linked to spatial datasets to examine environmental and behavioral drivers of chronic disease. ",
doi="10.2196/55170",
url="https://publichealth.jmir.org/2024/1/e55170",
url="http://www.ncbi.nlm.nih.gov/pubmed/39392682"
}


@Article{info:doi/10.2196/58502,
author="Burns, James
and Chen, Kelly
and Flathers, Matthew
and Currey, Danielle
and Macrynikola, Natalia
and Vaidyam, Aditya
and Langholm, Carsten
and Barnett, Ian
and Byun, Soo) Andrew (Jin
and Lane, Erlend
and Torous, John",
title="Transforming Digital Phenotyping Raw Data Into Actionable Biomarkers, Quality Metrics, and Data Visualizations Using Cortex Software Package: Tutorial",
journal="J Med Internet Res",
year="2024",
month="Aug",
day="23",
volume="26",
pages="e58502",
keywords="digital phenotyping",
keywords="mental health",
keywords="data visualization",
keywords="data analysis",
keywords="smartphones",
keywords="smartphone",
keywords="Cortex",
keywords="open-source",
keywords="data processing",
keywords="mindLAMP",
keywords="app",
keywords="apps",
keywords="data set",
keywords="clinical",
keywords="real world",
keywords="methodology",
keywords="mobile phone",
doi="10.2196/58502",
url="https://www.jmir.org/2024/1/e58502",
url="http://www.ncbi.nlm.nih.gov/pubmed/39178032"
}


@Article{info:doi/10.2196/57830,
author="Qi, Wenhao
and Zhu, Xiaohong
and He, Danni
and Wang, Bin
and Cao, Shihua
and Dong, Chaoqun
and Li, Yunhua
and Chen, Yanfei
and Wang, Bingsheng
and Shi, Yankai
and Jiang, Guowei
and Liu, Fang
and Boots, M. Lizzy M.
and Li, Jiaqi
and Lou, Xiajing
and Yao, Jiani
and Lu, Xiaodong
and Kang, Junling",
title="Mapping Knowledge Landscapes and Emerging Trends in AI for Dementia Biomarkers: Bibliometric and Visualization Analysis",
journal="J Med Internet Res",
year="2024",
month="Aug",
day="8",
volume="26",
pages="e57830",
keywords="artificial intelligence",
keywords="AI",
keywords="biomarker",
keywords="dementia",
keywords="machine learning",
keywords="bibliometric analysis",
abstract="Background: With the rise of artificial intelligence (AI) in the field of dementia biomarker research, exploring its current developmental trends and research focuses has become increasingly important. This study, using literature data mining, analyzes and assesses the key contributions and development scale of AI in dementia biomarker research. Objective: The aim of this study was to comprehensively evaluate the current state, hot topics, and future trends of AI in dementia biomarker research globally. Methods: This study thoroughly analyzed the literature in the application of AI to dementia biomarkers across various dimensions, such as publication volume, authors, institutions, journals, and countries, based on the Web of Science Core Collection. In addition, scales, trends, and potential connections between AI and biomarkers were extracted and deeply analyzed through multiple expert panels. Results: To date, the field includes 1070 publications across 362 journals, involving 74 countries and 1793 major research institutions, with a total of 6455 researchers. Notably, 69.41\% (994/1432) of the researchers ceased their studies before 2019. The most prevalent algorithms used are support vector machines, random forests, and neural networks. Current research frequently focuses on biomarkers such as imaging biomarkers, cerebrospinal fluid biomarkers, genetic biomarkers, and blood biomarkers. Recent advances have highlighted significant discoveries in biomarkers related to imaging, genetics, and blood, with growth in studies on digital and ophthalmic biomarkers. Conclusions: The field is currently in a phase of stable development, receiving widespread attention from numerous countries, institutions, and researchers worldwide. Despite this, stable clusters of collaborative research have yet to be established, and there is a pressing need to enhance interdisciplinary collaboration. Algorithm development has shown prominence, especially the application of support vector machines and neural networks in imaging studies. Looking forward, newly discovered biomarkers are expected to undergo further validation, and new types, such as digital biomarkers, will garner increased research interest and attention. ",
doi="10.2196/57830",
url="https://www.jmir.org/2024/1/e57830"
}


@Article{info:doi/10.2196/53371,
author="Howell, R. Carrie
and Zhang, Li
and Clay, J. Olivio
and Dutton, Gareth
and Horton, Trudi
and Mugavero, J. Michael
and Cherrington, L. Andrea",
title="Social Determinants of Health Phenotypes and Cardiometabolic Condition Prevalence Among Patients in a Large Academic Health System: Latent Class Analysis",
journal="JMIR Public Health Surveill",
year="2024",
month="Aug",
day="7",
volume="10",
pages="e53371",
keywords="social determinants of health",
keywords="electronic medical record",
keywords="phenotypes",
keywords="diabetes",
keywords="obesity",
keywords="cardiovascular disease",
keywords="obese",
keywords="social determinants",
keywords="social determinant",
keywords="cardiometabolic",
keywords="risk factors",
keywords="risk factor",
keywords="latent class analysis",
keywords="cardiometabolic disease",
keywords="EMR",
keywords="EHR",
keywords="electronic health record",
abstract="Background: Adverse social determinants of health (SDoH) have been associated with cardiometabolic disease; however, disparities in cardiometabolic outcomes are rarely the result of a single risk factor. Objective: This study aimed to identify and characterize SDoH phenotypes based on patient-reported and neighborhood-level data from the institutional electronic medical record and evaluate the prevalence of diabetes, obesity, and other cardiometabolic diseases by phenotype status. Methods: Patient-reported SDoH were collected (January to December 2020) and neighborhood-level social vulnerability, neighborhood socioeconomic status, and rurality were linked via census tract to geocoded patient addresses. Diabetes status was coded in the electronic medical record using International Classification of Diseases codes; obesity was defined using measured BMI ?30 kg/m2. Latent class analysis was used to identify clusters of SDoH (eg, phenotypes); we then examined differences in the prevalence of cardiometabolic conditions based on phenotype status using prevalence ratios (PRs). Results: Complete data were available for analysis for 2380 patients (mean age 53, SD 16 years; n=1405, 59\% female; n=1198, 50\% non-White). Roughly 8\% (n=179) reported housing insecurity, 30\% (n=710) reported resource needs (food, health care, or utilities), and 49\% (n=1158) lived in a high-vulnerability census tract. We identified 3 patient SDoH phenotypes: (1) high social risk, defined largely by self-reported SDoH (n=217, 9\%); (2) adverse neighborhood SDoH (n=1353, 56\%), defined largely by adverse neighborhood-level measures; and (3) low social risk (n=810, 34\%), defined as low individual- and neighborhood-level risks. Patients with an adverse neighborhood SDoH phenotype had higher prevalence of diagnosed type 2 diabetes (PR 1.19, 95\% CI 1.06?1.33), hypertension (PR 1.14, 95\% CI 1.02?1.27), peripheral vascular disease (PR 1.46, 95\% CI 1.09?1.97), and heart failure (PR 1.46, 95\% CI 1.20?1.79). Conclusions: Patients with the adverse neighborhood SDoH phenotype had higher prevalence of poor cardiometabolic conditions compared to phenotypes determined by individual-level characteristics, suggesting that neighborhood environment plays a role, even if individual measures of socioeconomic status are not suboptimal. ",
doi="10.2196/53371",
url="https://publichealth.jmir.org/2024/1/e53371"
}


@Article{info:doi/10.2196/59826,
author="Ortiz, Abigail
and Mulsant, H. Benoit",
title="Beyond Step Count: Are We Ready to Use Digital Phenotyping to Make Actionable Individual Predictions in Psychiatry?",
journal="J Med Internet Res",
year="2024",
month="Aug",
day="5",
volume="26",
pages="e59826",
keywords="digital phenotype",
keywords="digital phenotyping",
keywords="prediction",
keywords="predictions",
keywords="mental health",
keywords="mental illness",
keywords="mental illnesses",
keywords="mental disorder",
keywords="mental disorders",
keywords="US National Institute of Mental Health",
keywords="NIMH",
keywords="psychiatry",
keywords="psychiatrist",
keywords="psychiatrists",
doi="10.2196/59826",
url="https://www.jmir.org/2024/1/e59826"
}


@Article{info:doi/10.2196/49530,
author="Liang, Huey-Wen
and Wu, Chueh-Hung
and Lin, Chen
and Chang, Hsiang-Chih
and Lin, Yu-Hsuan
and Chen, Shao-Yu
and Hsu, Wei-Chen",
title="Rest-Activity Rhythm Differences in Acute Rehabilitation Between Poststroke Patients and Non--Brain Disease Controls: Comparative Study",
journal="J Med Internet Res",
year="2024",
month="Jul",
day="4",
volume="26",
pages="e49530",
keywords="circadian rhythms",
keywords="stroke rehabilitation, rest-activity rhythms, relative amplitude, delirium screening, interdaily stability",
abstract="Background: Circadian rhythm disruptions are a common concern for poststroke patients undergoing rehabilitation and might negatively impact their functional outcomes. Objective: Our research aimed to uncover unique patterns and disruptions specific to poststroke rehabilitation patients and identify potential differences in specific rest-activity rhythm indicators when compared to inpatient controls with non--brain-related lesions, such as patients with spinal cord injuries. Methods: We obtained a 7-day recording with a wearable actigraphy device from 25 poststroke patients (n=9, 36\% women; median age 56, IQR 46-71) and 25 age- and gender-matched inpatient control participants (n=15, 60\% women; median age 57, IQR 46.5-68.5). To assess circadian rhythm, we used a nonparametric method to calculate key rest-activity rhythm indicators---relative amplitude, interdaily stability, and intradaily variability. Relative amplitude, quantifying rest-activity rhythm amplitude while considering daily variations and unbalanced amplitudes, was calculated as the ratio of the difference between the most active 10 continuous hours and the least active 5 continuous hours to the sum of these 10 and 5 continuous hours. We also examined the clinical correlations between rest-activity rhythm indicators and delirium screening tools, such as the 4 A's Test and the Barthel Index, which assess delirium and activities of daily living. Results: Patients who had a stroke had higher least active 5-hour values compared to the control group (median 4.29, IQR 2.88-6.49 vs median 1.84, IQR 0.67-4.34; P=.008). The most active 10-hour values showed no significant differences between the groups (stroke group: median 38.92, IQR 14.60-40.87; control group: median 31.18, IQR 18.02-46.84; P=.93). The stroke group presented a lower relative amplitude compared to the control group (median 0.74, IQR 0.57-0.85 vs median 0.88, IQR 0.71-0.96; P=.009). Further analysis revealed no significant differences in other rest-activity rhythm metrics between the two groups. Among the patients who had a stroke, a negative correlation was observed between the 4 A's Test scores and relative amplitude ($\rho$=--0.41; P=.045). Across all participants, positive correlations emerged between the Barthel Index scores and both interdaily stability ($\rho$=0.34; P=.02) and the most active 10-hour value ($\rho$=0.42; P=.002). Conclusions: This study highlights the relevance of circadian rhythm disruptions in poststroke rehabilitation and provides insights into potential diagnostic and prognostic implications for rest-activity rhythm indicators as digital biomarkers. ",
doi="10.2196/49530",
url="https://www.jmir.org/2024/1/e49530"
}


@Article{info:doi/10.2196/52831,
author="Paolillo, W. Emily
and Casaletto, B. Kaitlin
and Clark, L. Annie
and Taylor, C. Jack
and Heuer, W. Hilary
and Wise, B. Amy
and Dhanam, Sreya
and Sanderson-Cimino, Mark
and Saloner, Rowan
and Kramer, H. Joel
and Kornak, John
and Kremers, Walter
and Forsberg, Leah
and Appleby, Brian
and Bayram, Ece
and Bozoki, Andrea
and Brushaber, Danielle
and Darby, Ryan R.
and Day, S. Gregory
and Dickerson, C. Bradford
and Domoto-Reilly, Kimiko
and Elahi, Fanny
and Fields, A. Julie
and Ghoshal, Nupur
and Graff-Radford, Neill
and G H Hall, Matthew
and Honig, S. Lawrence
and Huey, D. Edward
and Lapid, I. Maria
and Litvan, Irene
and Mackenzie, R. Ian
and Masdeu, C. Joseph
and Mendez, F. Mario
and Mester, Carly
and Miyagawa, Toji
and Naasan, Georges
and Pascual, Belen
and Pressman, Peter
and Ramos, Marisa Eliana
and Rankin, P. Katherine
and Rexach, Jessica
and Rojas, C. Julio
and VandeVrede, Lawren
and Wong, Bonnie
and Wszolek, K. Zbigniew
and Boeve, F. Bradley
and Rosen, J. Howard
and Boxer, L. Adam
and Staffaroni, M. Adam
and ",
title="Examining Associations Between Smartphone Use and Clinical Severity in Frontotemporal Dementia: Proof-of-Concept Study",
journal="JMIR Aging",
year="2024",
month="Jun",
day="26",
volume="7",
pages="e52831",
keywords="digital",
keywords="technology",
keywords="remote",
keywords="monitoring",
keywords="cognition",
keywords="neuropsychology",
keywords="cognitive impairment",
keywords="neurodegenerative",
keywords="screening",
keywords="clinical trials",
keywords="mobile phone",
abstract="Background: Frontotemporal lobar degeneration (FTLD) is a leading cause of dementia in individuals aged <65 years. Several challenges to conducting in-person evaluations in FTLD illustrate an urgent need to develop remote, accessible, and low-burden assessment techniques. Studies of unobtrusive monitoring of at-home computer use in older adults with mild cognitive impairment show that declining function is reflected in reduced computer use; however, associations with smartphone use are unknown. Objective: This study aims to characterize daily trajectories in smartphone battery use, a proxy for smartphone use, and examine relationships with clinical indicators of severity in FTLD. Methods: Participants were 231 adults (mean age 52.5, SD 14.9 years; n=94, 40.7\% men; n=223, 96.5\% non-Hispanic White) enrolled in the Advancing Research and Treatment of Frontotemporal Lobar Degeneration (ARTFL study) and Longitudinal Evaluation of Familial Frontotemporal Dementia Subjects (LEFFTDS study) Longitudinal Frontotemporal Lobar Degeneration (ALLFTD) Mobile App study, including 49 (21.2\%) with mild neurobehavioral changes and no functional impairment (ie, prodromal FTLD), 43 (18.6\%) with neurobehavioral changes and functional impairment (ie, symptomatic FTLD), and 139 (60.2\%) clinically normal adults, of whom 55 (39.6\%) harbored heterozygous pathogenic or likely pathogenic variants in an autosomal dominant FTLD gene. Participants completed the Clinical Dementia Rating plus National Alzheimer's Coordinating Center Frontotemporal Lobar Degeneration Behavior and Language Domains (CDR+NACC FTLD) scale, a neuropsychological battery; the Neuropsychiatric Inventory; and brain magnetic resonance imaging. The ALLFTD Mobile App was installed on participants' smartphones for remote, passive, and continuous monitoring of smartphone use. Battery percentage was collected every 15 minutes over an average of 28 (SD 4.2; range 14-30) days. To determine whether temporal patterns of battery percentage varied as a function of disease severity, linear mixed effects models examined linear, quadratic, and cubic effects of the time of day and their interactions with each measure of disease severity on battery percentage. Models covaried for age, sex, smartphone type, and estimated smartphone age. Results: The CDR+NACC FTLD global score interacted with time on battery percentage such that participants with prodromal or symptomatic FTLD demonstrated less change in battery percentage throughout the day (a proxy for less smartphone use) than clinically normal participants (P<.001 in both cases). Additional models showed that worse performance in all cognitive domains assessed (ie, executive functioning, memory, language, and visuospatial skills), more neuropsychiatric symptoms, and smaller brain volumes also associated with less battery use throughout the day (P<.001 in all cases). Conclusions: These findings support a proof of concept that passively collected data about smartphone use behaviors associate with clinical impairment in FTLD. This work underscores the need for future studies to develop and validate passive digital markers sensitive to longitudinal clinical decline across neurodegenerative diseases, with potential to enhance real-world monitoring of neurobehavioral change. ",
doi="10.2196/52831",
url="https://aging.jmir.org/2024/1/e52831",
url="http://www.ncbi.nlm.nih.gov/pubmed/38922667"
}


@Article{info:doi/10.2196/52316,
author="Das Swain, Vedant
and Ye, Jingjing
and Ramesh, Karthik Siva
and Mondal, Abhirup
and Abowd, D. Gregory
and De Choudhury, Munmun",
title="Leveraging Social Media to Predict COVID-19--Induced Disruptions to Mental Well-Being Among University Students: Modeling Study",
journal="JMIR Form Res",
year="2024",
month="Jun",
day="25",
volume="8",
pages="e52316",
keywords="social media",
keywords="mental health",
keywords="linguistic markers",
keywords="digital phenotyping",
keywords="COVID-19",
keywords="disaster well-being",
keywords="well-being",
keywords="machine learning",
keywords="temporal trends",
keywords="disruption",
abstract="Background: Large-scale crisis events such as COVID-19 often have secondary impacts on individuals' mental well-being. University students are particularly vulnerable to such impacts. Traditional survey-based methods to identify those in need of support do not scale over large populations and they do not provide timely insights. We pursue an alternative approach through social media data and machine learning. Our models aim to complement surveys and provide early, precise, and objective predictions of students disrupted by COVID-19. Objective: This study aims to demonstrate the feasibility of language on private social media as an indicator of crisis-induced disruption to mental well-being. Methods: We modeled 4124 Facebook posts provided by 43 undergraduate students, spanning over 2 years. We extracted temporal trends in the psycholinguistic attributes of their posts and comments. These trends were used as features to predict how COVID-19 disrupted their mental well-being. Results: The social media--enabled model had an F1-score of 0.79, which was a 39\% improvement over a model trained on the self-reported mental state of the participant. The features we used showed promise in predicting other mental states such as anxiety, depression, social, isolation, and suicidal behavior (F1-scores varied between 0.85 and 0.93). We also found that selecting the windows of time 7 months after the COVID-19--induced lockdown presented better results, therefore, paving the way for data minimization. Conclusions: We predicted COVID-19--induced disruptions to mental well-being by developing a machine learning model that leveraged language on private social media. The language in these posts described psycholinguistic trends in students' online behavior. These longitudinal trends helped predict mental well-being disruption better than models trained on correlated mental health questionnaires. Our work inspires further research into the potential applications of early, precise, and automatic warnings for individuals concerned about their mental health in times of crisis. ",
doi="10.2196/52316",
url="https://formative.jmir.org/2024/1/e52316",
url="http://www.ncbi.nlm.nih.gov/pubmed/38916951"
}


@Article{info:doi/10.2196/46691,
author="Wong, Chi-Wai David
and Bonnici, Timothy
and Gerry, Stephen
and Birks, Jacqueline
and Watkinson, J. Peter",
title="Effect of Digital Early Warning Scores on Hospital Vital Sign Observation Protocol Adherence: Stepped-Wedge Evaluation",
journal="J Med Internet Res",
year="2024",
month="Jun",
day="20",
volume="26",
pages="e46691",
keywords="vital signs",
keywords="early warning score",
keywords="track and trigger",
keywords="electronic charting",
keywords="stepped-wedge",
keywords="vital",
keywords="charting",
keywords="documentation",
keywords="deterioration",
keywords="hospital management",
keywords="clinical intervention",
keywords="decision-making",
keywords="patient risk",
keywords="hospital",
keywords="ICU",
keywords="intensive care unit",
keywords="UK",
keywords="United Kingdom",
keywords="intervention",
abstract="Background: Early warning scores (EWS) are routinely used in hospitals to assess a patient's risk of deterioration. EWS are traditionally recorded on paper observation charts but are increasingly recorded digitally. In either case, evidence for the clinical effectiveness of such scores is mixed, and previous studies have not considered whether EWS leads to changes in how deteriorating patients are managed. Objective: This study aims to examine whether the introduction of a digital EWS system was associated with more frequent observation of patients with abnormal vital signs, a precursor to earlier clinical intervention. Methods: We conducted a 2-armed stepped-wedge study from February 2015 to December 2016, over 4 hospitals in 1 UK hospital trust. In the control arm, vital signs were recorded using paper observation charts. In the intervention arm, a digital EWS system was used. The primary outcome measure was time to next observation (TTNO), defined as the time between a patient's first elevated EWS (EWS ?3) and subsequent observations set. Secondary outcomes were time to death in the hospital, length of stay, and time to unplanned intensive care unit admission. Differences between the 2 arms were analyzed using a mixed-effects Cox model. The usability of the system was assessed using the system usability score survey. Results: We included 12,802 admissions, 1084 in the paper (control) arm and 11,718 in the digital EWS (intervention) arm. The system usability score was 77.6, indicating good usability. The median TTNO in the control and intervention arms were 128 (IQR 73-218) minutes and 131 (IQR 73-223) minutes, respectively. The corresponding hazard ratio for TTNO was 0.99 (95\% CI 0.91-1.07; P=.73). Conclusions: We demonstrated strong clinical engagement with the system. We found no difference in any of the predefined patient outcomes, suggesting that the introduction of a highly usable electronic system can be achieved without impacting clinical care. Our findings contrast with previous claims that digital EWS systems are associated with improvement in clinical outcomes. Future research should investigate how digital EWS systems can be integrated with new clinical pathways adjusting staff behaviors to improve patient outcomes. ",
doi="10.2196/46691",
url="https://www.jmir.org/2024/1/e46691",
url="http://www.ncbi.nlm.nih.gov/pubmed/38900529"
}


@Article{info:doi/10.2196/55842,
author="Song, Sunmi
and Seo, YoungBin
and Hwang, SeoYeon
and Kim, Hae-Young
and Kim, Junesun",
title="Digital Phenotyping of Geriatric Depression Using a Community-Based Digital Mental Health Monitoring Platform for Socially Vulnerable Older Adults and Their Community Caregivers: 6-Week Living Lab Single-Arm Pilot Study",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Jun",
day="17",
volume="12",
pages="e55842",
keywords="depression",
keywords="monitoring system",
keywords="IoT",
keywords="AI",
keywords="wearable device",
keywords="digital mental health phenotyping",
keywords="living lab",
keywords="senior care",
keywords="Internet of Things",
keywords="artificial intelligence",
abstract="Background: Despite the increasing need for digital services to support geriatric mental health, the development and implementation of digital mental health care systems for older adults have been hindered by a lack of studies involving socially vulnerable older adult users and their caregivers in natural living environments. Objective: This study aims to determine whether digital sensing data on heart rate variability, sleep quality, and physical activity can predict same-day or next-day depressive symptoms among socially vulnerable older adults in their everyday living environments. In addition, this study tested the feasibility of a digital mental health monitoring platform designed to inform older adult users and their community caregivers about day-to-day changes in the health status of older adults. Methods: A single-arm, nonrandomized living lab pilot study was conducted with socially vulnerable older adults (n=25), their community caregivers (n=16), and a managerial social worker over a 6-week period during and after the COVID-19 pandemic. Depressive symptoms were assessed daily using the 9-item Patient Health Questionnaire via scripted verbal conversations with a mobile chatbot. Digital biomarkers for depression, including heart rate variability, sleep, and physical activity, were measured using a wearable sensor (Fitbit Sense) that was worn continuously, except during charging times. Daily individualized feedback, using traffic signal signs, on the health status of older adult users regarding stress, sleep, physical activity, and health emergency status was displayed on a mobile app for the users and on a web application for their community caregivers. Multilevel modeling was used to examine whether the digital biomarkers predicted same-day or next-day depressive symptoms. Study staff conducted pre- and postsurveys in person at the homes of older adult users to monitor changes in depressive symptoms, sleep quality, and system usability. Results: Among the 31 older adult participants, 25 provided data for the living lab and 24 provided data for the pre-post test analysis. The multilevel modeling results showed that increases in daily sleep fragmentation (P=.003) and sleep efficiency (P=.001) compared with one's average were associated with an increased risk of daily depressive symptoms in older adults. The pre-post test results indicated improvements in depressive symptoms (P=.048) and sleep quality (P=.02), but not in the system usability (P=.18). Conclusions: The findings suggest that wearable sensors assessing sleep quality may be utilized to predict daily fluctuations in depressive symptoms among socially vulnerable older adults. The results also imply that receiving individualized health feedback and sharing it with community caregivers may help improve the mental health of older adults. However, additional in-person training may be necessary to enhance usability. Trial Registration: ClinicalTrials.gov NCT06270121; https://clinicaltrials.gov/study/NCT06270121 ",
doi="10.2196/55842",
url="https://mhealth.jmir.org/2024/1/e55842",
url="http://www.ncbi.nlm.nih.gov/pubmed/38885033"
}


@Article{info:doi/10.2196/58398,
author="Maxin, J. Anthony
and Lim, H. Do
and Kush, Sophie
and Carpenter, Jack
and Shaibani, Rami
and Gulek, G. Bernice
and Harmon, G. Kimberly
and Mariakakis, Alex
and McGrath, B. Lynn
and Levitt, R. Michael",
title="Smartphone Pupillometry and Machine Learning for Detection of Acute Mild Traumatic Brain Injury: Cohort Study",
journal="JMIR Neurotech",
year="2024",
month="Jun",
day="13",
volume="3",
pages="e58398",
keywords="smartphone pupillometry",
keywords="pupillary light reflex",
keywords="biomarkers",
keywords="digital health",
keywords="mild traumatic brain injury",
keywords="concussion",
keywords="machine learning",
keywords="artificial intelligence",
keywords="AI",
keywords="pupillary",
keywords="pilot study",
keywords="brain",
keywords="brain injury",
keywords="injury",
keywords="diagnostic",
keywords="pupillometer",
keywords="neuroimaging",
keywords="diagnosis",
keywords="artificial",
keywords="mobile phone",
abstract="Background: Quantitative pupillometry is used in mild traumatic brain injury (mTBI) with changes in pupil reactivity noted after blast injury, chronic mTBI, and sports-related concussion. Objective: We evaluated the diagnostic capabilities of a smartphone-based digital pupillometer to differentiate patients with mTBI in the emergency department from controls. Methods: Adult patients diagnosed with acute mTBI with normal neuroimaging were evaluated in an emergency department within 36 hours of injury (control group: healthy adults). The PupilScreen smartphone pupillometer was used to measure the pupillary light reflex (PLR), and quantitative curve morphological parameters of the PLR were compared between mTBI and healthy controls. To address the class imbalance in our sample, a synthetic minority oversampling technique was applied. All possible combinations of PLR parameters produced by the smartphone pupillometer were then applied as features to 4 binary classification machine learning algorithms: random forest, k-nearest neighbors, support vector machine, and logistic regression. A 10-fold cross-validation technique stratified by cohort was used to produce accuracy, sensitivity, specificity, area under the curve, and F1-score metrics for the classification of mTBI versus healthy participants. Results: Of 12 patients with acute mTBI, 33\% (4/12) were female (mean age 54.1, SD 22.2 years), and 58\% (7/12) were White with a median Glasgow Coma Scale (GCS) of 15. Of the 132 healthy patients, 67\% (88/132) were female, with a mean age of 36 (SD 10.2) years and 64\% (84/132) were White with a median GCS of 15. Significant differences were observed in PLR recordings between healthy controls and patients with acute mTBI in the PLR parameters, that are (1) percent change (mean 34\%, SD 8.3\% vs mean 26\%, SD 7.9\%; P<.001), (2) minimum pupillary diameter (mean 34.8, SD 6.1 pixels vs mean 29.7, SD 6.1 pixels; P=.004), (3) maximum pupillary diameter (mean 53.6, SD 12.4 pixels vs mean 40.9, SD 11.9 pixels; P<.001), and (4) mean constriction velocity (mean 11.5, SD 5.0 pixels/second vs mean 6.8, SD 3.0 pixels/second; P<.001) between cohorts. After the synthetic minority oversampling technique, both cohorts had a sample size of 132 recordings. The best-performing binary classification model was a random forest model using the PLR parameters of latency, percent change, maximum diameter, minimum diameter, mean constriction velocity, and maximum constriction velocity as features. This model produced an overall accuracy of 93.5\%, sensitivity of 96.2\%, specificity of 90.9\%, area under the curve of 0.936, and F1-score of 93.7\% for differentiating between pupillary changes in mTBI and healthy participants. The absolute values are unable to be provided for the performance percentages reported here due to the mechanism of 10-fold cross validation that was used to obtain them. Conclusions: In this pilot study, quantitative smartphone pupillometry demonstrates the potential to be a useful tool in the future diagnosis of acute mTBI. ",
doi="10.2196/58398",
url="https://neuro.jmir.org/2024/1/e58398"
}


@Article{info:doi/10.2196/46895,
author="Cormack, Francesca
and McCue, Maggie
and Skirrow, Caroline
and Cashdollar, Nathan
and Taptiklis, Nick
and van Schaik, Tempest
and Fehnert, Ben
and King, James
and Chrones, Lambros
and Sarkey, Sara
and Kroll, Jasmin
and Barnett, H. Jennifer",
title="Characterizing Longitudinal Patterns in Cognition, Mood, And Activity in Depression With 6-Week High-Frequency Wearable Assessment: Observational Study",
journal="JMIR Ment Health",
year="2024",
month="May",
day="31",
volume="11",
pages="e46895",
keywords="cognition",
keywords="depression",
keywords="digital biomarkers",
keywords="ecological momentary assessment",
keywords="mobile health",
keywords="remote testing",
abstract="Background: Cognitive symptoms are an underrecognized aspect of depression that are often untreated. High-frequency cognitive assessment holds promise for improving disease and treatment monitoring. Although we have previously found it feasible to remotely assess cognition and mood in this capacity, further work is needed to ascertain the optimal methodology to implement and synthesize these techniques. Objective: The objective of this study was to examine (1) longitudinal changes in mood, cognition, activity levels, and heart rate over 6 weeks; (2) diurnal and weekday-related changes; and (3) co-occurrence of fluctuations between mood, cognitive function, and activity. Methods: A total of 30 adults with current mild-moderate depression stabilized on antidepressant monotherapy responded to testing delivered through an Apple Watch (Apple Inc) for 6 weeks. Outcome measures included cognitive function, assessed with 3 brief n-back tasks daily; self-reported depressed mood, assessed once daily; daily total step count; and average heart rate. Change over a 6-week duration, diurnal and day-of-week variations, and covariation between outcome measures were examined using nonlinear and multilevel models. Results: Participants showed initial improvement in the Cognition Kit N-Back performance, followed by a learning plateau. Performance reached 90\% of individual learning levels on average 10 days after study onset. N-back performance was typically better earlier and later in the day, and step counts were lower at the beginning and end of each week. Higher step counts overall were associated with faster n-back learning, and an increased daily step count was associated with better mood on the same (P<.001) and following day (P=.02). Daily n-back performance covaried with self-reported mood after participants reached their learning plateau (P=.01). Conclusions: The current results support the feasibility and sensitivity of high-frequency cognitive assessments for disease and treatment monitoring in patients with depression. Methods to model the individual plateau in task learning can be used as a sensitive approach to better characterize changes in behavior and improve the clinical relevance of cognitive data. Wearable technology allows assessment of activity levels, which may influence both cognition and mood. ",
doi="10.2196/46895",
url="https://mental.jmir.org/2024/1/e46895",
url="http://www.ncbi.nlm.nih.gov/pubmed/38819909"
}


@Article{info:doi/10.2196/50976,
author="Xu, Yucan
and Chan, Shaunlyn Christian
and Chan, Evangeline
and Chen, Junyou
and Cheung, Florence
and Xu, Zhongzhi
and Liu, Joyce
and Yip, Fai Paul Siu",
title="Tracking and Profiling Repeated Users Over Time in Text-Based Counseling: Longitudinal Observational Study With Hierarchical Clustering",
journal="J Med Internet Res",
year="2024",
month="May",
day="30",
volume="26",
pages="e50976",
keywords="web-based counseling",
keywords="text-based counseling",
keywords="repeated users",
keywords="frequent users",
keywords="hierarchical clustering",
keywords="service effectiveness",
keywords="risk profiling",
keywords="psychological profiles",
keywords="psycholinguistic analysis",
abstract="Background: Due to their accessibility and anonymity, web-based counseling services are expanding at an unprecedented rate. One of the most prominent challenges such services face is repeated users, who represent a small fraction of total users but consume significant resources by continually returning to the system and reiterating the same narrative and issues. A deeper understanding of repeated users and tailoring interventions may help improve service efficiency and effectiveness. Previous studies on repeated users were mainly on telephone counseling, and the classification of repeated users tended to be arbitrary and failed to capture the heterogeneity in this group of users. Objective: In this study, we aimed to develop a systematic method to profile repeated users and to understand what drives their use of the service. By doing so, we aimed to provide insight and practical implications that can inform the provision of service catering to different types of users and improve service effectiveness. Methods: We extracted session data from 29,400 users from a free 24/7 web-based counseling service from 2018 to 2021. To systematically investigate the heterogeneity of repeated users, hierarchical clustering was used to classify the users based on 3 indicators of service use behaviors, including the duration of their user journey, use frequency, and intensity. We then compared the psychological profile of the identified subgroups including their suicide risks and primary concerns to gain insights into the factors driving their patterns of service use. Results: Three clusters of repeated users with clear psychological profiles were detected: episodic, intermittent, and persistent-intensive users. Generally, compared with one-time users, repeated users showed higher suicide risks and more complicated backgrounds, including more severe presenting issues such as suicide or self-harm, bullying, and addictive behaviors. Higher frequency and intensity of service use were also associated with elevated suicide risk levels and a higher proportion of users citing mental disorders as their primary concerns. Conclusions: This study presents a systematic method of identifying and classifying repeated users in web-based counseling services. The proposed bottom-up clustering method identified 3 subgroups of repeated users with distinct service behaviors and psychological profiles. The findings can facilitate frontline personnel in delivering more efficient interventions and the proposed method can also be meaningful to a wider range of services in improving service provision, resource allocation, and service effectiveness. ",
doi="10.2196/50976",
url="https://www.jmir.org/2024/1/e50976",
url="http://www.ncbi.nlm.nih.gov/pubmed/38815258"
}


@Article{info:doi/10.2196/40689,
author="Choi, Adrien
and Ooi, Aysel
and Lottridge, Danielle",
title="Digital Phenotyping for Stress, Anxiety, and Mild Depression: Systematic Literature Review",
journal="JMIR Mhealth Uhealth",
year="2024",
month="May",
day="23",
volume="12",
pages="e40689",
keywords="digital phenotyping",
keywords="passive sensing",
keywords="stress",
keywords="anxiety",
keywords="depression",
keywords="PRISMA",
keywords="Preferred Reporting Items for Systematic Reviews and Meta-Analyses",
keywords="mobile phone",
abstract="Background: Unaddressed early-stage mental health issues, including stress, anxiety, and mild depression, can become a burden for individuals in the long term. Digital phenotyping involves capturing continuous behavioral data via digital smartphone devices to monitor human behavior and can potentially identify milder symptoms before they become serious. Objective: This systematic literature review aimed to answer the following questions: (1) what is the evidence of the effectiveness of digital phenotyping using smartphones in identifying behavioral patterns related to stress, anxiety, and mild depression? and (2) in particular, which smartphone sensors are found to be effective, and what are the associated challenges? Methods: We used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) process to identify 36 papers (reporting on 40 studies) to assess the key smartphone sensors related to stress, anxiety, and mild depression. We excluded studies conducted with nonadult participants (eg, teenagers and children) and clinical populations, as well as personality measurement and phobia studies. As we focused on the effectiveness of digital phenotyping using smartphones, results related to wearable devices were excluded. Results: We categorized the studies into 3 major groups based on the recruited participants: studies with students enrolled in universities, studies with adults who were unaffiliated to any particular organization, and studies with employees employed in an organization. The study length varied from 10 days to 3 years. A range of passive sensors were used in the studies, including GPS, Bluetooth, accelerometer, microphone, illuminance, gyroscope, and Wi-Fi. These were used to assess locations visited; mobility; speech patterns; phone use, such as screen checking; time spent in bed; physical activity; sleep; and aspects of social interactions, such as the number of interactions and response time. Of the 40 included studies, 31 (78\%) used machine learning models for prediction; most others (n=8, 20\%) used descriptive statistics. Students and adults who experienced stress, anxiety, or depression visited fewer locations, were more sedentary, had irregular sleep, and accrued increased phone use. In contrast to students and adults, less mobility was seen as positive for employees because less mobility in workplaces was associated with higher performance. Overall, travel, physical activity, sleep, social interaction, and phone use were related to stress, anxiety, and mild depression. Conclusions: This study focused on understanding whether smartphone sensors can be effectively used to detect behavioral patterns associated with stress, anxiety, and mild depression in nonclinical participants. The reviewed studies provided evidence that smartphone sensors are effective in identifying behavioral patterns associated with stress, anxiety, and mild depression. ",
doi="10.2196/40689",
url="https://mhealth.jmir.org/2024/1/e40689",
url="http://www.ncbi.nlm.nih.gov/pubmed/38780995"
}


@Article{info:doi/10.2196/53985,
author="Harada, Yukinori
and Sakamoto, Tetsu
and Sugimoto, Shu
and Shimizu, Taro",
title="Longitudinal Changes in Diagnostic Accuracy of a Differential Diagnosis List Developed by an AI-Based Symptom Checker: Retrospective Observational Study",
journal="JMIR Form Res",
year="2024",
month="May",
day="17",
volume="8",
pages="e53985",
keywords="atypical presentations",
keywords="diagnostic accuracy",
keywords="diagnosis",
keywords="diagnostics",
keywords="symptom checker",
keywords="uncommon diseases",
keywords="symptom checkers",
keywords="uncommon",
keywords="rare",
keywords="artificial intelligence",
abstract="Background: Artificial intelligence (AI) symptom checker models should be trained using real-world patient data to improve their diagnostic accuracy. Given that AI-based symptom checkers are currently used in clinical practice, their performance should improve over time. However, longitudinal evaluations of the diagnostic accuracy of these symptom checkers are limited. Objective: This study aimed to assess the longitudinal changes in the accuracy of differential diagnosis lists created by an AI-based symptom checker used in the real world. Methods: This was a single-center, retrospective, observational study. Patients who visited an outpatient clinic without an appointment between May 1, 2019, and April 30, 2022, and who were admitted to a community hospital in Japan within 30 days of their index visit were considered eligible. We only included patients who underwent an AI-based symptom checkup at the index visit, and the diagnosis was finally confirmed during follow-up. Final diagnoses were categorized as common or uncommon, and all cases were categorized as typical or atypical. The primary outcome measure was the accuracy of the differential diagnosis list created by the AI-based symptom checker, defined as the final diagnosis in a list of 10 differential diagnoses created by the symptom checker. To assess the change in the symptom checker's diagnostic accuracy over 3 years, we used a chi-square test to compare the primary outcome over 3 periods: from May 1, 2019, to April 30, 2020 (first year); from May 1, 2020, to April 30, 2021 (second year); and from May 1, 2021, to April 30, 2022 (third year). Results: A total of 381 patients were included. Common diseases comprised 257 (67.5\%) cases, and typical presentations were observed in 298 (78.2\%) cases. Overall, the accuracy of the differential diagnosis list created by the AI-based symptom checker was 172 (45.1\%), which did not differ across the 3 years (first year: 97/219, 44.3\%; second year: 32/72, 44.4\%; and third year: 43/90, 47.7\%; P=.85). The accuracy of the differential diagnosis list created by the symptom checker was low in those with uncommon diseases (30/124, 24.2\%) and atypical presentations (12/83, 14.5\%). In the multivariate logistic regression model, common disease (P<.001; odds ratio 4.13, 95\% CI 2.50-6.98) and typical presentation (P<.001; odds ratio 6.92, 95\% CI 3.62-14.2) were significantly associated with the accuracy of the differential diagnosis list created by the symptom checker. Conclusions: A 3-year longitudinal survey of the diagnostic accuracy of differential diagnosis lists developed by an AI-based symptom checker, which has been implemented in real-world clinical practice settings, showed no improvement over time. Uncommon diseases and atypical presentations were independently associated with a lower diagnostic accuracy. In the future, symptom checkers should be trained to recognize uncommon conditions. ",
doi="10.2196/53985",
url="https://formative.jmir.org/2024/1/e53985",
url="http://www.ncbi.nlm.nih.gov/pubmed/38758588"
}


@Article{info:doi/10.2196/53192,
author="Au-Yeung, M. Wan-Tai
and Liu, Yan
and Hanna, Remonda
and Gothard, Sarah
and Rodrigues, Nathaniel
and Leon Guerrero, Cierra
and Beattie, Zachary
and Kaye, Jeffrey",
title="Feasibility of Deploying Home-Based Digital Technology, Environmental Sensors, and Web-Based Surveys for Assessing Behavioral Symptoms and Identifying Their Precipitants in Older Adults: Longitudinal, Observational Study",
journal="JMIR Form Res",
year="2024",
month="May",
day="8",
volume="8",
pages="e53192",
keywords="neuropsychiatric symptoms",
keywords="mild cognitive impairment",
keywords="dementia",
keywords="unobtrusive monitoring",
keywords="digital biomarkers",
keywords="environmental precipitants",
keywords="mobile phone",
abstract="Background: Apathy, depression, and anxiety are prevalent neuropsychiatric symptoms experienced by older adults. Early detection, prevention, and intervention may improve outcomes. Objective: We aim to demonstrate the feasibility of deploying web-based weekly questionnaires inquiring about the behavioral symptoms of older adults with normal cognition, mild cognitive impairment, or early-stage dementia and to demonstrate the feasibility of deploying an in-home technology platform for measuring participant behaviors and their environment. Methods: The target population of this study is older adults with normal cognition, mild cognitive impairment, or early-stage dementia. This is an observational, longitudinal study with a study period of up to 9 months. The severity of participant behavioral symptoms (apathy, depression, and anxiety) was self-reported weekly through web-based surveys. Participants' digital biomarkers were continuously collected at their personal residences and through wearables throughout the duration of the study. The indoor physical environment at each residence, such as light level, noise level, temperature, humidity, or air quality, was also measured using indoor environmental sensors. Feasibility was examined, and preliminary correlation analysis between the level of symptoms and the digital biomarkers and between the level of symptoms and the indoor environment was performed. Results: At 13 months after recruitment began, a total of 9 participants had enrolled into this study. The participants showed high adherence rates in completing the weekly questionnaires (response rate: 275/278, 98.9\%), and data collection using the digital technology appeared feasible and acceptable to the participants with few exceptions. Participants' severity of behavioral symptoms fluctuated from week to week. Preliminary results show that the duration of sleep onset and noise level are positively correlated with the anxiety level in a subset of our participants. Conclusions: This study is a step toward more frequent assessment of older adults' behavioral symptoms and holistic in situ monitoring of older adults' behaviors and their living environment. The goal of this study is to facilitate the development of objective digital biomarkers of neuropsychiatric symptoms and to identify in-home environmental factors that contribute to these symptoms. ",
doi="10.2196/53192",
url="https://formative.jmir.org/2024/1/e53192",
url="http://www.ncbi.nlm.nih.gov/pubmed/38717798"
}


@Article{info:doi/10.2196/54622,
author="Hurwitz, Eric
and Butzin-Dozier, Zachary
and Master, Hiral
and O'Neil, T. Shawn
and Walden, Anita
and Holko, Michelle
and Patel, C. Rena
and Haendel, A. Melissa",
title="Harnessing Consumer Wearable Digital Biomarkers for Individualized Recognition of Postpartum Depression Using the All of Us Research Program Data Set: Cross-Sectional Study",
journal="JMIR Mhealth Uhealth",
year="2024",
month="May",
day="2",
volume="12",
pages="e54622",
keywords="wearable device",
keywords="All of Us",
keywords="postpartum depression",
keywords="machine learning",
keywords="Fitbit",
keywords="mobile phone",
abstract="Background: Postpartum depression (PPD) poses a significant maternal health challenge. The current approach to detecting PPD relies on in-person postpartum visits, which contributes to underdiagnosis. Furthermore, recognizing PPD symptoms can be challenging. Therefore, we explored the potential of using digital biomarkers from consumer wearables for PPD recognition. Objective: The main goal of this study was to showcase the viability of using machine learning (ML) and digital biomarkers related to heart rate, physical activity, and energy expenditure derived from consumer-grade wearables for the recognition of PPD. Methods: Using the All of Us Research Program Registered Tier v6 data set, we performed computational phenotyping of women with and without PPD following childbirth. Intraindividual ML models were developed using digital biomarkers from Fitbit to discern between prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods. Models were built using generalized linear models, random forest, support vector machine, and k-nearest neighbor algorithms and evaluated using the $\kappa$ statistic and multiclass area under the receiver operating characteristic curve (mAUC) to determine the algorithm with the best performance. The specificity of our individualized ML approach was confirmed in a cohort of women who gave birth and did not experience PPD. Moreover, we assessed the impact of a previous history of depression on model performance. We determined the variable importance for predicting the PPD period using Shapley additive explanations and confirmed the results using a permutation approach. Finally, we compared our individualized ML methodology against a traditional cohort-based ML model for PPD recognition and compared model performance using sensitivity, specificity, precision, recall, and F1-score. Results: Patient cohorts of women with valid Fitbit data who gave birth included <20 with PPD and 39 without PPD. Our results demonstrated that intraindividual models using digital biomarkers discerned among prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods, with random forest (mAUC=0.85; $\kappa$=0.80) models outperforming generalized linear models (mAUC=0.82; $\kappa$=0.74), support vector machine (mAUC=0.75; $\kappa$=0.72), and k-nearest neighbor (mAUC=0.74; $\kappa$=0.62). Model performance decreased in women without PPD, illustrating the method's specificity. Previous depression history did not impact the efficacy of the model for PPD recognition. Moreover, we found that the most predictive biomarker of PPD was calories burned during the basal metabolic rate. Finally, individualized models surpassed the performance of a conventional cohort-based model for PPD detection. Conclusions: This research establishes consumer wearables as a promising tool for PPD identification and highlights personalized ML approaches, which could transform early disease detection strategies. ",
doi="10.2196/54622",
url="https://mhealth.jmir.org/2024/1/e54622",
url="http://www.ncbi.nlm.nih.gov/pubmed/38696234"
}


@Article{info:doi/10.2196/53441,
author="Vidal Bustamante, M. Constanza
and Coombs III, Garth
and Rahimi-Eichi, Habiballah
and Mair, Patrick
and Onnela, Jukka-Pekka
and Baker, T. Justin
and Buckner, L. Randy",
title="Precision Assessment of Real-World Associations Between Stress and Sleep Duration Using Actigraphy Data Collected Continuously for an Academic Year: Individual-Level Modeling Study",
journal="JMIR Form Res",
year="2024",
month="Apr",
day="30",
volume="8",
pages="e53441",
keywords="deep phenotyping",
keywords="individualized models",
keywords="intensive longitudinal data",
keywords="sleep",
keywords="stress",
keywords="actigraphy",
keywords="accelerometer",
keywords="wearable",
keywords="mobile phone",
keywords="digital health",
abstract="Background: Heightened stress and insufficient sleep are common in the transition to college, often co-occur, and have both been linked to negative health outcomes. A challenge concerns disentangling whether perceived stress precedes or succeeds changes in sleep. These day-to-day associations may vary across individuals, but short study periods and group-level analyses in prior research may have obscured person-specific phenotypes. Objective: This study aims to obtain stable estimates of lead-lag associations between perceived stress and objective sleep duration in the individual, unbiased by the group, by developing an individual-level linear model that can leverage intensive longitudinal data while remaining parsimonious. Methods: In total, 55 college students (n=6, 11\% second-year students and n=49, 89\% first-year students) volunteered to provide daily self-reports of perceived stress via a smartphone app and wore an actigraphy wristband for the estimation of daily sleep duration continuously throughout the academic year (median usable daily observations per participant: 178, IQR 65.5). The individual-level linear model, developed in a Bayesian framework, included the predictor and outcome of interest and a covariate for the day of the week to account for weekly patterns. We validated the model on the cohort of second-year students (n=6, used as a pilot sample) by applying it to variables expected to correlate positively within individuals: objective sleep duration and self-reported sleep quality. The model was then applied to the fully independent target sample of first-year students (n=49) for the examination of bidirectional associations between daily stress levels and sleep duration. Results: Proof-of-concept analyses captured expected associations between objective sleep duration and subjective sleep quality in every pilot participant. Target analyses revealed negative associations between sleep duration and perceived stress in most of the participants (45/49, 92\%), but their temporal association varied. Of the 49 participants, 19 (39\%) showed a significant association (probability of direction>0.975): 8 (16\%) showed elevated stress in the day associated with shorter sleep later that night, 5 (10\%) showed shorter sleep associated with elevated stress the next day, and 6 (12\%) showed both directions of association. Of note, when analyzed using a group-based multilevel model, individual estimates were systematically attenuated, and some even reversed sign. Conclusions: The dynamic interplay of stress and sleep in daily life is likely person specific. Paired with intensive longitudinal data, our individual-level linear model provides a precision framework for the estimation of stable real-world behavioral and psychological dynamics and may support the personalized prioritization of intervention targets for health and well-being. ",
doi="10.2196/53441",
url="https://formative.jmir.org/2024/1/e53441",
url="http://www.ncbi.nlm.nih.gov/pubmed/38687600"
}


@Article{info:doi/10.2196/50259,
author="Cho, Kwangsu
and Kim, Minah
and Cho, Youngeun
and Hur, Ji-Won
and Kim, Hyung Do
and Park, Seonghyeon
and Park, Sunghyun
and Jang, Moonyoung
and Lee, Chang-Gun
and Kwon, Soo Jun",
title="Digital Phenotypes for Early Detection of Internet Gaming Disorder in Adolescent Students: Explorative Data-Driven Study",
journal="JMIR Ment Health",
year="2024",
month="Apr",
day="29",
volume="11",
pages="e50259",
keywords="adolescents",
keywords="digital biomarkers",
keywords="digital phenotyping",
keywords="digital psychiatry",
keywords="early detection",
keywords="IGD",
keywords="internet gaming disorder",
keywords="pediatric psychiatry",
keywords="proactive medicine",
keywords="secondary school",
keywords="universal screening",
abstract="Background: Limited awareness, social stigma, and access to mental health professionals hinder early detection and intervention of internet gaming disorder (IGD), which has emerged as a significant concern among young individuals. Prevalence estimates vary between 0.7\% and 15.6\%, and its recognition in the International Classification of Diseases, 11th Revision and Diagnostic and Statistical Manual of Mental Disorders, 5th Edition underscores its impact on academic functioning, social isolation, and mental health challenges. Objective: This study aimed to uncover digital phenotypes for the early detection of IGD among adolescents in learning settings. By leveraging sensor data collected from student tablets, the overarching objective is to incorporate these digital indicators into daily school activities to establish these markers as a mental health screening tool, facilitating the early identification and intervention for IGD cases. Methods: A total of 168 voluntary participants were engaged, consisting of 85 students with IGD and 83 students without IGD. There were 53\% (89/168) female and 47\% (79/168) male individuals, all within the age range of 13-14 years. The individual students learned their Korean literature and mathematics lessons on their personal tablets, with sensor data being automatically collected. Multiple regression with bootstrapping and multivariate ANOVA were used, prioritizing interpretability over predictability, for cross-validation purposes. Results: A negative correlation between IGD Scale (IGDS) scores and learning outcomes emerged (r166=--0.15; P=.047), suggesting that higher IGDS scores were associated with lower learning outcomes. Multiple regression identified 5 key indicators linked to IGD, explaining 23\% of the IGDS score variance: stroke acceleration ($\beta$=.33; P<.001), time interval between keys ($\beta$=--0.26; P=.01), word spacing ($\beta$=--0.25; P<.001), deletion ($\beta$=--0.24; P<.001), and horizontal length of strokes ($\beta$=0.21; P=.02). Multivariate ANOVA cross-validated these findings, revealing significant differences in digital phenotypes between potential IGD and non-IGD groups. The average effect size, measured by Cohen d, across the indicators was 0.40, indicating a moderate effect. Notable distinctions included faster stroke acceleration (Cohen d=0.68; P=<.001), reduced word spacing (Cohen d=.57; P=<.001), decreased deletion behavior (Cohen d=0.33; P=.04), and longer horizontal strokes (Cohen d=0.34; P=.03) in students with potential IGD compared to their counterparts without IGD. Conclusions: The aggregated findings show a negative correlation between IGD and learning performance, highlighting the effectiveness of digital markers in detecting IGD. This underscores the importance of digital phenotyping in advancing mental health care within educational settings. As schools adopt a 1-device-per-student framework, digital phenotyping emerges as a promising early detection method for IGD. This shift could transform clinical approaches from reactive to proactive measures. ",
doi="10.2196/50259",
url="https://mental.jmir.org/2024/1/e50259",
url="http://www.ncbi.nlm.nih.gov/pubmed/38683658"
}


@Article{info:doi/10.2196/47428,
author="Zhu, Yue
and Zhang, Ran
and Yin, Shuluo
and Sun, Yihui
and Womer, Fay
and Liu, Rongxun
and Zeng, Sheng
and Zhang, Xizhe
and Wang, Fei",
title="Digital Dietary Behaviors in Individuals With Depression: Real-World Behavioral Observation",
journal="JMIR Public Health Surveill",
year="2024",
month="Apr",
day="22",
volume="10",
pages="e47428",
keywords="dietary behaviors",
keywords="digital marker",
keywords="depression",
keywords="mental health",
keywords="appetite disturbance",
keywords="behavioral monitoring",
keywords="eating pattern",
keywords="electronic record",
keywords="digital health",
keywords="behavioral",
keywords="surveillance",
abstract="Background: Depression is often accompanied by changes in behavior, including dietary behaviors. The relationship between dietary behaviors and depression has been widely studied, yet previous research has relied on self-reported data which is subject to recall bias. Electronic device--based behavioral monitoring offers the potential for objective, real-time data collection of a large amount of continuous, long-term behavior data in naturalistic settings. Objective: The study aims to characterize digital dietary behaviors in depression, and to determine whether these behaviors could be used to detect depression. Methods: A total of 3310 students (2222 healthy controls [HCs], 916 with mild depression, and 172 with moderate-severe depression) were recruited for the study of their dietary behaviors via electronic records over a 1-month period, and depression severity was assessed in the middle of the month. The differences in dietary behaviors across the HCs, mild depression, and moderate-severe depression were determined by ANCOVA (analyses of covariance) with age, gender, BMI, and educational level as covariates. Multivariate logistic regression analyses were used to examine the association between dietary behaviors and depression severity. Support vector machine analysis was used to determine whether changes in dietary behaviors could detect mild and moderate-severe depression. Results: The study found that individuals with moderate-severe depression had more irregular eating patterns, more fluctuated feeding times, spent more money on dinner, less diverse food choices, as well as eating breakfast less frequently, and preferred to eat only lunch and dinner, compared with HCs. Moderate-severe depression was found to be negatively associated with the daily 3 regular meals pattern (breakfast-lunch-dinner pattern; OR 0.467, 95\% CI 0.239-0.912), and mild depression was positively associated with daily lunch and dinner pattern (OR 1.460, 95\% CI 1.016-2.100). These changes in digital dietary behaviors were able to detect mild and moderate-severe depression (accuracy=0.53, precision=0.60), with better accuracy for detecting moderate-severe depression (accuracy=0.67, precision=0.64). Conclusions: This is the first study to develop a profile of changes in digital dietary behaviors in individuals with depression using real-world behavioral monitoring. The results suggest that digital markers may be a promising approach for detecting depression. ",
doi="10.2196/47428",
url="https://publichealth.jmir.org/2024/1/e47428",
url="http://www.ncbi.nlm.nih.gov/pubmed/38648087"
}


@Article{info:doi/10.2196/50136,
author="Siepe, Sebastian Bj{\"o}rn
and Sander, Christian
and Schultze, Martin
and Kliem, Andreas
and Ludwig, Sascha
and Hegerl, Ulrich
and Reich, Hanna",
title="Time-Varying Network Models for the Temporal Dynamics of Depressive Symptomatology in Patients With Depressive Disorders: Secondary Analysis of Longitudinal Observational Data",
journal="JMIR Ment Health",
year="2024",
month="Apr",
day="18",
volume="11",
pages="e50136",
keywords="depression",
keywords="time series analysis",
keywords="network analysis",
keywords="experience sampling",
keywords="idiography",
keywords="time varying",
keywords="mobile phone",
abstract="Background: As depression is highly heterogenous, an increasing number of studies investigate person-specific associations of depressive symptoms in longitudinal data. However, most studies in this area of research conceptualize symptom interrelations to be static and time invariant, which may lead to important temporal features of the disorder being missed. Objective: To reveal the dynamic nature of depression, we aimed to use a recently developed technique to investigate whether and how associations among depressive symptoms change over time. Methods: Using daily data (mean length 274, SD 82 d) of 20 participants with depression, we modeled idiographic associations among depressive symptoms, rumination, sleep, and quantity and quality of social contacts as dynamic networks using time-varying vector autoregressive models. Results: The resulting models showed marked interindividual and intraindividual differences. For some participants, associations among variables changed in the span of some weeks, whereas they stayed stable over months for others. Our results further indicated nonstationarity in all participants. Conclusions: Idiographic symptom networks can provide insights into the temporal course of mental disorders and open new avenues of research for the study of the development and stability of psychopathological processes. ",
doi="10.2196/50136",
url="https://mental.jmir.org/2024/1/e50136",
url="http://www.ncbi.nlm.nih.gov/pubmed/38635978"
}


@Article{info:doi/10.2196/54538,
author="Park, Bogyeom
and Kim, Yuwon
and Park, Jinseok
and Choi, Hojin
and Kim, Seong-Eun
and Ryu, Hokyoung
and Seo, Kyoungwon",
title="Integrating Biomarkers From Virtual Reality and Magnetic Resonance Imaging for the Early Detection of Mild Cognitive Impairment Using a Multimodal Learning Approach: Validation Study",
journal="J Med Internet Res",
year="2024",
month="Apr",
day="17",
volume="26",
pages="e54538",
keywords="magnetic resonance imaging",
keywords="MRI",
keywords="virtual reality",
keywords="VR",
keywords="early detection",
keywords="mild cognitive impairment",
keywords="multimodal learning",
keywords="hand movement",
keywords="eye movement",
abstract="Background: Early detection of mild cognitive impairment (MCI), a transitional stage between normal aging and Alzheimer disease, is crucial for preventing the progression of dementia. Virtual reality (VR) biomarkers have proven to be effective in capturing behaviors associated with subtle deficits in instrumental activities of daily living, such as challenges in using a food-ordering kiosk, for early detection of MCI. On the other hand, magnetic resonance imaging (MRI) biomarkers have demonstrated their efficacy in quantifying observable structural brain changes that can aid in early MCI detection. Nevertheless, the relationship between VR-derived and MRI biomarkers remains an open question. In this context, we explored the integration of VR-derived and MRI biomarkers to enhance early MCI detection through a multimodal learning approach. Objective: We aimed to evaluate and compare the efficacy of VR-derived and MRI biomarkers in the classification of MCI while also examining the strengths and weaknesses of each approach. Furthermore, we focused on improving early MCI detection by leveraging multimodal learning to integrate VR-derived and MRI biomarkers. Methods: The study encompassed a total of 54 participants, comprising 22 (41\%) healthy controls and 32 (59\%) patients with MCI. Participants completed a virtual kiosk test to collect 4 VR-derived biomarkers (hand movement speed, scanpath length, time to completion, and the number of errors), and T1-weighted MRI scans were performed to collect 22 MRI biomarkers from both hemispheres. Analyses of covariance were used to compare these biomarkers between healthy controls and patients with MCI, with age considered as a covariate. Subsequently, the biomarkers that exhibited significant differences between the 2 groups were used to train and validate a multimodal learning model aimed at early screening for patients with MCI among healthy controls. Results: The support vector machine (SVM) using only VR-derived biomarkers achieved a sensitivity of 87.5\% and specificity of 90\%, whereas the MRI biomarkers showed a sensitivity of 90.9\% and specificity of 71.4\%. Moreover, a correlation analysis revealed a significant association between MRI-observed brain atrophy and impaired performance in instrumental activities of daily living in the VR environment. Notably, the integration of both VR-derived and MRI biomarkers into a multimodal SVM model yielded superior results compared to unimodal SVM models, achieving higher accuracy (94.4\%), sensitivity (100\%), specificity (90.9\%), precision (87.5\%), and F1-score (93.3\%). Conclusions: The results indicate that VR-derived biomarkers, characterized by their high specificity, can be valuable as a robust, early screening tool for MCI in a broader older adult population. On the other hand, MRI biomarkers, known for their high sensitivity, excel at confirming the presence of MCI. Moreover, the multimodal learning approach introduced in our study provides valuable insights into the improvement of early MCI detection by integrating a diverse set of biomarkers. ",
doi="10.2196/54538",
url="https://www.jmir.org/2024/1/e54538",
url="http://www.ncbi.nlm.nih.gov/pubmed/38631021"
}


@Article{info:doi/10.2196/56246,
author="Oreskovic, Jessica
and Kaufman, Jaycee
and Fossat, Yan",
title="Impact of Audio Data Compression on Feature Extraction for Vocal Biomarker Detection: Validation Study",
journal="JMIR Biomed Eng",
year="2024",
month="Apr",
day="15",
volume="9",
pages="e56246",
keywords="vocal biomarker",
keywords="biomarker",
keywords="biomarkers",
keywords="sound",
keywords="sounds",
keywords="audio",
keywords="compression",
keywords="voice",
keywords="acoustic",
keywords="acoustics",
keywords="audio compression",
keywords="feature extraction",
keywords="Python",
keywords="speech",
keywords="detect",
keywords="detection",
keywords="algorithm",
keywords="algorithms",
abstract="Background: Vocal biomarkers, derived from acoustic analysis of vocal characteristics, offer noninvasive avenues for medical screening, diagnostics, and monitoring. Previous research demonstrated the feasibility of predicting type 2 diabetes mellitus through acoustic analysis of smartphone-recorded speech. Building upon this work, this study explores the impact of audio data compression on acoustic vocal biomarker development, which is critical for broader applicability in health care. Objective: The objective of this research is to analyze how common audio compression algorithms (MP3, M4A, and WMA) applied by 3 different conversion tools at 2 bitrates affect features crucial for vocal biomarker detection. Methods: The impact of audio data compression on acoustic vocal biomarker development was investigated using uncompressed voice samples converted into MP3, M4A, and WMA formats at 2 bitrates (320 and 128 kbps) with MediaHuman (MH) Audio Converter, WonderShare (WS) UniConverter, and Fast Forward Moving Picture Experts Group (FFmpeg). The data set comprised recordings from 505 participants, totaling 17,298 audio files, collected using a smartphone. Participants recorded a fixed English sentence up to 6 times daily for up to 14 days. Feature extraction, including pitch, jitter, intensity, and Mel-frequency cepstral coefficients (MFCCs), was conducted using Python and Parselmouth. The Wilcoxon signed rank test and the Bonferroni correction for multiple comparisons were used for statistical analysis. Results: In this study, 36,970 audio files were initially recorded from 505 participants, with 17,298 recordings meeting the fixed sentence criteria after screening. Differences between the audio conversion software, MH, WS, and FFmpeg, were notable, impacting compression outcomes such as constant or variable bitrates. Analysis encompassed diverse data compression formats and a wide array of voice features and MFCCs. Wilcoxon signed rank tests yielded P values, with those below the Bonferroni-corrected significance level indicating significant alterations due to compression. The results indicated feature-specific impacts of compression across formats and bitrates. MH-converted files exhibited greater resilience compared to WS-converted files. Bitrate also influenced feature stability, with 38 cases affected uniquely by a single bitrate. Notably, voice features showed greater stability than MFCCs across conversion methods. Conclusions: Compression effects were found to be feature specific, with MH and FFmpeg showing greater resilience. Some features were consistently affected, emphasizing the importance of understanding feature resilience for diagnostic applications. Considering the implementation of vocal biomarkers in health care, finding features that remain consistent through compression for data storage or transmission purposes is valuable. Focused on specific features and formats, future research could broaden the scope to include diverse features, real-time compression algorithms, and various recording methods. This study enhances our understanding of audio compression's influence on voice features and MFCCs, providing insights for developing applications across fields. The research underscores the significance of feature stability in working with compressed audio data, laying a foundation for informed voice data use in evolving technological landscapes. ",
doi="10.2196/56246",
url="https://biomedeng.jmir.org/2024/1/e56246",
url="http://www.ncbi.nlm.nih.gov/pubmed/38875677"
}


@Article{info:doi/10.2196/53857,
author="Kilshaw, E. Robyn
and Boggins, Abigail
and Everett, Olivia
and Butner, Emma
and Leifker, R. Feea
and Baucom, W. Brian R.",
title="Benchmarking Mental Health Status Using Passive Sensor Data: Protocol for a Prospective Observational Study",
journal="JMIR Res Protoc",
year="2024",
month="Mar",
day="27",
volume="13",
pages="e53857",
keywords="audio data",
keywords="computational psychiatry",
keywords="data repository",
keywords="digital phenotyping",
keywords="machine learning",
keywords="passive sensor data",
abstract="Background: Computational psychiatry has the potential to advance the diagnosis, mechanistic understanding, and treatment of mental health conditions. Promising results from clinical samples have led to calls to extend these methods to mental health risk assessment in the general public; however, data typically used with clinical samples are neither available nor scalable for research in the general population. Digital phenotyping addresses this by capitalizing on the multimodal and widely available data created by sensors embedded in personal digital devices (eg, smartphones) and is a promising approach to extending computational psychiatry methods to improve mental health risk assessment in the general population. Objective: Building on recommendations from existing computational psychiatry and digital phenotyping work, we aim to create the first computational psychiatry data set that is tailored to studying mental health risk in the general population; includes multimodal, sensor-based behavioral features; and is designed to be widely shared across academia, industry, and government using gold standard methods for privacy, confidentiality, and data integrity. Methods: We are using a stratified, random sampling design with 2 crossed factors (difficulties with emotion regulation and perceived life stress) to recruit a sample of 400 community-dwelling adults balanced across high- and low-risk for episodic mental health conditions. Participants first complete self-report questionnaires assessing current and lifetime psychiatric and medical diagnoses and treatment, and current psychosocial functioning. Participants then complete a 7-day in situ data collection phase that includes providing daily audio recordings, passive sensor data collected from smartphones, self-reports of daily mood and significant events, and a verbal description of the significant daily events during a nightly phone call. Participants complete the same baseline questionnaires 6 and 12 months after this phase. Self-report questionnaires will be scored using standard methods. Raw audio and passive sensor data will be processed to create a suite of daily summary features (eg, time spent at home). Results: Data collection began in June 2022 and is expected to conclude by July 2024. To date, 310 participants have consented to the study; 149 have completed the baseline questionnaire and 7-day intensive data collection phase; and 61 and 31 have completed the 6- and 12-month follow-up questionnaires, respectively. Once completed, the proposed data set will be made available to academic researchers, industry, and the government using a stepped approach to maximize data privacy. Conclusions: This data set is designed as a complementary approach to current computational psychiatry and digital phenotyping research, with the goal of advancing mental health risk assessment within the general population. This data set aims to support the field's move away from siloed research laboratories collecting proprietary data and toward interdisciplinary collaborations that incorporate clinical, technical, and quantitative expertise at all stages of the research process. International Registered Report Identifier (IRRID): DERR1-10.2196/53857 ",
doi="10.2196/53857",
url="https://www.researchprotocols.org/2024/1/e53857",
url="http://www.ncbi.nlm.nih.gov/pubmed/38536220"
}


@Article{info:doi/10.2196/42904,
author="Reiter, Vittoria Alisa Maria
and Pantel, Tori Jean
and Danyel, Magdalena
and Horn, Denise
and Ott, Claus-Eric
and Mensah, Atta Martin",
title="Validation of 3 Computer-Aided Facial Phenotyping Tools (DeepGestalt, GestaltMatcher, and D-Score): Comparative Diagnostic Accuracy Study",
journal="J Med Internet Res",
year="2024",
month="Mar",
day="13",
volume="26",
pages="e42904",
keywords="facial phenotyping",
keywords="DeepGestalt",
keywords="facial recognition",
keywords="Face2Gene",
keywords="medical genetics",
keywords="diagnostic accuracy",
keywords="genetic syndrome",
keywords="machine learning",
keywords="GestaltMatcher",
keywords="D-Score",
keywords="genetics",
abstract="Background: While characteristic facial features provide important clues for finding the correct diagnosis in genetic syndromes, valid assessment can be challenging. The next-generation phenotyping algorithm DeepGestalt analyzes patient images and provides syndrome suggestions. GestaltMatcher matches patient images with similar facial features. The new D-Score provides a score for the degree of facial dysmorphism. Objective: We aimed to test state-of-the-art facial phenotyping tools by benchmarking GestaltMatcher and D-Score and comparing them to DeepGestalt. Methods: Using a retrospective sample of 4796 images of patients with 486 different genetic syndromes (London Medical Database, GestaltMatcher Database, and literature images) and 323 inconspicuous control images, we determined the clinical use of D-Score, GestaltMatcher, and DeepGestalt, evaluating sensitivity; specificity; accuracy; the number of supported diagnoses; and potential biases such as age, sex, and ethnicity. Results: DeepGestalt suggested 340 distinct syndromes and GestaltMatcher suggested 1128 syndromes. The top-30 sensitivity was higher for DeepGestalt (88\%, SD 18\%) than for GestaltMatcher (76\%, SD 26\%). DeepGestalt generally assigned lower scores but provided higher scores for patient images than for inconspicuous control images, thus allowing the 2 cohorts to be separated with an area under the receiver operating characteristic curve (AUROC) of 0.73. GestaltMatcher could not separate the 2 classes (AUROC 0.55). Trained for this purpose, D-Score achieved the highest discriminatory power (AUROC 0.86). D-Score's levels increased with the age of the depicted individuals. Male individuals yielded higher D-scores than female individuals. Ethnicity did not appear to influence D-scores. Conclusions: If used with caution, algorithms such as D-score could help clinicians with constrained resources or limited experience in syndromology to decide whether a patient needs further genetic evaluation. Algorithms such as DeepGestalt could support diagnosing rather common genetic syndromes with facial abnormalities, whereas algorithms such as GestaltMatcher could suggest rare diagnoses that are unknown to the clinician in patients with a characteristic, dysmorphic face. ",
doi="10.2196/42904",
url="https://www.jmir.org/2024/1/e42904",
url="http://www.ncbi.nlm.nih.gov/pubmed/38477981"
}


@Article{info:doi/10.2196/52377,
author="Ponzo, Sonia
and May, Merle
and Tamayo-Elizalde, Miren
and Bailey, Kerri
and Shand, J. Alanna
and Bamford, Ryan
and Multmeier, Jan
and Griessel, Ivan
and Szulyovszky, Benedek
and Blakey, William
and Valentine, Sophie
and Plans, David",
title="App Characteristics and Accuracy Metrics of Available Digital Biomarkers for Autism: Scoping Review",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Nov",
day="17",
volume="11",
pages="e52377",
keywords="autism",
keywords="diagnostics",
keywords="digital biomarkers",
keywords="digital health",
keywords="mobile apps",
keywords="neurodevelopmental conditions",
abstract="Background: Diagnostic delays in autism are common, with the time to diagnosis being up to 3 years from the onset of symptoms. Such delays have a proven detrimental effect on individuals and families going through the process. Digital health products, such as mobile apps, can help close this gap due to their scalability and ease of access. Further, mobile apps offer the opportunity to make the diagnostic process faster and more accurate by providing additional and timely information to clinicians undergoing autism assessments. Objective: The aim of this scoping review was to synthesize the available evidence about digital biomarker tools to aid clinicians, researchers in the autism field, and end users in making decisions as to their adoption within clinical and research settings. Methods: We conducted a structured literature search on databases and search engines to identify peer-reviewed studies and regulatory submissions that describe app characteristics, validation study details, and accuracy and validity metrics of commercial and research digital biomarker apps aimed at aiding the diagnosis of autism. Results: We identified 4 studies evaluating 4 products: 1 commercial and 3 research apps. The accuracy of the identified apps varied between 28\% and 80.6\%. Sensitivity and specificity also varied, ranging from 51.6\% to 81.6\% and 18.5\% to 80.5\%, respectively. Positive predictive value ranged from 20.3\% to 76.6\%, and negative predictive value fluctuated between 48.7\% and 97.4\%. Further, we found a lack of details around participants' demographics and, where these were reported, important imbalances in sex and ethnicity in the studies evaluating such products. Finally, evaluation methods as well as accuracy and validity metrics of available tools were not clearly reported in some cases and varied greatly across studies. Different comparators were also used, with some studies validating their tools against the Diagnostic and Statistical Manual of Mental Disorders criteria and others through self-reported measures. Further, while in most cases, 2 classes were used for algorithm validation purposes, 1 of the studies reported a third category (indeterminate). These discrepancies substantially impact the comparability and generalizability of the results, thus highlighting the need for standardized validation processes and the reporting of findings. Conclusions: Despite their popularity, systematic evaluations and syntheses of the current state of the art of digital health products are lacking. Standardized and transparent evaluations of digital health tools in diverse populations are needed to assess their real-world usability and validity, as well as help researchers, clinicians, and end users safely adopt novel tools within clinical and research practices. ",
doi="10.2196/52377",
url="https://mhealth.jmir.org/2023/1/e52377",
url="http://www.ncbi.nlm.nih.gov/pubmed/37976084"
}


@Article{info:doi/10.2196/48210,
author="Diaz-Ramos, E. Ramon
and Noriega, Isabella
and Trejo, A. Luis
and Stroulia, Eleni
and Cao, Bo",
title="Using Wearable Devices and Speech Data for Personalized Machine Learning in Early Detection of Mental Disorders: Protocol for a Participatory Research Study",
journal="JMIR Res Protoc",
year="2023",
month="Nov",
day="13",
volume="12",
pages="e48210",
keywords="machine learning",
keywords="speech analysis",
keywords="Depression, Anxiety, and Stress Scale",
keywords="DASS21",
keywords="depression",
keywords="anxiety",
keywords="stress",
keywords="mood disorders",
keywords="mental health",
keywords="voice",
keywords="smartwatches",
keywords="wearables",
abstract="Background: Early identification of mental disorder symptoms is crucial for timely treatment and reduction of recurring symptoms and disabilities. A tool to help individuals recognize warning signs is important. We posit that such a tool would have to rely on longitudinal analysis of patterns and trends in the individual's daily activities and mood, which can now be captured through data from wearable activity trackers, speech recordings from mobile devices, and the individual's own description of their mental state. In this paper, we describe such a tool developed by our team to detect early signs of depression, anxiety, and stress. Objective: This study aims to examine three questions about the effectiveness of machine learning models constructed based on multimodal data from wearables, speech, and self-reports: (1) How does speech about issues of personal context differ from speech while reading a neutral text, what type of speech data are more helpful in detecting mental health indicators, and how is the quality of the machine learning models influenced by multilanguage data? (2) Does accuracy improve with longitudinal data collection and how, and what are the most important features? and (3) How do personalized machine learning models compare against population-level models? Methods: We collect longitudinal data to aid machine learning in accurately identifying patterns of mental disorder symptoms. We developed an app that collects voice, physiological, and activity data. Physiological and activity data are provided by a variety of off-the-shelf fitness trackers, that record steps, active minutes, duration of sleeping stages (rapid eye movement, deep, and light sleep), calories consumed, distance walked, heart rate, and speed. We also collect voice recordings of users reading specific texts and answering open-ended questions chosen randomly from a set of questions without repetition. Finally, the app collects users' answers to the Depression, Anxiety, and Stress Scale. The collected data from wearable devices and voice recordings will be used to train machine learning models to predict the levels of anxiety, stress, and depression in participants. Results: The study is ongoing, and data collection will be completed by November 2023. We expect to recruit at least 50 participants attending 2 major universities (in Canada and Mexico) fluent in English or Spanish. The study will include participants aged between 18 and 35 years, with no communication disorders, acute neurological diseases, or history of brain damage. Data collection complied with ethical and privacy requirements. Conclusions: The study aims to advance personalized machine learning for mental health; generate a data set to predict Depression, Anxiety, and Stress Scale results; and deploy a framework for early detection of depression, anxiety, and stress. Our long-term goal is to develop a noninvasive and objective method for collecting mental health data and promptly detecting mental disorder symptoms. International Registered Report Identifier (IRRID): DERR1-10.2196/48210 ",
doi="10.2196/48210",
url="https://www.researchprotocols.org/2023/1/e48210",
url="http://www.ncbi.nlm.nih.gov/pubmed/37955959"
}


@Article{info:doi/10.2196/50924,
author="Watase, Teruhisa
and Omiya, Yasuhiro
and Tokuno, Shinichi",
title="Severity Classification Using Dynamic Time Warping--Based Voice Biomarkers for Patients With COVID-19: Feasibility Cross-Sectional Study",
journal="JMIR Biomed Eng",
year="2023",
month="Nov",
day="6",
volume="8",
pages="e50924",
keywords="voice biomarker",
keywords="dynamic time warping",
keywords="COVID-19",
keywords="smartphone",
keywords="severity classification",
keywords="biomarker",
keywords="feasibility study",
keywords="illness",
keywords="monitoring",
keywords="respiratory disease",
keywords="accuracy",
keywords="logistic model",
keywords="tool",
keywords="model",
abstract="Background: In Japan, individuals with mild COVID-19 illness previously required to be monitored in designated areas and were hospitalized only if their condition worsened to moderate illness or worse. Daily monitoring using a pulse oximeter was a crucial indicator for hospitalization. However, a drastic increase in the number of patients resulted in a shortage of pulse oximeters for monitoring. Therefore, an alternative and cost-effective method for monitoring patients with mild illness was required. Previous studies have shown that voice biomarkers for Parkinson disease or Alzheimer disease are useful for classifying or monitoring symptoms; thus, we tried to adapt voice biomarkers for classifying the severity of COVID-19 using a dynamic time warping (DTW) algorithm where voice wavelets can be treated as 2D features; the differences between wavelet features are calculated as scores. Objective: This feasibility study aimed to test whether DTW-based indices can generate voice biomarkers for a binary classification model using COVID-19 patients' voices to distinguish moderate illness from mild illness at a significant level. Methods: We conducted a cross-sectional study using voice samples of COVID-19 patients. Three kinds of long vowels were processed into 10-cycle waveforms with standardized power and time axes. The DTW-based indices were generated by all pairs of waveforms and tested with the Mann-Whitney U test ($\alpha$<.01) and verified with a linear discrimination analysis and confusion matrix to determine which indices were better for binary classification of disease severity. A binary classification model was generated based on a generalized linear model (GLM) using the most promising indices as predictors. The receiver operating characteristic curve/area under the curve (ROC/AUC) validated the model performance, and the confusion matrix calculated the model accuracy. Results: Participants in this study (n=295) were infected with COVID-19 between June 2021 and March 2022, were aged 20 years or older, and recuperated in Kanagawa prefecture. Voice samples (n=110) were selected from the participants' attribution matrix based on age group, sex, time of infection, and whether they had mild illness (n=61) or moderate illness (n=49). The DTW-based variance indices were found to be significant (P<.001, except for 1 of 6 indices), with a balanced accuracy in the range between 79\% and 88.6\% for the /a/, /e/, and /u/ vowel sounds. The GLM achieved a high balance accuracy of 86.3\% (for /a/), 80.2\% (for /e/), and 88\% (for /u/) and ROC/AUC of 94.8\% (95\% CI 90.6\%-94.8\%) for /a/, 86.5\% (95\% CI 79.8\%-86.5\%) for /e/, and 95.6\% (95\% CI 92.1\%-95.6\%) for /u/. Conclusions: The proposed model can be a voice biomarker for an alternative and cost-effective method of monitoring the progress of COVID-19 patients in care. ",
doi="10.2196/50924",
url="https://biomedeng.jmir.org/2023/1/e50924",
url="http://www.ncbi.nlm.nih.gov/pubmed/37982072"
}


@Article{info:doi/10.2196/49096,
author="Jenci?t?, Gabriel?
and Kasputyt?, Gabriel?
and Bunevi{\v c}ien?, Inesa
and Korobeinikova, Erika
and Vaitiekus, Domas
and In{\v c}i?ra, Arturas
and Jaru{\vs}evi{\v c}ius, Laimonas
and Bunevi{\v c}ius, Romas
and Krik{\vs}tolaitis, Ri{\v c}ardas
and Krilavi{\v c}ius, Tomas
and Juozaityt?, Elona
and Bunevi{\v c}ius, Adomas",
title="Digital Phenotyping for Monitoring and Disease Trajectory Prediction of Patients With Cancer: Protocol for a Prospective Observational Cohort Study",
journal="JMIR Res Protoc",
year="2023",
month="Oct",
day="10",
volume="12",
pages="e49096",
keywords="cancer",
keywords="digital phenotyping",
keywords="biomarkers",
keywords="oncology",
keywords="digital phenotype",
keywords="biomarker",
keywords="data collection",
keywords="data generation",
keywords="monitor",
keywords="monitoring",
keywords="predict",
keywords="prediction",
keywords="model",
keywords="models",
keywords="mobile phone",
abstract="Background: Timely recognition of cancer progression and treatment complications is important for treatment guidance. Digital phenotyping is a promising method for precise and remote monitoring of patients in their natural environments by using passively generated data from sensors of personal wearable devices. Further studies are needed to better understand the potential clinical benefits of digital phenotyping approaches to optimize care of patients with cancer. Objective: We aim to evaluate whether passively generated data from smartphone sensors are feasible for remote monitoring of patients with cancer to predict their disease trajectories and patient-centered health outcomes. Methods: We will recruit 200 patients undergoing treatment for cancer. Patients will be followed up for 6 months. Passively generated data by sensors of personal smartphone devices (eg, accelerometer, gyroscope, GPS) will be continuously collected using the developed LAIMA smartphone app during follow-up. We will evaluate (1) mobility data by using an accelerometer (mean time of active period, mean time of exertional physical activity, distance covered per day, duration of inactive period), GPS (places of interest visited daily, hospital visits), and gyroscope sensors and (2) sociability indices (frequency of duration of phone calls, frequency and length of text messages, and internet browsing time). Every 2 weeks, patients will be asked to complete questionnaires pertaining to quality of life (European Organization for Research and Treatment of Cancer Core Quality of Life Questionnaire [EORTC QLQ-C30]), depression symptoms (Patient Health Questionnaire-9 [PHQ-9]), and anxiety symptoms (General Anxiety Disorder-7 [GAD-7]) that will be deployed via the LAIMA app. Clinic visits will take place at 1-3 months and 3-6 months of the study. Patients will be evaluated for disease progression, cancer and treatment complications, and functional status (Eastern Cooperative Oncology Group) by the study oncologist and will complete the questionnaire for evaluating quality of life (EORTC QLQ-C30), depression symptoms (PHQ-9), and anxiety symptoms (GAD-7). We will examine the associations among digital, clinical, and patient-reported health outcomes to develop prediction models with clinically meaningful outcomes. Results: As of July 2023, we have reached the planned recruitment target, and patients are undergoing follow-up. Data collection is expected to be completed by September 2023. The final results should be available within 6 months after study completion. Conclusions: This study will provide in-depth insight into temporally and spatially precise trajectories of patients with cancer that will provide a novel digital health approach and will inform the design of future interventional clinical trials in oncology. Our findings will allow a better understanding of the potential clinical value of passively generated smartphone sensor data (digital phenotyping) for continuous and real-time monitoring of patients with cancer for treatment side effects, cancer complications, functional status, and patient-reported outcomes as well as prediction of disease progression or trajectories. International Registered Report Identifier (IRRID): PRR1-10.2196/49096 ",
doi="10.2196/49096",
url="https://www.researchprotocols.org/2023/1/e49096",
url="http://www.ncbi.nlm.nih.gov/pubmed/37815850"
}


@Article{info:doi/10.2196/44502,
author="Oudin, Antoine
and Maatoug, Redwan
and Bourla, Alexis
and Ferreri, Florian
and Bonnot, Olivier
and Millet, Bruno
and Schoeller, F{\'e}lix
and Mouchabac, St{\'e}phane
and Adrien, Vladimir",
title="Digital Phenotyping: Data-Driven Psychiatry to Redefine Mental Health",
journal="J Med Internet Res",
year="2023",
month="Oct",
day="4",
volume="25",
pages="e44502",
keywords="digital phenotype",
keywords="empowerment",
keywords="mental health",
keywords="personalized medicine",
keywords="psychiatry",
doi="10.2196/44502",
url="https://www.jmir.org/2023/1/e44502",
url="http://www.ncbi.nlm.nih.gov/pubmed/37792430"
}


@Article{info:doi/10.2196/40197,
author="Kelkar, Suneel Radhika
and Currey, Danielle
and Nagendra, Srilakshmi
and Mehta, Meherwan Urvakhsh
and Sreeraj, S. Vanteemar
and Torous, John
and Thirthalli, Jagadisha",
title="Utility of Smartphone-Based Digital Phenotyping Biomarkers in Assessing Treatment Response to Transcranial Magnetic Stimulation in Depression: Proof-of-Concept Study",
journal="JMIR Form Res",
year="2023",
month="Sep",
day="1",
volume="7",
pages="e40197",
keywords="theta burst stimulation",
keywords="treatment response",
keywords="predictive biomarker",
keywords="outcome",
keywords="digital phenotyping",
keywords="transcranial magnetic stimulation",
keywords="TMS",
keywords="depression",
keywords="smartphone",
keywords="mobile phone",
abstract="Background: Identifying biomarkers of response to transcranial magnetic stimulation (TMS) in treatment-resistant depression is a priority for personalizing care. Clinical and neurobiological determinants of treatment response to TMS, while promising, have limited scalability. Therefore, evaluating novel, technologically driven, and potentially scalable biomarkers, such as digital phenotyping, is necessary. Objective: This study aimed to examine the potential of smartphone-based digital phenotyping and its feasibility as a predictive biomarker of treatment response to TMS in depression. Methods: We assessed the feasibility of digital phenotyping by examining the adherence and retention rates. We used smartphone data from passive sensors as well as active symptom surveys to determine treatment response in a naturalistic course of TMS treatment for treatment-resistant depression. We applied a scikit-learn logistic regression model (l1 ratio=0.5; 2-fold cross-validation) using both active and passive data. We analyzed related variance metrics throughout the entire treatment duration and on a weekly basis to predict responders and nonresponders to TMS, defined as ?50\% reduction in clinician-rated symptom severity from baseline. Results: The adherence rate was 89.47\%, and the retention rate was 73\%. The area under the curve for correct classification of TMS response ranged from 0.59 (passive data alone) to 0.911 (both passive and active data) for data collected throughout the treatment course. Importantly, a model using the average of all features (passive and active) for the first week had an area under the curve of 0.7375 in predicting responder status at the end of the treatment. Conclusions: The results of our study suggest that it is feasible to use digital phenotyping data to assess response to TMS in depression. Early changes in digital phenotyping biomarkers, such as predicting response from the first week of data, as shown in our results, may also help guide the treatment course. ",
doi="10.2196/40197",
url="https://formative.jmir.org/2023/1/e40197",
url="http://www.ncbi.nlm.nih.gov/pubmed/37656496"
}


@Article{info:doi/10.2196/47084,
author="Edgcomb, Beni Juliet
and Tseng, Chi-hong
and Pan, Mengtong
and Klomhaus, Alexandra
and Zima, T. Bonnie",
title="Assessing Detection of Children With Suicide-Related Emergencies: Evaluation and Development of Computable Phenotyping Approaches",
journal="JMIR Ment Health",
year="2023",
month="Jul",
day="21",
volume="10",
pages="e47084",
keywords="child mental health",
keywords="suicide",
keywords="self-harm",
keywords="machine learning",
keywords="phenotyping",
abstract="Background: Although suicide is a leading cause of death among children, the optimal approach for using health care data sets to detect suicide-related emergencies among children is not known. Objective: This study aimed to assess the performance of suicide-related International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) codes and suicide-related chief complaint in detecting self-injurious thoughts and behaviors (SITB) among children compared with clinician chart review. The study also aimed to examine variations in performance by child sociodemographics and type of self-injury, as well as develop machine learning models trained on codified health record data (features) and clinician chart review (gold standard) and test model detection performance. Methods: A gold standard classification of suicide-related emergencies was determined through clinician manual review of clinical notes from 600 emergency department visits between 2015 and 2019 by children aged 10 to 17 years. Visits classified with nonfatal suicide attempt or intentional self-harm using the Centers for Disease Control and Prevention surveillance case definition list of ICD-10-CM codes and suicide-related chief complaint were compared with the gold standard classification. Machine learning classifiers (least absolute shrinkage and selection operator--penalized logistic regression and random forest) were then trained and tested using codified health record data (eg, child sociodemographics, medications, disposition, and laboratory testing) and the gold standard classification. The accuracy, sensitivity, and specificity of each detection approach and relative importance of features were examined. Results: SITB accounted for 47.3\% (284/600) of the visits. Suicide-related diagnostic codes missed nearly one-third (82/284, 28.9\%) and suicide-related chief complaints missed more than half (153/284, 53.9\%) of the children presenting to emergency departments with SITB. Sensitivity was significantly lower for male children than for female children (0.69, 95\% CI 0.61-0.77 vs 0.84, 95\% CI 0.78-0.90, respectively) and for preteens compared with adolescents (0.66, 95\% CI 0.54-0.78 vs 0.86, 95\% CI 0.80-0.92, respectively). Specificity was significantly lower for detecting preparatory acts (0.68, 95\% CI 0.64-0.72) and attempts (0.67, 95\% CI 0.63-0.71) than for detecting ideation (0.79, 95\% CI 0.75-0.82). Machine learning--based models significantly improved the sensitivity of detection compared with suicide-related codes and chief complaint alone. Models considering all 84 features performed similarly to models considering only mental health--related ICD-10-CM codes and chief complaints (34 features) and models considering non--ICD-10-CM code indicators and mental health--related chief complaints (53 features). Conclusions: The capacity to detect children with SITB may be strengthened by applying a machine learning--based approach to codified health record data. To improve integration between clinical research informatics and child mental health care, future research is needed to evaluate the potential benefits of implementing detection approaches at the point of care and identifying precise targets for suicide prevention interventions in children. ",
doi="10.2196/47084",
url="https://mental.jmir.org/2023/1/e47084",
url="http://www.ncbi.nlm.nih.gov/pubmed/37477974"
}


@Article{info:doi/10.2196/46105,
author="Idrisoglu, Alper
and Dallora, Luiza Ana
and Anderberg, Peter
and Berglund, Sanmartin Johan",
title="Applied Machine Learning Techniques to Diagnose Voice-Affecting Conditions and Disorders: Systematic Literature Review",
journal="J Med Internet Res",
year="2023",
month="Jul",
day="19",
volume="25",
pages="e46105",
keywords="diagnosis",
keywords="digital biomarkers",
keywords="machine learning",
keywords="monitoring",
keywords="voice-affecting disorder",
keywords="voice features",
abstract="Background: Normal voice production depends on the synchronized cooperation of multiple physiological systems, which makes the voice sensitive to changes. Any systematic, neurological, and aerodigestive distortion is prone to affect voice production through reduced cognitive, pulmonary, and muscular functionality. This sensitivity inspired using voice as a biomarker to examine disorders that affect the voice. Technological improvements and emerging machine learning (ML) technologies have enabled possibilities of extracting digital vocal features from the voice for automated diagnosis and monitoring systems. Objective: This study aims to summarize a comprehensive view of research on voice-affecting disorders that uses ML techniques for diagnosis and monitoring through voice samples where systematic conditions, nonlaryngeal aerodigestive disorders, and neurological disorders are specifically of interest. Methods: This systematic literature review (SLR) investigated the state of the art of voice-based diagnostic and monitoring systems with ML technologies, targeting voice-affecting disorders without direct relation to the voice box from the point of view of applied health technology. Through a comprehensive search string, studies published from 2012 to 2022 from the databases Scopus, PubMed, and Web of Science were scanned and collected for assessment. To minimize bias, retrieval of the relevant references in other studies in the field was ensured, and 2 authors assessed the collected studies. Low-quality studies were removed through a quality assessment and relevant data were extracted through summary tables for analysis. The articles were checked for similarities between author groups to prevent cumulative redundancy bias during the screening process, where only 1 article was included from the same author group. Results: In the analysis of the 145 included studies, support vector machines were the most utilized ML technique (51/145, 35.2\%), with the most studied disease being Parkinson disease (PD; reported in 87/145, 60\%, studies). After 2017, 16 additional voice-affecting disorders were examined, in contrast to the 3 investigated previously. Furthermore, an upsurge in the use of artificial neural network--based architectures was observed after 2017. Almost half of the included studies were published in last 2 years (2021 and 2022). A broad interest from many countries was observed. Notably, nearly one-half (n=75) of the studies relied on 10 distinct data sets, and 11/145 (7.6\%) used demographic data as an input for ML models. Conclusions: This SLR revealed considerable interest across multiple countries in using ML techniques for diagnosing and monitoring voice-affecting disorders, with PD being the most studied disorder. However, the review identified several gaps, including limited and unbalanced data set usage in studies, and a focus on diagnostic test rather than disorder-specific monitoring. Despite the limitations of being constrained by only peer-reviewed publications written in English, the SLR provides valuable insights into the current state of research on ML-based voice-affecting disorder diagnosis and monitoring and highlighting areas to address in future research. ",
doi="10.2196/46105",
url="https://www.jmir.org/2023/1/e46105",
url="http://www.ncbi.nlm.nih.gov/pubmed/37467031"
}


@Article{info:doi/10.2196/45614,
author="Boussina, Aaron
and Wardi, Gabriel
and Shashikumar, Prajwal Supreeth
and Malhotra, Atul
and Zheng, Kai
and Nemati, Shamim",
title="Representation Learning and Spectral Clustering for the Development and External Validation of Dynamic Sepsis Phenotypes: Observational Cohort Study",
journal="J Med Internet Res",
year="2023",
month="Jun",
day="23",
volume="25",
pages="e45614",
keywords="sepsis",
keywords="phenotype",
keywords="emergency service, hospital",
keywords="disease progression",
keywords="artificial intelligence",
keywords="machine learning",
keywords="emergency",
keywords="infection",
keywords="clinical phenotype",
keywords="clinical phenotyping",
keywords="transition model",
keywords="transition modeling",
abstract="Background: Recent attempts at clinical phenotyping for sepsis have shown promise in identifying groups of patients with distinct treatment responses. Nonetheless, the replicability and actionability of these phenotypes remain an issue because the patient trajectory is a function of both the patient's physiological state and the interventions they receive. Objective: We aimed to develop a novel approach for deriving clinical phenotypes using unsupervised learning and transition modeling. Methods: Forty commonly used clinical variables from the electronic health record were used as inputs to a feed-forward neural network trained to predict the onset of sepsis. Using spectral clustering on the representations from this network, we derived and validated consistent phenotypes across a diverse cohort of patients with sepsis. We modeled phenotype dynamics as a Markov decision process with transitions as a function of the patient's current state and the interventions they received. Results: Four consistent and distinct phenotypes were derived from over 11,500 adult patients who were admitted from the University of California, San Diego emergency department (ED) with sepsis between January 1, 2016, and January 31, 2020. Over 2000 adult patients admitted from the University of California, Irvine ED with sepsis between November 4, 2017, and August 4, 2022, were involved in the external validation. We demonstrate that sepsis phenotypes are not static and evolve in response to physiological factors and based on interventions. We show that roughly 45\% of patients change phenotype membership within the first 6 hours of ED arrival. We observed consistent trends in patient dynamics as a function of interventions including early administration of antibiotics. Conclusions: We derived and describe 4 sepsis phenotypes present within 6 hours of triage in the ED. We observe that the administration of a 30 mL/kg fluid bolus may be associated with worse outcomes in certain phenotypes, whereas prompt antimicrobial therapy is associated with improved outcomes. ",
doi="10.2196/45614",
url="https://www.jmir.org/2023/1/e45614",
url="http://www.ncbi.nlm.nih.gov/pubmed/37351927"
}


@Article{info:doi/10.2196/46103,
author="Fischer, Aurelie
and Aguayo, A. Gloria
and Oustric, Pauline
and Morin, Laurent
and Larche, Jerome
and Benoy, Charles
and Fagherazzi, Guy",
title="Co-Design of a Voice-Based Digital Health Solution to Monitor Persisting Symptoms Related to COVID-19 (UpcomingVoice Study): Protocol for a Mixed Methods Study",
journal="JMIR Res Protoc",
year="2023",
month="Jun",
day="19",
volume="12",
pages="e46103",
keywords="COVID-19",
keywords="long COVID symptoms",
keywords="vocal biomarkers",
keywords="digital health",
keywords="co-design",
keywords="mixed methods",
keywords="mobile phone",
abstract="Background: Between 10\% and 20\% of people with a COVID-19 infection will develop the so-called long COVID syndrome, which is characterized by fluctuating symptoms. Long COVID has a high impact on the quality of life of affected people, who often feel abandoned by the health care system and are demanding new tools to help them manage their symptoms. New digital monitoring solutions could allow them to visualize the evolution of their symptoms and could be tools to communicate with health care professionals (HCPs). The use of voice and vocal biomarkers could facilitate the accurate and objective monitoring of persisting and fluctuating symptoms. However, to assess the needs and ensure acceptance of this innovative approach by its potential users---people with persisting COVID-19--related symptoms, with or without a long COVID diagnosis, and HCPs involved in long COVID care---it is crucial to include them in the entire development process. Objective: In the UpcomingVoice study, we aimed to define the most relevant aspects of daily life that people with long COVID would like to be improved, assess how the use of voice and vocal biomarkers could be a potential solution to help them, and determine the general specifications and specific items of a digital health solution to monitor long COVID symptoms using vocal biomarkers with its end users. Methods: UpcomingVoice is a cross-sectional mixed methods study and consists of a quantitative web-based survey followed by a qualitative phase based on semistructured individual interviews and focus groups. People with long COVID and HCPs in charge of patients with long COVID will be invited to participate in this fully web-based study. The quantitative data collected from the survey will be analyzed using descriptive statistics. Qualitative data from the individual interviews and the focus groups will be transcribed and analyzed using a thematic analysis approach. Results: The study was approved by the National Research Ethics Committee of Luxembourg (number 202208/04) in August 2022 and started in October 2022 with the launch of the web-based survey. Data collection will be completed in September 2023, and the results will be published in 2024. Conclusions: This mixed methods study will identify the needs of people affected by long COVID in their daily lives and describe the main symptoms or problems that would need to be monitored and improved. We will determine how using voice and vocal biomarkers could meet these needs and codevelop a tailored voice-based digital health solution with its future end users. This project will contribute to improving the quality of life and care of people with long COVID. The potential transferability to other diseases will be explored, which will contribute to the deployment of vocal biomarkers in general. Trial Registration: ClinicalTrials.gov NCT05546918; https://clinicaltrials.gov/ct2/show/NCT05546918 International Registered Report Identifier (IRRID): DERR1-10.2196/46103 ",
doi="10.2196/46103",
url="https://www.researchprotocols.org/2023/1/e46103",
url="http://www.ncbi.nlm.nih.gov/pubmed/37335611"
}


@Article{info:doi/10.2196/44986,
author="Braund, A. Taylor
and O'Dea, Bridianne
and Bal, Debopriyo
and Maston, Kate
and Larsen, Mark
and Werner-Seidler, Aliza
and Tillman, Gabriel
and Christensen, Helen",
title="Associations Between Smartphone Keystroke Metadata and Mental Health Symptoms in Adolescents: Findings From the Future Proofing Study",
journal="JMIR Ment Health",
year="2023",
month="May",
day="15",
volume="10",
pages="e44986",
keywords="adolescents",
keywords="anxiety",
keywords="depression",
keywords="digital phenotype",
keywords="keystroke dynamics",
keywords="keystroke metadata",
keywords="smartphone",
keywords="students",
abstract="Background: Mental disorders are prevalent during adolescence. Among the digital phenotypes currently being developed to monitor mental health symptoms, typing behavior is one promising candidate. However, few studies have directly assessed associations between typing behavior and mental health symptom severity, and whether these relationships differs between genders. Objective: In a cross-sectional analysis of a large cohort, we tested whether various features of typing behavior derived from keystroke metadata were associated with mental health symptoms and whether these relationships differed between genders. Methods: A total of 934 adolescents from the Future Proofing study undertook 2 typing tasks on their smartphones through the Future Proofing app. Common keystroke timing and frequency features were extracted across tasks. Mental health symptoms were assessed using the Patient Health Questionnaire-Adolescent version, the Children's Anxiety Scale-Short Form, the Distress Questionnaire 5, and the Insomnia Severity Index. Bivariate correlations were used to test whether keystroke features were associated with mental health symptoms. The false discovery rates of P values were adjusted to q values. Machine learning models were trained and tested using independent samples (ie, 80\% train 20\% test) to identify whether keystroke features could be combined to predict mental health symptoms. Results: Keystroke timing features showed a weak negative association with mental health symptoms across participants. When split by gender, females showed weak negative relationships between keystroke timing features and mental health symptoms, and weak positive relationships between keystroke frequency features and mental health symptoms. The opposite relationships were found for males (except for dwell). Machine learning models using keystroke features alone did not predict mental health symptoms. Conclusions: Increased mental health symptoms are weakly associated with faster typing, with important gender differences. Keystroke metadata should be collected longitudinally and combined with other digital phenotypes to enhance their clinical relevance. Trial Registration: Australian and New Zealand Clinical Trial Registry, ACTRN12619000855123; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=377664\&isReview=true ",
doi="10.2196/44986",
url="https://mental.jmir.org/2023/1/e44986",
url="http://www.ncbi.nlm.nih.gov/pubmed/37184904"
}


@Article{info:doi/10.2196/45405,
author="Anmella, Gerard
and Corponi, Filippo
and Li, M. Bryan
and Mas, Ariadna
and Sanabra, Miriam
and Pacchiarotti, Isabella
and Valent{\'i}, Marc
and Grande, Iria
and Benabarre, Antoni
and Gim{\'e}nez-Palomo, Anna
and Garriga, Marina
and Agasi, Isabel
and Bastidas, Anna
and Cavero, Myriam
and Fern{\'a}ndez-Plaza, Tabatha
and Arbelo, N{\'e}stor
and Bioque, Miquel
and Garc{\'i}a-Rizo, Clemente
and Verdolini, Norma
and Madero, Santiago
and Murru, Andrea
and Amoretti, Silvia
and Mart{\'i}nez-Aran, Anabel
and Ruiz, Victoria
and Fico, Giovanna
and De Prisco, Michele
and Oliva, Vincenzo
and Solanes, Aleix
and Radua, Joaquim
and Samalin, Ludovic
and Young, H. Allan
and Vieta, Eduard
and Vergari, Antonio
and Hidalgo-Mazzei, Diego",
title="Exploring Digital Biomarkers of Illness Activity in Mood Episodes: Hypotheses Generating and Model Development Study",
journal="JMIR Mhealth Uhealth",
year="2023",
month="May",
day="4",
volume="11",
pages="e45405",
keywords="depression",
keywords="mania",
keywords="bipolar disorder",
keywords="major depressive disorder",
keywords="machine learning",
keywords="deep learning",
keywords="physiological data",
keywords="digital biomarker",
keywords="wearable",
keywords="Empatica E4",
abstract="Background: Depressive and manic episodes within bipolar disorder (BD) and major depressive disorder (MDD) involve altered mood, sleep, and activity, alongside physiological alterations wearables can capture. Objective: Firstly, we explored whether physiological wearable data could predict (aim 1) the severity of an acute affective episode at the intra-individual level and (aim 2) the polarity of an acute affective episode and euthymia among different individuals. Secondarily, we explored which physiological data were related to prior predictions, generalization across patients, and associations between affective symptoms and physiological data. Methods: We conducted a prospective exploratory observational study including patients with BD and MDD on acute affective episodes (manic, depressed, and mixed) whose physiological data were recorded using a research-grade wearable (Empatica E4) across 3 consecutive time points (acute, response, and remission of episode). Euthymic patients and healthy controls were recorded during a single session (approximately 48 h). Manic and depressive symptoms were assessed using standardized psychometric scales. Physiological wearable data included the following channels: acceleration (ACC), skin temperature, blood volume pulse, heart rate (HR), and electrodermal activity (EDA). Invalid physiological data were removed using a rule-based filter, and channels were time aligned at 1-second time units and segmented at window lengths of 32 seconds, as best-performing parameters. We developed deep learning predictive models, assessed the channels' individual contribution using permutation feature importance analysis, and computed physiological data to psychometric scales' items normalized mutual information (NMI). We present a novel, fully automated method for the preprocessing and analysis of physiological data from a research-grade wearable device, including a viable supervised learning pipeline for time-series analyses. Results: Overall, 35 sessions (1512 hours) from 12 patients (manic, depressed, mixed, and euthymic) and 7 healthy controls (mean age 39.7, SD 12.6 years; 6/19, 32\% female) were analyzed. The severity of mood episodes was predicted with moderate (62\%-85\%) accuracies (aim 1), and their polarity with moderate (70\%) accuracy (aim 2). The most relevant features for the former tasks were ACC, EDA, and HR. There was a fair agreement in feature importance across classification tasks (Kendall W=0.383). Generalization of the former models on unseen patients was of overall low accuracy, except for the intra-individual models. ACC was associated with ``increased motor activity'' (NMI>0.55), ``insomnia'' (NMI=0.6), and ``motor inhibition'' (NMI=0.75). EDA was associated with ``aggressive behavior'' (NMI=1.0) and ``psychic anxiety'' (NMI=0.52). Conclusions: Physiological data from wearables show potential to identify mood episodes and specific symptoms of mania and depression quantitatively, both in BD and MDD. Motor activity and stress-related physiological data (EDA and HR) stand out as potential digital biomarkers for predicting mania and depression, respectively. These findings represent a promising pathway toward personalized psychiatry, in which physiological wearable data could allow the early identification and intervention of mood episodes. ",
doi="10.2196/45405",
url="https://mhealth.jmir.org/2023/1/e45405",
url="http://www.ncbi.nlm.nih.gov/pubmed/36939345"
}


@Article{info:doi/10.2196/42714,
author="Odhiambo, Odero Chrisogonas
and Ablonczy, Lukacs
and Wright, J. Pamela
and Corbett, F. Cynthia
and Reichardt, Sydney
and Valafar, Homayoun",
title="Detecting Medication-Taking Gestures Using Machine Learning and Accelerometer Data Collected via Smartwatch Technology: Instrument Validation Study",
journal="JMIR Hum Factors",
year="2023",
month="May",
day="4",
volume="10",
pages="e42714",
keywords="machine learning",
keywords="neural networks",
keywords="automated pattern recognition",
keywords="medication adherence",
keywords="ecological momentary assessment",
keywords="digital signal processing",
keywords="digital biomarkers",
abstract="Background: Medication adherence is a global public health challenge, as only approximately 50\% of people adhere to their medication regimens. Medication reminders have shown promising results in terms of promoting medication adherence. However, practical mechanisms to determine whether a medication has been taken or not, once people are reminded, remain elusive. Emerging smartwatch technology may more objectively, unobtrusively, and automatically detect medication taking than currently available methods. Objective: This study aimed to examine the feasibility of detecting natural medication-taking gestures using smartwatches. Methods: A convenience sample (N=28) was recruited using the snowball sampling method. During data collection, each participant recorded at least 5 protocol-guided (scripted) medication-taking events and at least 10 natural instances of medication-taking events per day for 5 days. Using a smartwatch, the accelerometer data were recorded for each session at a sampling rate of 25 Hz. The raw recordings were scrutinized by a team member to validate the accuracy of the self-reports. The validated data were used to train an artificial neural network (ANN) to detect a medication-taking event. The training and testing data included previously recorded accelerometer data from smoking, eating, and jogging activities in addition to the medication-taking data recorded in this study. The accuracy of the model to identify medication taking was evaluated by comparing the ANN's output with the actual output. Results: Most (n=20, 71\%) of the 28 study participants were college students and aged 20 to 56 years. Most individuals were Asian (n=12, 43\%) or White (n=12, 43\%), single (n=24, 86\%), and right-hand dominant (n=23, 82\%). In total, 2800 medication-taking gestures (n=1400, 50\% natural plus n=1400, 50\% scripted gestures) were used to train the network. During the testing session, 560 natural medication-taking events that were not previously presented to the ANN were used to assess the network. The accuracy, precision, and recall were calculated to confirm the performance of the network. The trained ANN exhibited an average true-positive and true-negative performance of 96.5\% and 94.5\%, respectively. The network exhibited <5\% error in the incorrect classification of medication-taking gestures. Conclusions: Smartwatch technology may provide an accurate, nonintrusive means of monitoring complex human behaviors such as natural medication-taking gestures. Future research is warranted to evaluate the efficacy of using modern sensing devices and machine learning algorithms to monitor medication-taking behavior and improve medication adherence. ",
doi="10.2196/42714",
url="https://humanfactors.jmir.org/2023/1/e42714",
url="http://www.ncbi.nlm.nih.gov/pubmed/37140971"
}


@Article{info:doi/10.2196/38920,
author="Lind, N. Monika
and Kahn, E. Lauren
and Crowley, Ryann
and Reed, Wyatt
and Wicks, Geordie
and Allen, B. Nicholas",
title="Reintroducing the Effortless Assessment Research System (EARS)",
journal="JMIR Ment Health",
year="2023",
month="Apr",
day="26",
volume="10",
pages="e38920",
keywords="mobile sensing",
keywords="passive sensing",
keywords="personal sensing",
keywords="digital phenotyping",
keywords="ecological momentary assessment",
keywords="digital mental health",
doi="10.2196/38920",
url="https://mental.jmir.org/2023/1/e38920",
url="http://www.ncbi.nlm.nih.gov/pubmed/37099361"
}


@Article{info:doi/10.2196/47898,
author="Torous, John
and Benson, M. Nicole
and Myrick, Keris
and Eysenbach, Gunther",
title="Focusing on Digital Research Priorities for Advancing the Access and Quality of Mental Health",
journal="JMIR Ment Health",
year="2023",
month="Apr",
day="24",
volume="10",
pages="e47898",
keywords="digital phenotyping",
keywords="mental health",
keywords="depression",
keywords="anxiety",
keywords="smartphone",
doi="10.2196/47898",
url="https://mental.jmir.org/2023/1/e47898",
url="http://www.ncbi.nlm.nih.gov/pubmed/37093624"
}


@Article{info:doi/10.2196/44410,
author="Kaur, Savneet
and Larsen, Erik
and Harper, James
and Purandare, Bharat
and Uluer, Ahmet
and Hasdianda, Adrian Mohammad
and Umale, Arun Nikita
and Killeen, James
and Castillo, Edward
and Jariwala, Sunit",
title="Development and Validation of a Respiratory-Responsive Vocal Biomarker--Based Tool for Generalizable Detection of Respiratory Impairment: Independent Case-Control Studies in Multiple Respiratory Conditions Including Asthma, Chronic Obstructive Pulmonary Disease, and COVID-19",
journal="J Med Internet Res",
year="2023",
month="Apr",
day="14",
volume="25",
pages="e44410",
keywords="vocal biomarkers",
keywords="COVID-19",
keywords="respiratory-responsive vocal biomarker",
keywords="RRVB",
keywords="artificial intelligence",
keywords="machine learning",
keywords="asthma",
keywords="smartphones",
keywords="mobile phone",
keywords="eHealth",
keywords="mobile health",
keywords="mHealth",
keywords="respiratory symptom",
keywords="respiratory",
keywords="voice",
keywords="vocal",
keywords="sound",
keywords="speech",
abstract="Background: Vocal biomarker--based machine learning approaches have shown promising results in the detection of various health conditions, including respiratory diseases, such as asthma. Objective: This study aimed to determine whether a respiratory-responsive vocal biomarker (RRVB) model platform initially trained on an asthma and healthy volunteer (HV) data set can differentiate patients with active COVID-19 infection from asymptomatic HVs by assessing its sensitivity, specificity, and odds ratio (OR). Methods: A logistic regression model using a weighted sum of voice acoustic features was previously trained and validated on a data set of approximately 1700 patients with a confirmed asthma diagnosis and a similar number of healthy controls. The same model has shown generalizability to patients with chronic obstructive pulmonary disease, interstitial lung disease, and cough. In this study, 497 participants (female: n=268, 53.9\%; <65 years old: n=467, 94\%; Marathi speakers: n=253, 50.9\%; English speakers: n=223, 44.9\%; Spanish speakers: n=25, 5\%) were enrolled across 4 clinical sites in the United States and India and provided voice samples and symptom reports on their personal smartphones. The participants included patients who are symptomatic COVID-19 positive and negative as well as asymptomatic HVs. The RRVB model performance was assessed by comparing it with the clinical diagnosis of COVID-19 confirmed by reverse transcriptase--polymerase chain reaction. Results: The ability of the RRVB model to differentiate patients with respiratory conditions from healthy controls was previously demonstrated on validation data in asthma, chronic obstructive pulmonary disease, interstitial lung disease, and cough, with ORs of 4.3, 9.1, 3.1, and 3.9, respectively. The same RRVB model in this study in COVID-19 performed with a sensitivity of 73.2\%, specificity of 62.9\%, and OR of 4.64 (P<.001). Patients who experienced respiratory symptoms were detected more frequently than those who did not experience respiratory symptoms and completely asymptomatic patients (sensitivity: 78.4\% vs 67.4\% vs 68\%, respectively). Conclusions: The RRVB model has shown good generalizability across respiratory conditions, geographies, and languages. Results using data set of patients with COVID-19 demonstrate its meaningful potential to serve as a prescreening tool for identifying individuals at risk for COVID-19 infection in combination with temperature and symptom reports. Although not a COVID-19 test, these results suggest that the RRVB model can encourage targeted testing. Moreover, the generalizability of this model for detecting respiratory symptoms across different linguistic and geographic contexts suggests a potential path for the development and validation of voice-based tools for broader disease surveillance and monitoring applications in the future. ",
doi="10.2196/44410",
url="https://www.jmir.org/2023/1/e44410",
url="http://www.ncbi.nlm.nih.gov/pubmed/36881540"
}


@Article{info:doi/10.2196/37469,
author="Aalbers, George
and Hendrickson, T. Andrew
and Vanden Abeele, MP Mariek
and Keijsers, Loes",
title="Smartphone-Tracked Digital Markers of Momentary Subjective Stress in College Students: Idiographic Machine Learning Analysis",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Mar",
day="23",
volume="11",
pages="e37469",
keywords="mobile health",
keywords="mobile phone",
keywords="digital phenotype",
keywords="digital biomarker",
keywords="machine learning",
keywords="personalized models",
abstract="Background: Stress is an important predictor of mental health problems such as burnout and depression. Acute stress is considered adaptive, whereas chronic stress is viewed as detrimental to well-being. To aid in the early detection of chronic stress, machine learning models are increasingly trained to learn the quantitative relation from digital footprints to self-reported stress. Prior studies have investigated general principles in population-wide studies, but the extent to which the findings apply to individuals is understudied. Objective: We aimed to explore to what extent machine learning models can leverage features of smartphone app use log data to recognize momentary subjective stress in individuals, which of these features are most important for predicting stress and represent potential digital markers of stress, the nature of the relations between these digital markers and stress, and the degree to which these relations differ across people. Methods: Student participants (N=224) self-reported momentary subjective stress 5 times per day up to 60 days in total (44,381 observations); in parallel, dedicated smartphone software continuously logged their smartphone app use. We extracted features from the log data (eg, time spent on app categories such as messenger apps and proxies for sleep duration and onset) and trained machine learning models to predict momentary subjective stress from these features using 2 approaches: modeling general relations at the group level (nomothetic approach) and modeling relations for each person separately (idiographic approach). To identify potential digital markers of momentary subjective stress, we applied explainable artificial intelligence methodology (ie, Shapley additive explanations). We evaluated model accuracy on a person-to-person basis in out-of-sample observations. Results: We identified prolonged use of messenger and social network site apps and proxies for sleep duration and onset as the most important features across modeling approaches (nomothetic vs idiographic). The relations of these digital markers with momentary subjective stress differed from person to person, as did model accuracy. Sleep proxies, messenger, and social network use were heterogeneously related to stress (ie, negative in some and positive or zero in others). Model predictions correlated positively and statistically significantly with self-reported stress in most individuals (median person-specific correlation=0.15-0.19 for nomothetic models and median person-specific correlation=0.00-0.09 for idiographic models). Conclusions: Our findings indicate that smartphone log data can be used for identifying digital markers of stress and also show that the relation between specific digital markers and stress differs from person to person. These findings warrant follow-up studies in other populations (eg, professionals and clinical populations) and pave the way for similar research using physiological measures of stress. ",
doi="10.2196/37469",
url="https://mhealth.jmir.org/2023/1/e37469",
url="http://www.ncbi.nlm.nih.gov/pubmed/36951924"
}


@Article{info:doi/10.2196/42646,
author="Langener, M. Anna
and Stulp, Gert
and Kas, J. Martien
and Bringmann, F. Laura",
title="Capturing the Dynamics of the Social Environment Through Experience Sampling Methods, Passive Sensing, and Egocentric Networks: Scoping Review",
journal="JMIR Ment Health",
year="2023",
month="Mar",
day="17",
volume="10",
pages="e42646",
keywords="social context",
keywords="experience sampling method",
keywords="egocentric network",
keywords="digital phenotyping",
keywords="passive measures",
keywords="ambulatory assessment",
keywords="mobile phone",
abstract="Background: Social interactions are important for well-being, and therefore, researchers are increasingly attempting to capture people's social environment. Many different disciplines have developed tools to measure the social environment, which can be highly variable over time. The experience sampling method (ESM) is often used in psychology to study the dynamics within a person and the social environment. In addition, passive sensing is often used to capture social behavior via sensors from smartphones or other wearable devices. Furthermore, sociologists use egocentric networks to track how social relationships are changing. Each of these methods is likely to tap into different but important parts of people's social environment. Thus far, the development and implementation of these methods have occurred mostly separately from each other. Objective: Our aim was to synthesize the literature on how these methods are currently used to capture the changing social environment in relation to well-being and assess how to best combine these methods to study well-being. Methods: We conducted a scoping review according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Results: We included 275 studies. In total, 3 important points follow from our review. First, each method captures a different but important part of the social environment at a different temporal resolution. Second, measures are rarely validated (>70\% of ESM studies and 50\% of passive sensing studies were not validated), which undermines the robustness of the conclusions drawn. Third, a combination of methods is currently lacking (only 15/275, 5.5\% of the studies combined ESM and passive sensing, and no studies combined all 3 methods) but is essential in understanding well-being. Conclusions: We highlight that the practice of using poorly validated measures hampers progress in understanding the relationship between the changing social environment and well-being. We conclude that different methods should be combined more often to reduce the participants' burden and form a holistic perspective on the social environment. ",
doi="10.2196/42646",
url="https://mental.jmir.org/2023/1/e42646",
url="http://www.ncbi.nlm.nih.gov/pubmed/36930210"
}


@Article{info:doi/10.2196/39546,
author="De Boer, Christopher
and Ghomrawi, Hassan
and Zeineddin, Suhail
and Linton, Samuel
and Kwon, Soyang
and Abdullah, Fizan",
title="A Call to Expand the Scope of Digital Phenotyping",
journal="J Med Internet Res",
year="2023",
month="Mar",
day="14",
volume="25",
pages="e39546",
keywords="digital phenotyping",
keywords="wearables",
keywords="digital health",
keywords="data collection",
keywords="real-time",
keywords="data",
keywords="digital devices",
keywords="smartphones",
keywords="phenotype",
keywords="quantification",
keywords="phenotyping",
keywords="wearable devices",
keywords="tracking",
keywords="monitoring",
keywords="clinical data",
keywords="applcaition",
keywords="implementation",
doi="10.2196/39546",
url="https://www.jmir.org/2023/1/e39546",
url="http://www.ncbi.nlm.nih.gov/pubmed/36917148"
}


@Article{info:doi/10.2196/43296,
author="Niemeijer, Koen
and Mestdagh, Merijn
and Verdonck, Stijn
and Meers, Kristof
and Kuppens, Peter",
title="Combining Experience Sampling and Mobile Sensing for Digital Phenotyping With m-Path Sense: Performance Study",
journal="JMIR Form Res",
year="2023",
month="Mar",
day="7",
volume="7",
pages="e43296",
keywords="digital phenotyping",
keywords="mobile health",
keywords="mHealth",
keywords="mobile sensing",
keywords="passive sensing",
keywords="ambulatory assessment",
keywords="experience sampling",
keywords="ecological momentary assessment",
keywords="smartphones",
keywords="mobile phone",
abstract="Background: The experience sampling methodology (ESM) has long been considered as the gold standard for gathering data in everyday life. In contrast, current smartphone technology enables us to acquire data that are much richer, more continuous, and unobtrusive than is possible via ESM. Although data obtained from smartphones, known as mobile sensing, can provide useful information, its stand-alone usefulness is limited when not combined with other sources of information such as data from ESM studies. Currently, there are few mobile apps available that allow researchers to combine the simultaneous collection of ESM and mobile sensing data. Furthermore, such apps focus mostly on passive data collection with only limited functionality for ESM data collection. Objective: In this paper, we presented and evaluated the performance of m-Path Sense, a novel, full-fledged, and secure ESM platform with background mobile sensing capabilities. Methods: To create an app with both ESM and mobile sensing capabilities, we combined m-Path, a versatile and user-friendly platform for ESM, with the Copenhagen Research Platform Mobile Sensing framework, a reactive cross-platform framework for digital phenotyping. We also developed an R package, named mpathsenser, which extracts raw data to an SQLite database and allows the user to link and inspect data from both sources. We conducted a 3-week pilot study in which we delivered ESM questionnaires while collecting mobile sensing data to evaluate the app's sampling reliability and perceived user experience. As m-Path is already widely used, the ease of use of the ESM system was not investigated. Results: Data from m-Path Sense were submitted by 104 participants, totaling 69.51 GB (430.43 GB after decompression) or approximately 37.50 files or 31.10 MB per participant per day. After binning accelerometer and gyroscope data to 1 value per second using summary statistics, the entire SQLite database contained 84,299,462 observations and was 18.30 GB in size. The reliability of sampling frequency in the pilot study was satisfactory for most sensors, based on the absolute number of collected observations. However, the relative coverage rate---the ratio between the actual and expected number of measurements---was below its target value. This could mostly be ascribed to gaps in the data caused by the operating system pushing away apps running in the background, which is a well-known issue in mobile sensing. Finally, some participants reported mild battery drain, which was not considered problematic for the assessed participants' perceived user experience. Conclusions: To better study behavior in everyday life, we developed m-Path Sense, a fusion of both m-Path for ESM and Copenhagen Research Platform Mobile Sensing. Although reliable passive data collection with mobile phones remains challenging, it is a promising approach toward digital phenotyping when combined with ESM. ",
doi="10.2196/43296",
url="https://formative.jmir.org/2023/1/e43296",
url="http://www.ncbi.nlm.nih.gov/pubmed/36881444"
}


@Article{info:doi/10.2196/42935,
author="Yang, Xiao
and Knights, Jonathan
and Bangieva, Victoria
and Kambhampati, Vinayak",
title="Association Between the Severity of Depressive Symptoms and Human-Smartphone Interactions: Longitudinal Study",
journal="JMIR Form Res",
year="2023",
month="Feb",
day="22",
volume="7",
pages="e42935",
keywords="depression",
keywords="human-smartphone interaction",
keywords="longitudinal data analysis",
keywords="within-person effect",
keywords="between-person effect",
keywords="nonergodicity",
abstract="Background: Various behavioral sensing research studies have found that depressive symptoms are associated with human-smartphone interaction behaviors, including lack of diversity in unique physical locations, entropy of time spent in each location, sleep disruption, session duration, and typing speed. These behavioral measures are often tested against the total score of depressive symptoms, and the recommended practice to disaggregate within- and between-person effects in longitudinal data is often neglected. Objective: We aimed to understand depression as a multidimensional process and explore the association between specific dimensions and behavioral measures computed from passively sensed human-smartphone interactions. We also aimed to highlight the nonergodicity in psychological processes and the importance of disaggregating within- and between-person effects in the analysis. Methods: Data used in this study were collected by Mindstrong Health, a telehealth provider that focuses on individuals with serious mental illness. Depressive symptoms were measured by the Diagnostic and Statistical Manual of Mental Disorders Fifth Edition (DSM-5) Self-Rated Level 1 Cross-Cutting Symptom Measure-Adult Survey every 60 days for a year. Participants' interactions with their smartphones were passively recorded, and 5 behavioral measures were developed and were expected to be associated with depressive symptoms according to either theoretical proposition or previous empirical evidence. Multilevel modeling was used to explore the longitudinal relations between the severity of depressive symptoms and these behavioral measures. Furthermore, within- and between-person effects were disaggregated to accommodate the nonergodicity commonly found in psychological processes. Results: This study included 982 records of DSM Level 1 depressive symptom measurements and corresponding human-smartphone interaction data from 142 participants (age range 29-77 years; mean age 55.1 years, SD 10.8 years; 96 female participants). Loss of interest in pleasurable activities was associated with app count ($\gamma$10=?0.14; P=.01; within-person effect). Depressed mood was associated with typing time interval ($\gamma$05=0.88; P=.047; within-person effect) and session duration ($\gamma$05=?0.37; P=.03; between-person effect). Conclusions: This study contributes new evidence for associations between human-smartphone interaction behaviors and the severity of depressive symptoms from a dimensional perspective, and it highlights the importance of considering the nonergodicity of psychological processes and analyzing the within- and between-person effects separately. ",
doi="10.2196/42935",
url="https://formative.jmir.org/2023/1/e42935",
url="http://www.ncbi.nlm.nih.gov/pubmed/36811951"
}


@Article{info:doi/10.2196/39258,
author="Currey, Danielle
and Torous, John",
title="Digital Phenotyping Data to Predict Symptom Improvement and Mental Health App Personalization in College Students: Prospective Validation of a Predictive Model",
journal="J Med Internet Res",
year="2023",
month="Feb",
day="9",
volume="25",
pages="e39258",
keywords="mHealth",
keywords="mental health",
keywords="smartphones",
keywords="phenotype",
keywords="symptom",
keywords="college",
keywords="students",
keywords="young adults",
keywords="responsive",
keywords="personalized",
keywords="app",
keywords="application",
keywords="intervention",
keywords="effectiveness",
keywords="protocol",
keywords="model",
keywords="digital",
keywords="engagement",
keywords="algorithm",
keywords="usage",
abstract="Background: Mental health apps offer a transformative means to increase access to scalable evidence-based care for college students. Yet low rates of engagement currently preclude the effectiveness of these apps. One promising solution is to make these apps more responsive and personalized through digital phenotyping methods able to predict symptoms and offer tailored interventions. Objective: Following our protocol and using the exact model shared in that paper, our primary aim in this study is to assess the prospective validity of mental health symptom prediction using the mindLAMP app through a replication study. We also explored secondary aims around app intervention personalization and correlations of engagement with the Technology Acceptance Model (TAM) and Digital Working Alliance Inventory scale in the context of automating the study. Methods: The study was 28 days in duration and followed the published protocol, with participants collecting digital phenotyping data and being offered optional scheduled and algorithm-recommended app interventions. Study compensation was tied to the completion of weekly surveys and was not otherwise tied to engagement or use of the app. Results: The data from 67 participants were used in this analysis. The area under the curve values for the symptom prediction model ranged from 0.58 for the UCLA Loneliness Scale to 0.71 for the Patient Health Questionnaire-9. Engagement with the scheduled app interventions was high, with a study mean of 73\%, but few participants engaged with the optional recommended interventions. The perceived utility of the app in the TAM was higher (P=.01) among those completing at least one recommended intervention. Conclusions: Our results suggest how digital phenotyping methods can be used to create generalizable models that may help create more personalized and engaging mental health apps. Automating studies is feasible, and our results suggest targets to increase engagement in future studies. International Registered Report Identifier (IRRID): RR2-10.2196/37954 ",
doi="10.2196/39258",
url="https://www.jmir.org/2023/1/e39258",
url="http://www.ncbi.nlm.nih.gov/pubmed/36757759"
}


@Article{info:doi/10.2196/42611,
author="Dobson, Rosie
and Li, Lily Linwei
and Garner, Katie
and Tane, Taria
and McCool, Judith
and Whittaker, Robyn",
title="The Use of Sensors to Detect Anxiety for In-the-Moment Intervention: Scoping Review",
journal="JMIR Ment Health",
year="2023",
month="Feb",
day="2",
volume="10",
pages="e42611",
keywords="anxiety",
keywords="wearables",
keywords="sensors",
keywords="mental health",
keywords="digital mental health",
keywords="digital health intervention",
keywords="wearable device",
abstract="Background: With anxiety a growing issue and barriers to accessing support services, there is a need for innovative solutions to provide early intervention. In-the-moment interventions support individuals to recognize early signs of distress and use coping mechanisms to prevent or manage this distress. There is potential for wearable sensors linked to an individual's mobile phone to provide in-the-moment support tailored to individual needs and physiological responses. Objective: The aim of this scoping review is to examine the role of sensors in detecting the physiological signs of anxiety to initiate and direct interventions for its management. Methods: Relevant studies were identified through searches conducted in Embase, MEDLINE, APA PsycINFO, ProQuest, and Scopus. Studies were identified if they were conducted with people with stress or anxiety or at risk of anxiety and included a wearable sensor providing real-time data for in-the-moment management of anxiety. Results: Of the 1087 studies identified, 11 studies were included in the review, including 5 randomized controlled trials and 6 pilot or pretesting studies. The results showed that most studies successfully demonstrated improvements in their target variables. This included overall anxiety and stress levels, and the implementation of in-the-moment stress and anxiety management techniques such as diaphragmatic breathing. There was wide variation in the types of sensors used, physiological measures, and sensor-linked interventions. Conclusions: This review indicates that sensors are potentially a useful tool in detecting anxiety and facilitating the implementation of a known control mechanism to reduce anxiety and improve mood, but further work is needed to understand the acceptability and effectiveness of this type of intervention. ",
doi="10.2196/42611",
url="https://mental.jmir.org/2023/1/e42611",
url="http://www.ncbi.nlm.nih.gov/pubmed/36729590"
}


@Article{info:doi/10.2196/42032,
author="Haji, Shotaro
and Fujita, Koji
and Oki, Ryosuke
and Osaki, Yusuke
and Miyamoto, Ryosuke
and Morino, Hiroyuki
and Nagano, Seiichi
and Atsuta, Naoki
and Kanazawa, Yuki
and Matsumoto, Yuki
and Arisawa, Atsuko
and Kawai, Hisashi
and Sato, Yasutaka
and Sakaguchi, Satoshi
and Yagi, Kenta
and Hamatani, Tatsuto
and Kagimura, Tatsuo
and Yanagawa, Hiroaki
and Mochizuki, Hideki
and Doyu, Manabu
and Sobue, Gen
and Harada, Masafumi
and Izumi, Yuishin",
title="An Exploratory Trial of EPI-589 in Amyotrophic Lateral Sclerosis (EPIC-ALS): Protocol for a Multicenter, Open-Labeled, 24-Week, Single-Group Study",
journal="JMIR Res Protoc",
year="2023",
month="Jan",
day="30",
volume="12",
pages="e42032",
keywords="amyotrophic lateral sclerosis",
keywords="biomarker",
keywords="clinical trial",
keywords="magnetic resonance imaging",
keywords="oxidative stress",
abstract="Background: Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disorder, with its currently approved drugs, including riluzole and edaravone, showing limited therapeutic effects. Therefore, safe and effective drugs are urgently necessary. EPI-589 is an orally available, small-molecule, novel redox-active agent characterized by highly potent protective effects against oxidative stress with high blood-brain barrier permeability. Given the apparent oxidative stress and mitochondrial dysfunction involvement in the pathogenesis of ALS, EPI-589 may hold promise as a therapeutic agent. Objective: This protocol aims to describe the design and rationale for the EPI-589 Early Phase 2 Investigator-Initiated Clinical Trial for ALS (EPIC-ALS). Methods: EPIC-ALS is an explorative, open-labeled, single-arm trial that evaluates the safety and tolerability of EPI-589 in patients with ALS. This trial consists of 12-week run-in, 24-week treatment, and 4-week follow-up periods. Patients will receive 500 mg of EPI-589 3 times daily over the 24-week treatment period. Clinical assessments include the mean monthly change of Amyotrophic Lateral Sclerosis Functional Rating Scale--Revised total score. The biomarkers are selected to analyze the effect on oxidative stress and neuronal damage. The plasma biomarkers are 8-hydroxy-2{\textasciiacutex}-deoxyguanosine (8-OHdG), 3-nitrotyrosine (3-NT), neurofilament light chain (NfL), phosphorylated neurofilament heavy chain (pNfH), homocysteine, and creatinine. The cerebrospinal fluid biomarkers are 8-OHdG, 3-NT, NfL, pNfH, and ornithine. The magnetic resonance biomarkers are fractional anisotropy in the corticospinal tract and N-acetylaspartate in the primary motor area. Results: This trial began data collection in September 2021 and is expected to be completed in October 2023. Conclusions: This study can provide useful data to understand the characteristics of EPI-589. Trial Registration: Japan Primary Registries Network jRCT2061210031; tinyurl.com/2p84emu6 International Registered Report Identifier (IRRID): DERR1-10.2196/42032 ",
doi="10.2196/42032",
url="https://www.researchprotocols.org/2023/1/e42032",
url="http://www.ncbi.nlm.nih.gov/pubmed/36716091"
}


@Article{info:doi/10.2196/37225,
author="Ettore, Eric
and M{\"u}ller, Philipp
and Hinze, Jonas
and Riemenschneider, Matthias
and Benoit, Michel
and Giordana, Bruno
and Postin, Danilo
and Hurlemann, Rene
and Lecomte, Amandine
and Musiol, Michel
and Lindsay, Hali
and Robert, Philippe
and K{\"o}nig, Alexandra",
title="Digital Phenotyping for Differential Diagnosis of Major Depressive Episode: Narrative Review",
journal="JMIR Ment Health",
year="2023",
month="Jan",
day="23",
volume="10",
pages="e37225",
keywords="depression",
keywords="bipolar disorder",
keywords="posttraumatic stress disorder",
keywords="differential diagnosis",
keywords="digital phenotyping",
keywords="speech analysis",
keywords="nonverbal behavior",
keywords="physiological measures",
keywords="mental health",
keywords="clinical interview",
keywords="diagnosis",
keywords="mental disorder",
keywords="interview",
keywords="digital health",
keywords="psychotrauma",
keywords="digital",
keywords="information",
abstract="Background: Major depressive episode (MDE) is a common clinical syndrome. It can be found in different pathologies such as major depressive disorder (MDD), bipolar disorder (BD), posttraumatic stress disorder (PTSD), or even occur in the context of psychological trauma. However, only 1 syndrome is described in international classifications (Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition [DSM-5]/International Classification of Diseases 11th Revision [ICD-11]), which do not take into account the underlying pathology at the origin of the MDE. Clinical interviews are currently the best source of information to obtain the etiological diagnosis of MDE. Nevertheless, it does not allow an early diagnosis and there are no objective measures of extracted clinical information. To remedy this, the use of digital tools and their correlation with clinical symptomatology could be useful. Objective: We aimed to review the current application of digital tools for MDE diagnosis while highlighting shortcomings for further research. In addition, our work was focused on digital devices easy to use during clinical interview and mental health issues where depression is common. Methods: We conducted a narrative review of the use of digital tools during clinical interviews for MDE by searching papers published in PubMed/MEDLINE, Web of Science, and Google Scholar databases since February 2010. The search was conducted from June to September 2021. Potentially relevant papers were then compared against a checklist for relevance and reviewed independently for inclusion, with focus on 4 allocated topics of (1) automated voice analysis, behavior analysis by (2) video and physiological measures, (3) heart rate variability (HRV), and (4) electrodermal activity (EDA). For this purpose, we were interested in 4 frequently found clinical conditions in which MDE can occur: (1) MDD, (2) BD, (3) PTSD, and (4) psychological trauma. Results: A total of 74 relevant papers on the subject were qualitatively analyzed and the information was synthesized. Thus, a digital phenotype of MDE seems to emerge consisting of modifications in speech features (namely, temporal, prosodic, spectral, source, and formants) and in speech content, modifications in nonverbal behavior (head, hand, body and eyes movement, facial expressivity, and gaze), and a decrease in physiological measurements (HRV and EDA). We not only found similarities but also differences when MDE occurs in MDD, BD, PTSD, or psychological trauma. However, comparative studies were rare in BD or PTSD conditions, which does not allow us to identify clear and distinct digital phenotypes. Conclusions: Our search identified markers from several modalities that hold promise for helping with a more objective diagnosis of MDE. To validate their potential, further longitudinal and prospective studies are needed. ",
doi="10.2196/37225",
url="https://mental.jmir.org/2023/1/e37225",
url="http://www.ncbi.nlm.nih.gov/pubmed/36689265"
}


@Article{info:doi/10.2196/41427,
author="Bae, ChulYoung
and Kim, Bo-Seon
and Cho, KyungHee
and Kim, Ji-Hyun
and Kim, In-Hee
and Kim, Jeong-Hoon",
title="Effects of Customized Digital Health Care Service on Metabolic Syndrome Status and Lifestyle Using a Health Care App: Clinical Trial",
journal="JMIR Form Res",
year="2023",
month="Jan",
day="18",
volume="7",
pages="e41427",
keywords="biomarkers",
keywords="health care",
keywords="lifestyle",
keywords="metabolic syndrome",
keywords="telemedicine",
abstract="Background: Untact cultures have rapidly spread around the world as a result of the prolongation of the COVID-19 pandemic, leading to various types of research and technological developments in the fields of medicine and health care, where digital health care refers to health care services provided in a digital environment. Previous studies relating to digital health care demonstrated its effectiveness in managing chronic diseases such as hypertension and diabetes. While many studies have applied digital health care to various diseases, daily health care is needed for healthy individuals before they are diagnosed with a disease. Accordingly, research on individuals who have not been diagnosed with a disease is also necessary. Objective: This study aimed to identify the effects of using a customized digital health care service (CDHCS) on risk factors for metabolic syndrome (MS) and lifestyle improvement. Methods: The population consisted of 63 adults who underwent a health checkup at the National Health Insurance Service Ilsan (NHIS) Hospital in 2020. Measured variables include basic clinical indicators, MS-related variables, and lifestyle variables. All items were measured at NHIS Ilsan Hospital before the use of the CDHCS and 3 months thereafter. The CDHCS used in this study is a mobile app that analyzes the health condition of the user by identifying their risk factors and provides appropriate health care content. For comparison between before and after CDHCS use (pre-post comparison), paired t test was used for continuous variables, and a chi-square test was used for nominal variables. Results: The study population included 30 (47.6\%) male and 33 (52.4\%) female participants, and the mean age was 47.61 (SD 13.93) years. The changes in clinical indicators before and after intervention results showed a decrease in weight, waist circumference, triglyceride, and high-density lipoprotein cholesterol and increases in systolic blood pressure and diastolic blood pressure. The distribution of the risk group increased from 32 (50.8\%) to 34 (54\%) and that of the MS group decreased from 18 (28.6\%) to 16 (25.4\%). The mean metabolic syndrome age--chronological age before the CDHCS was 2.20 years, which decreased to 1.72 years after CDHCS, showing a decrease of 0.48 years in the mean metabolic syndrome age--chronological age after the intervention. While all lifestyle variables, except alcohol consumption, showed a tendency toward improvement, the differences were not statistically significant. Conclusions: Although there was no statistical significance in the variables under study, this pilot study will provide a foundation for more accurate verification of CDHCS in future research. ",
doi="10.2196/41427",
url="https://formative.jmir.org/2023/1/e41427",
url="http://www.ncbi.nlm.nih.gov/pubmed/36652290"
}


@Article{info:doi/10.2196/41042,
author="Motahari-Nezhad, Hossein
and Al-Abdulkarim, Hana
and Fgaier, Meriem
and Abid, Mahdi Mohamed
and P{\'e}ntek, M{\'a}rta
and Gul{\'a}csi, L{\'a}szl{\'o}
and Zrubka, Zsombor",
title="Digital Biomarker--Based Interventions: Systematic Review of Systematic Reviews",
journal="J Med Internet Res",
year="2022",
month="Dec",
day="21",
volume="24",
number="12",
pages="e41042",
keywords="digital biomarker",
keywords="digital health",
keywords="digital devices",
keywords="AMSTAR-2",
keywords="GRADE",
keywords="methodological quality",
keywords="evidence synthesis",
keywords="publication bias",
keywords="imprecision",
keywords="implantable",
keywords="wearable",
abstract="Background: The introduction of new medical technologies such as sensors has accelerated the process of collecting patient data for relevant clinical decisions, which has led to the introduction of a new technology known as digital biomarkers. Objective: This study aims to assess the methodological quality and quality of evidence from meta-analyses of digital biomarker--based interventions. Methods: This study follows the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guideline for reporting systematic reviews, including original English publications of systematic reviews reporting meta-analyses of clinical outcomes (efficacy and safety endpoints) of digital biomarker--based interventions compared with alternative interventions without digital biomarkers. Imaging or other technologies that do not measure objective physiological or behavioral data were excluded from this study. A literature search of PubMed and the Cochrane Library was conducted, limited to 2019-2020. The quality of the methodology and evidence synthesis of the meta-analyses were assessed using AMSTAR-2 (A Measurement Tool to Assess Systematic Reviews 2) and GRADE (Grading of Recommendations, Assessment, Development, and Evaluations), respectively. This study was funded by the National Research, Development and Innovation Fund of Hungary. Results: A total of 25 studies with 91 reported outcomes were included in the final analysis; 1 (4\%), 1 (4\%), and 23 (92\%) studies had high, low, and critically low methodologic quality, respectively. As many as 6 clinical outcomes (7\%) had high-quality evidence and 80 outcomes (88\%) had moderate-quality evidence; 5 outcomes (5\%) were rated with a low level of certainty, mainly due to risk of bias (85/91, 93\%), inconsistency (27/91, 30\%), and imprecision (27/91, 30\%). There is high-quality evidence of improvements in mortality, transplant risk, cardiac arrhythmia detection, and stroke incidence with cardiac devices, albeit with low reporting quality. High-quality reviews of pedometers reported moderate-quality evidence, including effects on physical activity and BMI. No reports with high-quality evidence and high methodological quality were found. Conclusions: Researchers in this field should consider the AMSTAR-2 criteria and GRADE to produce high-quality studies in the future. In addition, patients, clinicians, and policymakers are advised to consider the results of this study before making clinical decisions regarding digital biomarkers to be informed of the degree of certainty of the various interventions investigated in this study. The results of this study should be considered with its limitations, such as the narrow time frame. International Registered Report Identifier (IRRID): RR2-10.2196/28204 ",
doi="10.2196/41042",
url="https://www.jmir.org/2022/12/e41042",
url="http://www.ncbi.nlm.nih.gov/pubmed/36542427"
}


@Article{info:doi/10.2196/42249,
author="Iyer, Ravi
and Nedeljkovic, Maja
and Meyer, Denny",
title="Using Vocal Characteristics To Classify Psychological Distress in Adult Helpline Callers: Retrospective Observational Study",
journal="JMIR Form Res",
year="2022",
month="Dec",
day="19",
volume="6",
number="12",
pages="e42249",
keywords="machine learning",
keywords="distress",
keywords="voice",
keywords="mental distress",
keywords="psychological stress",
keywords="artificial intelligence",
keywords="emotional distress",
keywords="voice biomarker",
keywords="biomarker",
keywords="digital health intervention",
keywords="mental health",
keywords="mental health intervention",
keywords="psychological well being",
keywords="speech analysis",
abstract="Background: Elevated psychological distress has demonstrated impacts on individuals' health. Reliable and efficient ways to detect distress are key to early intervention. Artificial intelligence has the potential to detect states of emotional distress in an accurate, efficient, and timely manner. Objective: The aim of this study was to automatically classify short segments of speech obtained from callers to national suicide prevention helpline services according to high versus low psychological distress and using a range of vocal characteristics in combination with machine learning approaches. Methods: A total of 120 telephone call recordings were initially converted to 16-bit pulse code modulation format. Short variable-length segments of each call were rated on psychological distress using the distress thermometer by the responding counselor and a second team of psychologists (n=6) blinded to the initial ratings. Following this, 24 vocal characteristics were initially extracted from 40-ms speech frames nested within segments within calls. After highly correlated variables were eliminated, 19 remained. Of 19 vocal characteristics, 7 were identified and validated as predictors of psychological distress using a penalized generalized additive mixed effects regression model, accounting for nonlinearity, autocorrelation, and moderation by sex. Speech frames were then grouped using k-means clustering based on the selected vocal characteristics. Finally, component-wise gradient boosting incorporating these clusters was used to classify each speech frame according to high versus low psychological distress. Classification accuracy was confirmed via leave-one-caller-out cross-validation, ensuring that speech segments from individual callers were not used in both the training and test data. Results: The sample comprised 87 female and 33 male callers. From an initial pool of 19 characteristics, 7 vocal characteristics were identified. After grouping speech frames into 2 separate clusters (correlation with sex of caller, Cramer's V =0.02), the component-wise gradient boosting algorithm successfully classified psychological distress to a high level of accuracy, with an area under the receiver operating characteristic curve of 97.39\% (95\% CI 96.20-98.45) and an area under the precision-recall curve of 97.52 (95\% CI 95.71-99.12). Thus, 39,282 of 41,883 (93.39\%) speech frames nested within 728 of 754 segments (96.6\%) were classified as exhibiting low psychological distress, and 71455 of 75503 (94.64\%) speech frames nested within 382 of 423 (90.3\%) segments were classified as exhibiting high psychological distress. As the probability of high psychological distress increases, male callers spoke louder, with greater vowel articulation but with greater roughness (subharmonic depth). In contrast, female callers exhibited decreased vocal clarity (entropy), greater proportion of signal noise, higher frequencies, increased breathiness (spectral slope), and increased roughness of speech with increasing psychological distress. Individual caller random effects contributed 68\% to risk reduction in the classification algorithm, followed by cluster configuration (23.4\%), spectral slope (4.4\%), and the 50th percentile frequency (4.2\%). Conclusions: The high level of accuracy achieved suggests possibilities for real-time detection of psychological distress in helpline settings and has potential uses in pre-emptive triage and evaluations of counseling outcomes. Trial Registration: ANZCTR ACTRN12622000486729; https://www.anzctr.org.au/ACTRN12622000486729.aspx ",
doi="10.2196/42249",
url="https://formative.jmir.org/2022/12/e42249",
url="http://www.ncbi.nlm.nih.gov/pubmed/36534456"
}


@Article{info:doi/10.2196/40339,
author="Watanabe, Kazuhiro
and Tsutsumi, Akizumi",
title="The Passive Monitoring of Depression and Anxiety Among Workers Using Digital Biomarkers Based on Their Physical Activity and Working Conditions: 2-Week Longitudinal Study",
journal="JMIR Form Res",
year="2022",
month="Nov",
day="30",
volume="6",
number="11",
pages="e40339",
keywords="digital biomarkers",
keywords="mobile health",
keywords="mental health",
keywords="psychological distress",
keywords="depression",
keywords="anxiety",
keywords="physical activity",
abstract="Background: Digital data on physical activity are useful for self-monitoring and preventing depression and anxiety. Although previous studies have reported machine or deep learning models that use physical activity for passive monitoring of depression and anxiety, there are no models for workers. The working population has different physical activity patterns from other populations, which is based on commuting, holiday patterns, physical demands, occupations, and industries. These working conditions are useful in optimizing the model used in predicting depression and anxiety. Further, recurrent neural networks increase predictive accuracy by using previous inputs on physical activity, depression, and anxiety. Objective: This study evaluated the performance of a deep learning model optimized for predicting depression and anxiety in workers. Psychological distress was considered a depression and anxiety indicator. Methods: A 2-week longitudinal study was conducted with workers in urban areas in Japan. Absent workers were excluded. In a daily survey, psychological distress was measured using a self-reported questionnaire. As features, activity time by intensity was determined using the Google Fit application. Additionally, we measured age, gender, occupations, employment status, work shift types, working hours, and whether the response date was a working or nonworking day. A deep learning model, using long short-term memory, was developed and validated to predict psychological distress the next day, using features of the previous day. Further, a 5-fold cross-validation method was used to evaluate the performance of the aforementioned model. As the primary indicator of performance, classification accuracy for the severity of the psychological distress (light, subthreshold, and severe) was considered. Results: A total of 1661 days of supervised data were obtained from 236 workers, who were aged between 20 and 69 years. The overall classification accuracy for psychological distress was 76.3\% (SD 0.04\%). The classification accuracy for severe-, subthreshold-, and light-level psychological distress was 51.1\% (SD 0.05\%), 60.6\% (SD 0.05\%), and 81.6\% (SD 0.04\%), respectively. The model predicted a light-level psychological distress the next day after the participants had been involved in 3 peaks of activity (in the morning, noon, and evening) on the previous day. Lower activity levels were predicted as subthreshold- and severe-level psychological distress. Different predictive results were observed on the basis of occupations and whether the previous day was a working or nonworking day. Conclusions: The developed deep learning model showed a similar performance as in previous studies and, in particular, high accuracy for light-level psychological distress. Working conditions and long short-term memory were useful in maintaining the model performance for monitoring depression and anxiety, using digitally recorded physical activity in workers. The developed model can be implemented in mobile apps and may further be practically used by workers to self-monitor and maintain their mental health state. ",
doi="10.2196/40339",
url="https://formative.jmir.org/2022/11/e40339",
url="http://www.ncbi.nlm.nih.gov/pubmed/36449342"
}


@Article{info:doi/10.2196/41003,
author="Acien, Alejandro
and Morales, Aythami
and Vera-Rodriguez, Ruben
and Fierrez, Julian
and Mondesire-Crump, Ijah
and Arroyo-Gallego, Teresa",
title="Detection of Mental Fatigue in the General Population: Feasibility Study of Keystroke Dynamics as a Real-world Biomarker",
journal="JMIR Biomed Eng",
year="2022",
month="Nov",
day="21",
volume="7",
number="2",
pages="e41003",
keywords="fatigue",
keywords="keystroke",
keywords="biometrics",
keywords="digital biomarker",
keywords="TypeNet",
keywords="domain adaptation",
keywords="fatigue detection",
keywords="typing patterns",
keywords="circadian cycles",
keywords="mental fatigue",
keywords="psychomotor patterns",
keywords="monitoring",
keywords="mental health",
keywords="keystroke dynamics",
abstract="Background: Mental fatigue is a common and potentially debilitating state that can affect individuals' health and quality of life. In some cases, its manifestation can precede or mask early signs of other serious mental or physiological conditions. Detecting and assessing mental fatigue can be challenging nowadays as it relies on self-evaluation and rating questionnaires, which are highly influenced by subjective bias. Introducing more objective, quantitative, and sensitive methods to characterize mental fatigue could be critical to improve its management and the understanding of its connection to other clinical conditions. Objective: This paper aimed to study the feasibility of using keystroke biometrics for mental fatigue detection during natural typing. As typing involves multiple motor and cognitive processes that are affected by mental fatigue, our hypothesis was that the information captured in keystroke dynamics can offer an interesting mean to characterize users' mental fatigue in a real-world setting. Methods: We apply domain transformation techniques to adapt and transform TypeNet, a state-of-the-art deep neural network, originally intended for user authentication, to generate a network optimized for the fatigue detection task. All experiments were conducted using 3 keystroke databases that comprise different contexts and data collection protocols. Results: Our preliminary results showed area under the curve performances ranging between 72.2\% and 80\% for fatigue versus rested sample classification, which is aligned with previously published models on daily alertness and circadian cycles. This demonstrates the potential of our proposed system to characterize mental fatigue fluctuations via natural typing patterns. Finally, we studied the performance of an active detection approach that leverages the continuous nature of keystroke biometric patterns for the assessment of users' fatigue in real time. Conclusions: Our results suggest that the psychomotor patterns that characterize mental fatigue manifest during natural typing, which can be quantified via automated analysis of users' daily interaction with their device. These findings represent a step towards the development of a more objective, accessible, and transparent solution to monitor mental fatigue in a real-world environment. ",
doi="10.2196/41003",
url="https://biomedeng.jmir.org/2022/2/e41003",
url="http://www.ncbi.nlm.nih.gov/pubmed/38875698"
}


@Article{info:doi/10.2196/41014,
author="Loch, Andrade Alexandre
and Lopes-Rocha, Caroline Ana
and Ara, Anderson
and Gondim, Medrado Jo{\~a}o
and Cecchi, A. Guillermo
and Corcoran, Mary Cheryl
and Mota, Bezerra Nat{\'a}lia
and Argolo, C. Felipe",
title="Ethical Implications of the Use of Language Analysis Technologies for the Diagnosis and Prediction of Psychiatric Disorders",
journal="JMIR Ment Health",
year="2022",
month="Nov",
day="1",
volume="9",
number="11",
pages="e41014",
keywords="at-risk mental state",
keywords="psychosis",
keywords="clinical high risk",
keywords="digital phenotyping",
keywords="machine learning",
keywords="artificial intelligence",
keywords="natural language processing",
doi="10.2196/41014",
url="https://mental.jmir.org/2022/11/e41014",
url="http://www.ncbi.nlm.nih.gov/pubmed/36318266"
}


@Article{info:doi/10.2196/35722,
author="Motahari-Nezhad, Hossein
and Fgaier, Meriem
and Mahdi Abid, Mohamed
and P{\'e}ntek, M{\'a}rta
and Gul{\'a}csi, L{\'a}szl{\'o}
and Zrubka, Zsombor",
title="Digital Biomarker--Based Studies: Scoping Review of Systematic Reviews",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Oct",
day="24",
volume="10",
number="10",
pages="e35722",
keywords="scoping review",
keywords="digital biomarkers",
keywords="health",
keywords="behavioral data",
keywords="physiological data",
keywords="digital health",
keywords="remote monitoring",
keywords="wearable",
keywords="implantable",
keywords="digestible",
keywords="portable",
keywords="sensor",
keywords="mobile phone",
abstract="Background: Sensors and digital devices have revolutionized the measurement, collection, and storage of behavioral and physiological data, leading to the new term digital biomarkers. Objective: This study aimed to investigate the scope of clinical evidence covered by systematic reviews (SRs) of randomized controlled trials involving digital biomarkers. Methods: This scoping review was organized using the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. With the search limited to English publications, full-text SRs of digital biomarkers included randomized controlled trials that involved a human population and reported changes in participants' health status. PubMed and the Cochrane Library were searched with time frames limited to 2019 and 2020. The World Health Organization's classification systems for diseases (International Classification of Diseases, Eleventh Revision), health interventions (International Classification of Health Interventions), and bodily functions (International Classification of Functioning, Disability, and Health [ICF]) were used to classify populations, interventions, and outcomes, respectively. Results: A total of 31 SRs met the inclusion criteria. The majority of SRs studied patients with circulatory system diseases (19/31, 61\%) and respiratory system diseases (9/31, 29\%). Most of the prevalent interventions focused on physical activity behavior (16/31, 52\%) and conversion of cardiac rhythm (4/31, 13\%). Looking after one's health (physical activity; 15/31, 48\%), walking (12/31, 39\%), heart rhythm functions (8/31, 26\%), and mortality (7/31, 23\%) were the most commonly reported outcomes. In total, 16 physiological and behavioral data groups were identified using the ICF tool, such as looking after one's health (physical activity; 14/31, 45\%), walking (11/31, 36\%), heart rhythm (7/31, 23\%), and weight maintenance functions (7/31, 23\%). Various digital devices were also studied to collect these data in the included reviews, such as smart glasses, smartwatches, smart bracelets, smart shoes, and smart socks for measuring heart functions, gait pattern functions, and temperature. A substantial number (24/31, 77\%) of digital biomarkers were used as interventions. Moreover, wearables (22/31, 71\%) were the most common types of digital devices. Position sensors (21/31, 68\%) and heart rate sensors and pulse rate sensors (12/31, 39\%) were the most prevalent types of sensors used to acquire behavioral and physiological data in the SRs. Conclusions: In recent years, the clinical evidence concerning digital biomarkers has been systematically reviewed in a wide range of study populations, interventions, digital devices, and sensor technologies, with the dominance of physical activity and cardiac monitors. We used the World Health Organization's ICF tool for classifying behavioral and physiological data, which seemed to be an applicable tool to categorize the broad scope of digital biomarkers identified in this review. To understand the clinical value of digital biomarkers, the strength and quality of the evidence on their health consequences need to be systematically evaluated. ",
doi="10.2196/35722",
url="https://mhealth.jmir.org/2022/10/e35722",
url="http://www.ncbi.nlm.nih.gov/pubmed/36279171"
}


@Article{info:doi/10.2196/40667,
author="Zhang, Yuezhou
and Folarin, A. Amos
and Sun, Shaoxiong
and Cummins, Nicholas
and Vairavan, Srinivasan
and Qian, Linglong
and Ranjan, Yatharth
and Rashid, Zulqarnain
and Conde, Pauline
and Stewart, Callum
and Laiou, Petroula
and Sankesara, Heet
and Matcham, Faith
and White, M. Katie
and Oetzmann, Carolin
and Ivan, Alina
and Lamers, Femke
and Siddi, Sara
and Simblett, Sara
and Rintala, Aki
and Mohr, C. David
and Myin-Germeys, Inez
and Wykes, Til
and Haro, Maria Josep
and Penninx, H. Brenda W. J.
and Narayan, A. Vaibhav
and Annas, Peter
and Hotopf, Matthew
and Dobson, B. Richard J.
and ",
title="Associations Between Depression Symptom Severity and Daily-Life Gait Characteristics Derived From Long-Term Acceleration Signals in Real-World Settings: Retrospective Analysis",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Oct",
day="4",
volume="10",
number="10",
pages="e40667",
keywords="depression",
keywords="gait",
keywords="mobile health",
keywords="mHealth",
keywords="acceleration signals",
keywords="monitoring",
keywords="wearable devices",
keywords="mobile phones",
keywords="mental health",
abstract="Background: Gait is an essential manifestation of depression. However, the gait characteristics of daily walking and their relationships with depression have yet to be fully explored. Objective: The aim of this study was to explore associations between depression symptom severity and daily-life gait characteristics derived from acceleration signals in real-world settings. Methods: We used two ambulatory data sets (N=71 and N=215) with acceleration signals collected by wearable devices and mobile phones, respectively. We extracted 12 daily-life gait features to describe the distribution and variance of gait cadence and force over a long-term period. Spearman coefficients and linear mixed-effects models were used to explore the associations between daily-life gait features and depression symptom severity measured by the 15-item Geriatric Depression Scale (GDS-15) and 8-item Patient Health Questionnaire (PHQ-8) self-reported questionnaires. The likelihood-ratio (LR) test was used to test whether daily-life gait features could provide additional information relative to the laboratory gait features. Results: Higher depression symptom severity was significantly associated with lower gait cadence of high-performance walking (segments with faster walking speed) over a long-term period in both data sets. The linear regression model with long-term daily-life gait features (R2=0.30) fitted depression scores significantly better (LR test P=.001) than the model with only laboratory gait features (R2=0.06). Conclusions: This study indicated that the significant links between daily-life walking characteristics and depression symptom severity could be captured by both wearable devices and mobile phones. The daily-life gait patterns could provide additional information for predicting depression symptom severity relative to laboratory walking. These findings may contribute to developing clinical tools to remotely monitor mental health in real-world settings. ",
doi="10.2196/40667",
url="https://mhealth.jmir.org/2022/10/e40667",
url="http://www.ncbi.nlm.nih.gov/pubmed/36194451"
}


@Article{info:doi/10.2196/34768,
author="Petsani, Despoina
and Konstantinidis, Evdokimos
and Katsouli, Aikaterini-Marina
and Zilidou, Vasiliki
and Dias, B. Sofia
and Hadjileontiadis, Leontios
and Bamidis, Panagiotis",
title="Digital Biomarkers for Well-being Through Exergame Interactions: Exploratory Study",
journal="JMIR Serious Games",
year="2022",
month="Sep",
day="13",
volume="10",
number="3",
pages="e34768",
keywords="serious games",
keywords="machine learning",
keywords="physical well-being",
keywords="cognitive well-being",
abstract="Background: Ecologically valid evaluations of patient states or well-being by means of new technologies is a key issue in contemporary research in health and well-being of the aging population. The in-game metrics generated from the interaction of users with serious games (SG) can potentially be used to predict or characterize a user's state of health and well-being. There is currently an increasing body of research that investigates the use of measures of interaction with games as digital biomarkers for health and well-being. Objective: The aim of this paper is to predict well-being digital biomarkers from data collected during interactions with SG, using the values of standard clinical assessment tests as ground truth. Methods: The data set was gathered during the interaction with patients with Parkinson disease with the webFitForAll exergame platform, an SG engine designed to promote physical activity among older adults, patients, and vulnerable populations. The collected data, referred to as in-game metrics, represent the body movements captured by a 3D sensor camera and translated into game analytics. Standard clinical tests gathered before and after the long-term interaction with exergames (preintervention test vs postintervention test) were used to provide user baselines. Results: Our results showed that in-game metrics can effectively categorize participants into groups of different cognitive and physical states. Different in-game metrics have higher descriptive values for specific tests and can be used to predict the value range for these tests. Conclusions: Our results provide encouraging evidence for the value of in-game metrics as digital biomarkers and can boost the analysis of improving in-game metrics to obtain more detailed results. ",
doi="10.2196/34768",
url="https://games.jmir.org/2022/3/e34768",
url="http://www.ncbi.nlm.nih.gov/pubmed/36099000"
}


@Article{info:doi/10.2196/38130,
author="Hackett, Katherine
and Giovannetti, Tania",
title="Capturing Cognitive Aging in Vivo: Application of a Neuropsychological Framework for Emerging Digital Tools",
journal="JMIR Aging",
year="2022",
month="Sep",
day="7",
volume="5",
number="3",
pages="e38130",
keywords="digital phenotyping",
keywords="neuropsychology",
keywords="aging",
keywords="dementia",
keywords="smartphone",
keywords="neurological",
keywords="psychological",
keywords="older adults",
doi="10.2196/38130",
url="https://aging.jmir.org/2022/3/e38130",
url="http://www.ncbi.nlm.nih.gov/pubmed/36069747"
}


@Article{info:doi/10.2196/38943,
author="Choudhary, Soumya
and Thomas, Nikita
and Alshamrani, Sultan
and Srinivasan, Girish
and Ellenberger, Janine
and Nawaz, Usman
and Cohen, Roy",
title="A Machine Learning Approach for Continuous Mining of Nonidentifiable Smartphone Data to Create a Novel Digital Biomarker Detecting Generalized Anxiety Disorder: Prospective Cohort Study",
journal="JMIR Med Inform",
year="2022",
month="Aug",
day="30",
volume="10",
number="8",
pages="e38943",
keywords="digital phenotyping",
keywords="machine learning",
keywords="mental health",
keywords="profiling metric",
keywords="smartphone data",
keywords="anxiety assessment",
keywords="mining technique",
keywords="algorithm prediction",
keywords="digital marker",
keywords="behavioral marker",
keywords="anxiety",
abstract="Background: Anxiety is one of the leading causes of mental health disability around the world. Currently, a majority of the population who experience anxiety go undiagnosed or untreated. New and innovative ways of diagnosing and monitoring anxiety have emerged using smartphone sensor--based monitoring as a metric for the management of anxiety. This is a novel study as it adds to the field of research through the use of nonidentifiable smartphone usage to help detect and monitor anxiety remotely and in a continuous and passive manner. Objective: This study aims to evaluate the accuracy of a novel mental behavioral profiling metric derived from smartphone usage for the identification and tracking of generalized anxiety disorder (GAD). Methods: Smartphone data and self-reported 7-item GAD anxiety assessments were collected from 229 participants using an Android operating system smartphone in an observational study over an average of 14 days (SD 29.8). A total of 34 features were mined to be constructed as a potential digital phenotyping marker from continuous smartphone usage data. We further analyzed the correlation of these digital behavioral markers against each item of the 7-item Generalized Anxiety Disorder Scale (GAD-7) and its influence on the predictions of machine learning algorithms. Results: A total of 229 participants were recruited in this study who had completed the GAD-7 assessment and had at least one set of passive digital data collected within a 24-hour period. The mean GAD-7 score was 11.8 (SD 5.7). Regression modeling was tested against classification modeling and the highest prediction accuracy was achieved from a binary XGBoost classification model (precision of 73\%-81\%; recall of 68\%-87\%; F1-score of 71\%-79\%; accuracy of 76\%; area under the curve of 80\%). Nonparametric permutation testing with Pearson correlation results indicated that the proposed metric (Mental Health Similarity Score [MHSS]) had a colinear relationship between GAD-7 Items 1, 3 and 7. Conclusions: The proposed MHSS metric demonstrates the feasibility of using passively collected nonintrusive smartphone data and machine learning--based data mining techniques to track an individuals' daily anxiety levels with a 76\% accuracy that directly relates to the GAD-7 scale. ",
doi="10.2196/38943",
url="https://medinform.jmir.org/2022/8/e38943",
url="http://www.ncbi.nlm.nih.gov/pubmed/36040777"
}


@Article{info:doi/10.2196/38495,
author="Chikersal, Prerna
and Venkatesh, Shruthi
and Masown, Karman
and Walker, Elizabeth
and Quraishi, Danyal
and Dey, Anind
and Goel, Mayank
and Xia, Zongqi",
title="Predicting Multiple Sclerosis Outcomes During the COVID-19 Stay-at-home Period: Observational Study Using Passively Sensed Behaviors and Digital Phenotyping",
journal="JMIR Ment Health",
year="2022",
month="Aug",
day="24",
volume="9",
number="8",
pages="e38495",
keywords="mobile sensing",
keywords="sensor",
keywords="sensing",
keywords="mobile health",
keywords="mHealth",
keywords="algorithm",
keywords="multiple sclerosis",
keywords="disability",
keywords="mental health",
keywords="depression",
keywords="sleep",
keywords="fatigue",
keywords="tiredness",
keywords="predict",
keywords="machine learning",
keywords="feature selection",
keywords="neurological disorder",
keywords="COVID-19",
keywords="isolation",
keywords="behavior change",
keywords="health outcome",
keywords="fitness",
keywords="movement",
keywords="physical activity",
keywords="exercise",
keywords="tracker",
keywords="digital phenotyping",
abstract="Background: The COVID-19 pandemic has broad negative impact on the physical and mental health of people with chronic neurological disorders such as multiple sclerosis (MS). Objective: We presented a machine learning approach leveraging passive sensor data from smartphones and fitness trackers of people with MS to predict their health outcomes in a natural experiment during a state-mandated stay-at-home period due to a global pandemic. Methods: First, we extracted features that capture behavior changes due to the stay-at-home order. Then, we adapted and applied an existing algorithm to these behavior-change features to predict the presence of depression, high global MS symptom burden, severe fatigue, and poor sleep quality during the stay-at-home period. Results: Using data collected between November 2019 and May 2020, the algorithm detected depression with an accuracy of 82.5\% (65\% improvement over baseline; F1-score: 0.84), high global MS symptom burden with an accuracy of 90\% (39\% improvement over baseline; F1-score: 0.93), severe fatigue with an accuracy of 75.5\% (22\% improvement over baseline; F1-score: 0.80), and poor sleep quality with an accuracy of 84\% (28\% improvement over baseline; F1-score: 0.84). Conclusions: Our approach could help clinicians better triage patients with MS and potentially other chronic neurological disorders for interventions and aid patient self-monitoring in their own environment, particularly during extraordinarily stressful circumstances such as pandemics, which would cause drastic behavior changes. ",
doi="10.2196/38495",
url="https://mental.jmir.org/2022/8/e38495",
url="http://www.ncbi.nlm.nih.gov/pubmed/35849686"
}


@Article{info:doi/10.2196/38934,
author="de Angel, Valeria
and Lewis, Serena
and White, M. Katie
and Matcham, Faith
and Hotopf, Matthew",
title="Clinical Targets and Attitudes Toward Implementing Digital Health Tools for Remote Measurement in Treatment for Depression: Focus Groups With Patients and Clinicians",
journal="JMIR Ment Health",
year="2022",
month="Aug",
day="15",
volume="9",
number="8",
pages="e38934",
keywords="depression",
keywords="digital health tools",
keywords="implementation",
keywords="qualitative",
keywords="wearable devices",
keywords="smartphone",
keywords="passive sensing",
keywords="sensor data",
keywords="mobile health",
keywords="mHealth",
keywords="mood disorders",
keywords="digital phenotyping",
keywords="mobile phone",
abstract="Background: Remote measurement technologies, such as smartphones and wearable devices, can improve treatment outcomes for depression through enhanced illness characterization and monitoring. However, little is known about digital outcomes that are clinically meaningful to patients and clinicians. Moreover, if these technologies are to be successfully implemented within treatment, stakeholders' views on the barriers to and facilitators of their implementation in treatment must be considered. Objective: This study aims to identify clinically meaningful targets for digital health research in depression and explore attitudes toward their implementation in psychological services. Methods: A grounded theory approach was used on qualitative data from 3 focus groups of patients with a current diagnosis of depression and clinicians with >6 months of experience with delivering psychotherapy (N=22). Results: Emerging themes on clinical targets fell into the following two main categories: promoters and markers of change. The former are behaviors that participants engage in to promote mental health, and the latter signal a change in mood. These themes were further subdivided into external changes (changes in behavior) or internal changes (changes in thoughts or feelings) and mapped with potential digital sensors. The following six implementation acceptability themes emerged: technology-related factors, information and data management, emotional support, cognitive support, increased self-awareness, and clinical utility. Conclusions: The promoters versus markers of change differentiation have implications for a causal model of digital phenotyping in depression, which this paper presents. Internal versus external subdivisions are helpful in determining which factors are more susceptible to being measured by using active versus passive methods. The implications for implementation within psychotherapy are discussed with regard to treatment effectiveness, service provision, and patient and clinician experience. ",
doi="10.2196/38934",
url="https://mental.jmir.org/2022/8/e38934",
url="http://www.ncbi.nlm.nih.gov/pubmed/35969448"
}


@Article{info:doi/10.2196/38570,
author="Helgerud, Jan
and Haglo, H{\aa}vard
and Hoff, Jan",
title="Prediction of VO2max From Submaximal Exercise Using the Smartphone Application Myworkout GO: Validation Study of a Digital Health Method",
journal="JMIR Cardio",
year="2022",
month="Aug",
day="4",
volume="6",
number="2",
pages="e38570",
keywords="high-intensity interval training",
keywords="cardiovascular health",
keywords="physical inactivity",
keywords="endurance training",
keywords="measurement accuracy",
abstract="Background: Physical inactivity remains the largest risk factor for the development of cardiovascular disease worldwide. Wearable devices have become a popular method of measuring activity-based outcomes and facilitating behavior change to increase cardiorespiratory fitness (CRF) or maximal oxygen consumption (VO2max) and reduce weight. However, it is critical to determine their accuracy in measuring these variables. Objective: This study aimed to determine the accuracy of using a smartphone and the application Myworkout GO for submaximal prediction of VO2max. Methods: Participants included 162 healthy volunteers: 58 women and 104 men (17-73 years old). The study consisted of 3 experimental tests randomized to 3 separate days. One-day VO2max was assessed with Metamax II, with the participant walking or running on the treadmill. On the 2 other days, the application Myworkout GO used standardized high aerobic intensity interval training (HIIT) on the treadmill to predict VO2max. Results: There were no significant differences between directly measured VO2max (mean 49, SD 14 mL/kg/min) compared with the VO2max predicted by Myworkout GO (mean 50, SD 14 mL/kg/min). The direct and predicted VO2max values were highly correlated, with an R2 of 0.97 (P<.001) and standard error of the estimate (SEE) of 2.2 mL/kg/min, with no sex differences. Conclusions: Myworkout GO accurately calculated VO2max, with an SEE of 4.5\% in the total group. The submaximal HIIT session (4 x 4 minutes) incorporated in the application was tolerated well by the participants. We present health care providers and their patients with a more accurate and practical version of health risk estimation. This might increase physical activity and improve exercise habits in the general population. ",
doi="10.2196/38570",
url="https://cardio.jmir.org/2022/2/e38570",
url="http://www.ncbi.nlm.nih.gov/pubmed/35925653"
}


@Article{info:doi/10.2196/34669,
author="Zhou, Weizhuang
and Chan, En Yu
and Foo, Sheng Chuan
and Zhang, Jingxian
and Teo, Xian Jing
and Davila, Sonia
and Huang, Weiting
and Yap, Jonathan
and Cook, Stuart
and Tan, Patrick
and Chin, Woon-Loong Calvin
and Yeo, Keong Khung
and Lim, Khong Weng
and Krishnaswamy, Pavitra",
title="High-Resolution Digital Phenotypes From Consumer Wearables and Their Applications in Machine Learning of Cardiometabolic Risk Markers: Cohort Study",
journal="J Med Internet Res",
year="2022",
month="Jul",
day="29",
volume="24",
number="7",
pages="e34669",
keywords="wearable device",
keywords="heart rate",
keywords="cardiometabolic disease",
keywords="risk prediction",
keywords="digital phenotypes",
keywords="polygenic risk scores",
keywords="time series analysis",
keywords="machine learning",
keywords="free-living",
abstract="Background: Consumer-grade wearable devices enable detailed recordings of heart rate and step counts in free-living conditions. Recent studies have shown that summary statistics from these wearable recordings have potential uses for longitudinal monitoring of health and disease states. However, the relationship between higher resolution physiological dynamics from wearables and known markers of health and disease remains largely uncharacterized. Objective: We aimed to derive high-resolution digital phenotypes from observational wearable recordings and to examine their associations with modifiable and inherent markers of cardiometabolic disease risk. Methods: We introduced a principled framework to extract interpretable high-resolution phenotypes from wearable data recorded in free-living conditions. The proposed framework standardizes the handling of data irregularities; encodes contextual information regarding the underlying physiological state at any given time; and generates a set of 66 minimally redundant features across active, sedentary, and sleep states. We applied our approach to a multimodal data set, from the SingHEART study (NCT02791152), which comprises heart rate and step count time series from wearables, clinical screening profiles, and whole genome sequences from 692 healthy volunteers. We used machine learning to model nonlinear relationships between the high-resolution phenotypes on the one hand and clinical or genomic risk markers for blood pressure, lipid, weight and sugar abnormalities on the other. For each risk type, we performed model comparisons based on Brier scores to assess the predictive value of high-resolution features over and beyond typical baselines. We also qualitatively characterized the wearable phenotypes for participants who had actualized clinical events. Results: We found that the high-resolution features have higher predictive value than typical baselines for clinical markers of cardiometabolic disease risk: the best models based on high-resolution features had 17.9\% and 7.36\% improvement in Brier score over baselines based on age and gender and resting heart rate, respectively (P<.001 in each case). Furthermore, heart rate dynamics from different activity states contain distinct information (maximum absolute correlation coefficient of 0.15). Heart rate dynamics in sedentary states are most predictive of lipid abnormalities and obesity, whereas patterns in active states are most predictive of blood pressure abnormalities (P<.001). Moreover, in comparison with standard measures, higher resolution patterns in wearable heart rate recordings are better able to represent subtle physiological dynamics related to genomic risk for cardiometabolic disease (improvement of 11.9\%-22.0\% in Brier scores; P<.001). Finally, illustrative case studies reveal connections between these high-resolution phenotypes and actualized clinical events, even for borderline profiles lacking apparent cardiometabolic risk markers. Conclusions: High-resolution digital phenotypes recorded by consumer wearables in free-living states have the potential to enhance the prediction of cardiometabolic disease risk and could enable more proactive and personalized health management. ",
doi="10.2196/34669",
url="https://www.jmir.org/2022/7/e34669",
url="http://www.ncbi.nlm.nih.gov/pubmed/35904853"
}


@Article{info:doi/10.2196/39618,
author="Dlima, Dayna Schenelle
and Shevade, Santosh
and Menezes, Rebecca Sonia
and Ganju, Aakash",
title="Digital Phenotyping in Health Using Machine Learning Approaches: Scoping Review",
journal="JMIR Bioinform Biotech",
year="2022",
month="Jul",
day="18",
volume="3",
number="1",
pages="e39618",
keywords="digital phenotyping",
keywords="machine learning",
keywords="personal device data",
keywords="passive data",
keywords="active data",
keywords="wearable device",
keywords="wearable sensor",
keywords="mobile application",
keywords="digital health",
abstract="Background: Digital phenotyping is the real-time collection of individual-level active and passive data from users in naturalistic and free-living settings via personal digital devices, such as mobile phones and wearable devices. Given the novelty of research in this field, there is heterogeneity in the clinical use cases, types of data collected, modes of data collection, data analysis methods, and outcomes measured. Objective: The primary aim of this scoping review was to map the published research on digital phenotyping and to outline study characteristics, data collection and analysis methods, machine learning approaches, and future implications. Methods: We utilized an a priori approach for the literature search and data extraction and charting process, guided by the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-analyses Extension for Scoping Reviews). We identified relevant studies published in 2020, 2021, and 2022 on PubMed and Google Scholar using search terms related to digital phenotyping. The titles, abstracts, and keywords were screened during the first stage of the screening process, and the second stage involved screening the full texts of the shortlisted articles. We extracted and charted the descriptive characteristics of the final studies, which were countries of origin, study design, clinical areas, active and/or passive data collected, modes of data collection, data analysis approaches, and limitations. Results: A total of 454 articles on PubMed and Google Scholar were identified through search terms associated with digital phenotyping, and 46 articles were deemed eligible for inclusion in this scoping review. Most studies evaluated wearable data and originated from North America. The most dominant study design was observational, followed by randomized trials, and most studies focused on psychiatric disorders, mental health disorders, and neurological diseases. A total of 7 studies used machine learning approaches for data analysis, with random forest, logistic regression, and support vector machines being the most common. Conclusions: Our review provides foundational as well as application-oriented approaches toward digital phenotyping in health. Future work should focus on more prospective, longitudinal studies that include larger data sets from diverse populations, address privacy and ethical concerns around data collection from consumer technologies, and build ``digital phenotypes'' to personalize digital health interventions and treatment plans. ",
doi="10.2196/39618",
url="https://bioinform.jmir.org/2022/1/e39618"
}


@Article{info:doi/10.2196/38294,
author="Kilshaw, E. Robyn
and Adamo, Colin
and Butner, E. Jonathan
and Deboeck, R. Pascal
and Shi, Qinxin
and Bulik, M. Cynthia
and Flatt, E. Rachael
and Thornton, M. Laura
and Argue, Stuart
and Tregarthen, Jenna
and Baucom, W. Brian R.",
title="Passive Sensor Data for Characterizing States of Increased Risk for Eating Disorder Behaviors in the Digital Phenotyping Arm of the Binge Eating Genetics Initiative: Protocol for an Observational Study",
journal="JMIR Res Protoc",
year="2022",
month="Jun",
day="2",
volume="11",
number="6",
pages="e38294",
keywords="digital phenotyping",
keywords="eating disorders",
keywords="personal digital devices",
keywords="methodology",
abstract="Background: Data that can be easily, efficiently, and safely collected via cell phones and other digital devices have great potential for clinical application. Here, we focus on how these data could be used to refine and augment intervention strategies for binge eating disorder (BED) and bulimia nervosa (BN), conditions that lack highly efficacious, enduring, and accessible treatments. These data are easy to collect digitally but are highly complex and present unique methodological challenges that invite innovative solutions. Objective: We describe the digital phenotyping component of the Binge Eating Genetics Initiative, which uses personal digital device data to capture dynamic patterns of risk for binge and purge episodes. Characteristic data signatures will ultimately be used to develop personalized models of eating disorder pathologies and just-in-time interventions to reduce risk for related behaviors. Here, we focus on the methods used to prepare the data for analysis and discuss how these approaches can be generalized beyond the current application. Methods: The University of North Carolina Biomedical Institutional Review Board approved all study procedures. Participants who met diagnostic criteria for BED or BN provided real time assessments of eating behaviors and feelings through the Recovery Record app delivered on iPhones and the Apple Watches. Continuous passive measures of physiological activation (heart rate) and physical activity (step count) were collected from Apple Watches over 30 days. Data were cleaned to account for user and device recording errors, including duplicate entries and unreliable heart rate and step values. Across participants, the proportion of data points removed during cleaning ranged from <0.1\% to 2.4\%, depending on the data source. To prepare the data for multivariate time series analysis, we used a novel data handling approach to address variable measurement frequency across data sources and devices. This involved mapping heart rate, step count, feeling ratings, and eating disorder behaviors onto simultaneous minute-level time series that will enable the characterization of individual- and group-level regulatory dynamics preceding and following binge and purge episodes. Results: Data collection and cleaning are complete. Between August 2017 and May 2021, 1019 participants provided an average of 25 days of data yielding 3,419,937 heart rate values, 1,635,993 step counts, 8274 binge or purge events, and 85,200 feeling observations. Analysis will begin in spring 2022. Conclusions: We provide a detailed description of the methods used to collect, clean, and prepare personal digital device data from one component of a large, longitudinal eating disorder study. The results will identify digital signatures of increased risk for binge and purge events, which may ultimately be used to create digital interventions for BED and BN. Our goal is to contribute to increased transparency in the handling and analysis of personal digital device data. Trial Registration: ClinicalTrials.gov NCT04162574; https://clinicaltrials.gov/ct2/show/NCT04162574 International Registered Report Identifier (IRRID): DERR1-10.2196/38294 ",
doi="10.2196/38294",
url="https://www.researchprotocols.org/2022/6/e38294",
url="http://www.ncbi.nlm.nih.gov/pubmed/35653175"
}


@Article{info:doi/10.2196/35696,
author="Husted, Skov Karina Louise
and Brink-Kj{\ae}r, Andreas
and Fogelstr{\o}m, Mathilde
and Hulst, Pernille
and Bleibach, Akita
and Henneberg, Kaj-{\AA}ge
and S{\o}rensen, Dissing Helge Bjarup
and Dela, Flemming
and Jacobsen, Brings Jens Christian
and Helge, Wulff J{\o}rn",
title="A Model for Estimating Biological Age From Physiological Biomarkers of Healthy Aging: Cross-sectional Study",
journal="JMIR Aging",
year="2022",
month="May",
day="10",
volume="5",
number="2",
pages="e35696",
keywords="biological age",
keywords="model development",
keywords="principal component analysis",
keywords="healthy aging",
keywords="biomarkers",
keywords="aging",
abstract="Background: Individual differences in the rate of aging and susceptibility to disease are not accounted for by chronological age alone. These individual differences are better explained by biological age, which may be estimated by biomarker prediction models. In the light of the aging demographics of the global population and the increase in lifestyle-related morbidities, it is interesting to invent a new biological age model to be used for health promotion. Objective: This study aims to develop a model that estimates biological age based on physiological biomarkers of healthy aging. Methods: Carefully selected physiological variables from a healthy study population of 100 women and men were used as biomarkers to establish an estimate of biological age. Principal component analysis was applied to the biomarkers and the first principal component was used to define the algorithm estimating biological age. Results: The first principal component accounted for 31\% in women and 25\% in men of the total variance in the biological age model combining mean arterial pressure, glycated hemoglobin, waist circumference, forced expiratory volume in 1 second, maximal oxygen consumption, adiponectin, high-density lipoprotein, total cholesterol, and soluble urokinase-type plasminogen activator receptor. The correlation between the corrected biological age and chronological age was r=0.86 (P<.001) and r=0.81 (P<.001) for women and men, respectively, and the agreement was high and unbiased. No difference was found between mean chronological age and mean biological age, and the slope of the regression line was near 1 for both sexes. Conclusions: Estimating biological age from these 9 biomarkers of aging can be used to assess general health compared with the healthy aging trajectory. This may be useful to evaluate health interventions and as an aid to enhance awareness of individual health risks and behavior when deviating from this trajectory. Trial Registration: ClinicalTrials.gov NCT03680768; https://clinicaltrials.gov/ct2/show/NCT03680768 International Registered Report Identifier (IRRID): RR2-10.2196/19209 ",
doi="10.2196/35696",
url="https://aging.jmir.org/2022/2/e35696",
url="http://www.ncbi.nlm.nih.gov/pubmed/35536617"
}


@Article{info:doi/10.2196/35549,
author="Braund, A. Taylor
and Zin, The May
and Boonstra, W. Tjeerd
and Wong, J. Quincy J.
and Larsen, E. Mark
and Christensen, Helen
and Tillman, Gabriel
and O'Dea, Bridianne",
title="Smartphone Sensor Data for Identifying and Monitoring Symptoms of Mood Disorders: A Longitudinal Observational Study",
journal="JMIR Ment Health",
year="2022",
month="May",
day="4",
volume="9",
number="5",
pages="e35549",
keywords="depression",
keywords="bipolar disorder",
keywords="sensors",
keywords="mobile app",
keywords="circadian rhythm",
keywords="mobile phone",
abstract="Background: Mood disorders are burdensome illnesses that often go undetected and untreated. Sensor technologies within smartphones may provide an opportunity for identifying the early changes in circadian rhythm and social support/connectedness that signify the onset of a depressive or manic episode. Objective: Using smartphone sensor data, this study investigated the relationship between circadian rhythm, which was determined by GPS data, and symptoms of mental health among a clinical sample of adults diagnosed with major depressive disorder or bipolar disorder. Methods: A total of 121 participants were recruited from a clinical setting to take part in a 10-week observational study. Self-report questionnaires for mental health outcomes, social support, social connectedness, and quality of life were assessed at 6 time points throughout the study period. Participants consented to passively sharing their smartphone GPS data for the duration of the study. Circadian rhythm (ie, regularity of location changes in a 24-hour rhythm) was extracted from GPS mobility patterns at baseline. Results: Although we found no association between circadian rhythm and mental health functioning at baseline, there was a positive association between circadian rhythm and the size of participants' social support networks at baseline (r=0.22; P=.03; R2=0.049). In participants with bipolar disorder, circadian rhythm was associated with a change in anxiety from baseline; a higher circadian rhythm was associated with an increase in anxiety and a lower circadian rhythm was associated with a decrease in anxiety at time point 5. Conclusions: Circadian rhythm, which was extracted from smartphone GPS data, was associated with social support and predicted changes in anxiety in a clinical sample of adults with mood disorders. Larger studies are required for further validations. However, smartphone sensing may have the potential to monitor early symptoms of mood disorders. ",
doi="10.2196/35549",
url="https://mental.jmir.org/2022/5/e35549",
url="http://www.ncbi.nlm.nih.gov/pubmed/35507385"
}


@Article{info:doi/10.2196/30517,
author="Ribeiro, Ricardo
and Trifan, Alina
and Neves, R. Ant{\'o}nio J.",
title="Lifelog Retrieval From Daily Digital Data: Narrative Review",
journal="JMIR Mhealth Uhealth",
year="2022",
month="May",
day="2",
volume="10",
number="5",
pages="e30517",
keywords="lifelog",
keywords="lifelogging",
keywords="information retrieval",
keywords="image retrieval",
keywords="computer vision",
keywords="signal processing",
keywords="event segmentation",
keywords="mobile phone",
abstract="Background: Over the past decade, the wide availability and small size of different types of sensors, together with the decrease in pricing, have allowed the acquisition of a substantial amount of data about a person's life in real time. These sensors can be incorporated into personal electronic devices available at a reasonable cost, such as smartphones and small wearable devices. They allow the acquisition of images, audio, location, physical activity, and physiological signals among other data. With these data, usually denoted as lifelog data, we can then analyze and understand personal experiences and behaviors. This process is called lifelogging. Objective: The objective of this paper was to present a narrative review of the existing literature about lifelogging over the past decade. To achieve this goal, we analyzed lifelogging applications used to retrieve relevant information from daily digital data, some of them with the purpose of monitoring and assisting people with memory issues and others designed for memory augmentation. We aimed for this review to be used by researchers to obtain a broad idea of the type of data used, methodologies, and applications available in this research field. Methods: We followed a narrative review methodology to conduct a comprehensive search for relevant publications in Google Scholar and Scopus databases using lifelog topic--related keywords. A total of 411 publications were retrieved and screened. Of these 411 publications, 114 (27.7\%) publications were fully reviewed. In addition, 30 publications were manually included based on our bibliographical knowledge of this research field. Results: From the 144 reviewed publications, a total of 113 (78.5\%) were selected and included in this narrative review based on content analysis. The findings of this narrative review suggest that lifelogs are prone to become powerful tools to retrieve memories or increase knowledge about an individual's experiences or behaviors. Several computational tools are already available for a considerable range of applications. These tools use multimodal data of different natures, with visual lifelogs being one of the most used and rich sources of information. Different approaches and algorithms to process these data are currently in use, as this review will unravel. Moreover, we identified several open questions and possible lines of investigation in lifelogging. Conclusions: The use of personal lifelogs can be beneficial to improve the quality of our life, as they can serve as tools for memory augmentation or for providing support to people with memory issues. Through the acquisition and analysis of lifelog data, lifelogging systems can create digital memories that can be potentially used as surrogate memory. Through this narrative review, we understand that contextual information can be extracted from lifelogs, which provides an understanding of the daily life of a person based on events, experiences, and behaviors. ",
doi="10.2196/30517",
url="https://mhealth.jmir.org/2022/5/e30517",
url="http://www.ncbi.nlm.nih.gov/pubmed/35499858"
}


@Article{info:doi/10.2196/25249,
author="Polhemus, Ashley
and Novak, Jan
and Majid, Shazmin
and Simblett, Sara
and Morris, Daniel
and Bruce, Stuart
and Burke, Patrick
and Dockendorf, F. Marissa
and Temesi, Gergely
and Wykes, Til",
title="Data Visualization for Chronic Neurological and Mental Health Condition Self-management: Systematic Review of User Perspectives",
journal="JMIR Ment Health",
year="2022",
month="Apr",
day="28",
volume="9",
number="4",
pages="e25249",
keywords="digital health",
keywords="remote measurement technology",
keywords="neurology",
keywords="mental health",
keywords="data visualization",
keywords="user-centered design",
abstract="Background: Remote measurement technologies (RMT) such as mobile health devices and apps are increasingly used by those living with chronic neurological and mental health conditions. RMT enables real-world data collection and regular feedback, providing users with insights about their own conditions. Data visualizations are an integral part of RMT, although little is known about visualization design preferences from the perspectives of those living with chronic conditions. Objective: The aim of this review was to explore the experiences and preferences of individuals with chronic neurological and mental health conditions on data visualizations derived from RMT to manage health. Methods: In this systematic review, we searched peer-reviewed literature and conference proceedings (PubMed, IEEE Xplore, EMBASE, Web of Science, Association for Computing Machinery Computer-Human Interface proceedings, and the Cochrane Library) for original papers published between January 2007 and September 2021 that reported perspectives on data visualization of people living with chronic neurological and mental health conditions. Two reviewers independently screened each abstract and full-text article, with disagreements resolved through discussion. Studies were critically appraised, and extracted data underwent thematic synthesis. Results: We identified 35 eligible publications from 31 studies representing 12 conditions. Coded data coalesced into 3 themes: desire for data visualization, impact of visualizations on condition management, and visualization design considerations. Data visualizations were viewed as an integral part of users' experiences with RMT, impacting satisfaction and engagement. However, user preferences were diverse and often conflicting both between and within conditions. Conclusions: When used effectively, data visualizations are valuable, engaging components of RMT. They can provide structure and insight, allowing individuals to manage their own health more effectively. However, visualizations are not ``one-size-fits-all,'' and it is important to engage with potential users during visualization design to understand when, how, and with whom the visualizations will be used to manage health. ",
doi="10.2196/25249",
url="https://mental.jmir.org/2022/4/e25249",
url="http://www.ncbi.nlm.nih.gov/pubmed/35482368"
}


@Article{info:doi/10.2196/34105,
author="Newson, Jane Jennifer
and Pastukh, Vladyslav
and Thiagarajan, C. Tara",
title="Assessment of Population Well-being With the Mental Health Quotient: Validation Study",
journal="JMIR Ment Health",
year="2022",
month="Apr",
day="20",
volume="9",
number="4",
pages="e34105",
keywords="psychiatry",
keywords="public health",
keywords="methods",
keywords="mental health",
keywords="population health",
keywords="social determinants of health",
keywords="global health",
keywords="behavioral symptoms",
keywords="diagnosis",
keywords="symptom assessment",
keywords="psychopathology",
keywords="mental disorders",
keywords="mHealth",
keywords="depression",
keywords="anxiety",
keywords="attention deficit disorder with hyperactivity",
keywords="autistic disorder",
keywords="internet",
abstract="Background: The Mental Health Quotient (MHQ) is an anonymous web-based assessment of mental health and well-being that comprehensively covers symptoms across 10 major psychiatric disorders, as well as positive elements of mental function. It uses a novel life impact scale and provides a score to the individual that places them on a spectrum from Distressed to Thriving along with a personal report that offers self-care recommendations. Since April 2020, the MHQ has been freely deployed as part of the Mental Health Million Project. Objective: This paper demonstrates the reliability and validity of the MHQ, including the construct validity of the life impact scale, sample and test-retest reliability of the assessment, and criterion validation of the MHQ with respect to clinical burden and productivity loss. Methods: Data were taken from the Mental Health Million open-access database (N=179,238) and included responses from English-speaking adults (aged?18 years) from the United States, Canada, the United Kingdom, Ireland, Australia, New Zealand, South Africa, Singapore, India, and Nigeria collected during 2021. To assess sample reliability, random demographically matched samples (each 11,033/179,238, 6.16\%) were compared within the same 6-month period. Test-retest reliability was determined using the subset of individuals who had taken the assessment twice ?3 days apart (1907/179,238, 1.06\%). To assess the construct validity of the life impact scale, additional questions were asked about the frequency and severity of an example symptom (feelings of sadness, distress, or hopelessness; 4247/179,238, 2.37\%). To assess criterion validity, elements rated as having a highly negative life impact by a respondent (equivalent to experiencing the symptom ?5 days a week) were mapped to clinical diagnostic criteria to calculate the clinical burden (174,618/179,238, 97.42\%). In addition, MHQ scores were compared with the number of workdays missed or with reduced productivity in the past month (7625/179,238, 4.25\%). Results: Distinct samples collected during the same period had indistinguishable MHQ distributions and MHQ scores were correlated with r=0.84 between retakes within an 8- to 120-day period. Life impact ratings were correlated with frequency and severity of symptoms, with a clear linear relationship (R2>0.99). Furthermore, the aggregate MHQ scores were systematically related to both clinical burden and productivity. At one end of the scale, 89.08\% (8986/10,087) of those in the Distressed category mapped to one or more disorders and had an average productivity loss of 15.2 (SD 11.2; SEM [standard error of measurement] 0.5) days per month. In contrast, at the other end of the scale, 0\% (1/24,365) of those in the Thriving category mapped to any of the 10 disorders and had an average productivity loss of 1.3 (SD 3.6; SEM 0.1) days per month. Conclusions: The MHQ is a valid and reliable assessment of mental health and well-being when delivered anonymously on the web. ",
doi="10.2196/34105",
url="https://mental.jmir.org/2022/4/e34105",
url="http://www.ncbi.nlm.nih.gov/pubmed/35442210"
}


@Article{info:doi/10.2196/34548,
author="Hu, Jiming
and Xing, Kai
and Zhang, Yan
and Liu, Miao
and Wang, Zhiwei",
title="Global Research Trends in Tyrosine Kinase Inhibitors: Coword and Visualization Study",
journal="JMIR Med Inform",
year="2022",
month="Apr",
day="8",
volume="10",
number="4",
pages="e34548",
keywords="TKIs",
keywords="coword analysis",
keywords="literature visualization",
keywords="NSCLC",
keywords="targeted therapy",
keywords="CML",
keywords="topics distribution",
keywords="HER2",
keywords="pharmacokinetics",
abstract="Background: Tyrosine kinase inhibitors (TKIs) have achieved revolutionary results in the treatment of a wide range of tumors, and many studies on this topic continue to be published every year. Some of the published reviews provide great value for us to understand TKIs. However, there is a lack of studies on the knowledge structure, bibliometric analysis, and visualization results in TKIs research. Objective: This paper aims to investigate the knowledge structure, hotspots, and trends of evolution of the TKIs research by co-word analysis and literature visualization and help researchers in this field to gain a comprehensive understanding of the current status and trends. Methods: We retrieved all academic papers about TKIs published between 2016 and 2020 from the Web of Science. By counting keywords from those papers, we generated the co-word networks by extracting the co-occurrence relationships between keywords, and then segmented communities to identify the subdirections of TKIs research by calculating the network metrics of the overall and local networks. We also mapped the association network topology, including the network within and between TKIs subdirections, to reveal the association and structure among varied subdirections. Furthermore, we detected keyword bursts by combining their burst weights and durations to reveal changes in the focus of TKIs research. Finally, evolution venation and strategic diagram were generated to reveal the trends of TKIs research. Results: We obtained 6782 unique words (total frequency 26,175) from 5584 paper titles. Finally, 296 high-frequency words were selected with a threshold of 10 after discussion, the total frequency of which accounted for 65.41\% (17,120/26,175). The analysis of burst disciplines revealed a variable number of burst words of TKIs research every year, especially in 2019 and 2020, such as HER2, pyrotinib, next-generation sequencing, immunotherapy, ALK-TKI, ALK rearrangement. By network calculation, the TKIs co-word network was divided into 6 communities: C1 (non-small--cell lung cancer), C2 (targeted therapy), C3 (chronic myeloid leukemia), C4 (HER2), C5 (pharmacokinetics), and C6 (ALK). The venation diagram revealed several clear and continuous evolution trends, such as non-small--cell lung cancer venation, chronic myeloid leukemia venation, renal cell carcinoma venation, chronic lymphocytic leukemia venation. In the strategic diagram, C1 (non-small--cell lung cancer) was the core direction located in the first quadrant, C2 (targeted therapy) was exactly at the junction of the first and fourth quadrants, which meant that C2 was developing; and C3 (chronic myeloid leukemia), C4 (HER2), and C5 (pharmacokinetics) were all immature and located in the third quadrant. Conclusions: Using co-word analysis and literature visualization, we revealed the hotspots, knowledge structure, and trends of evolution of TKIs research between 2016 and 2020. TKIs research mainly focused on targeted therapies against varied tumors, particularly against non-small--cell lung cancer. The attention on chronic myeloid leukemia and pharmacokinetics was gradually decreasing, but the focus on HER2 and ALK was rapidly increasing. TKIs research had shown a clear development path: TKIs research was disease focused and revolved around ``gene targets/targeted drugs/resistance mechanisms.'' Our outcomes will provide sound and effective support to researchers, funders, policymakers, and clinicians. ",
doi="10.2196/34548",
url="https://medinform.jmir.org/2022/4/e34548",
url="http://www.ncbi.nlm.nih.gov/pubmed/35072634"
}


@Article{info:doi/10.2196/25643,
author="Niemeijer, Koen
and Mestdagh, Merijn
and Kuppens, Peter",
title="Tracking Subjective Sleep Quality and Mood With Mobile Sensing: Multiverse Study",
journal="J Med Internet Res",
year="2022",
month="Mar",
day="18",
volume="24",
number="3",
pages="e25643",
keywords="mobile sensing",
keywords="sleep",
keywords="subjective sleep quality",
keywords="negative affect",
keywords="depression",
keywords="multiverse",
keywords="multilevel modeling",
keywords="machine learning",
keywords="mood",
keywords="mood disorder",
keywords="mobile sensors",
keywords="sleep quality",
keywords="clinical applications",
abstract="Background: Sleep influences moods and mood disorders. Existing methods for tracking the quality of people's sleep are laborious and obtrusive. If a method were available that would allow effortless and unobtrusive tracking of sleep quality, it would mark a significant step toward obtaining sleep data for research and clinical applications. Objective: Our goal was to evaluate the potential of mobile sensing data to obtain information about a person's sleep quality. For this purpose, we investigated to what extent various automatically gathered mobile sensing features are capable of predicting (1) subjective sleep quality (SSQ), (2) negative affect (NA), and (3) depression; these variables are associated with objective sleep quality. Through a multiverse analysis, we examined how the predictive quality varied as a function of the selected sensor, the extracted feature, various preprocessing options, and the statistical prediction model. Methods: We used data from a 2-week trial where we collected mobile sensing and experience sampling data from an initial sample of 60 participants. After data cleaning and removing participants with poor compliance, we retained 50 participants. Mobile sensing data involved the accelerometer, charging status, light sensor, physical activity, screen activity, and Wi-Fi status. Instructions were given to participants to keep their smartphone charged and connected to Wi-Fi at night. We constructed 1 model for every combination of multiverse parameters to evaluate their effects on each of the outcome variables. We evaluated the statistical models by applying them to training, validation, and test sets to prevent overfitting. Results: Most models (on either of the outcome variables) were not informative on the validation set (ie, predicted R2?0). However, our best models achieved R2 values of 0.658, 0.779, and 0.074 for SSQ, NA, and depression, respectively on the training set and R2 values of 0.348, 0.103, and 0.025, respectively on the test set. Conclusions: The approach demonstrated in this paper has shown that different choices (eg, preprocessing choices, various statistical models, different features) lead to vastly different results that are bad and relatively good as well. Nevertheless, there were some promising results, particularly for SSQ, which warrant further research on this topic. ",
doi="10.2196/25643",
url="https://www.jmir.org/2022/3/e25643",
url="http://www.ncbi.nlm.nih.gov/pubmed/35302502"
}


@Article{info:doi/10.2196/31021,
author="Almowil, Zahra
and Zhou, Shang-Ming
and Brophy, Sinead
and Croxall, Jodie",
title="Concept Libraries for Repeatable and Reusable Research: Qualitative Study Exploring the Needs of Users",
journal="JMIR Hum Factors",
year="2022",
month="Mar",
day="15",
volume="9",
number="1",
pages="e31021",
keywords="electronic health records",
keywords="record linkage",
keywords="reproducible research",
keywords="clinical codes",
keywords="concept libraries",
abstract="Background: Big data research in the field of health sciences is hindered by a lack of agreement on how to identify and define different conditions and their medications. This means that researchers and health professionals often have different phenotype definitions for the same condition. This lack of agreement makes it difficult to compare different study findings and hinders the ability to conduct repeatable and reusable research. Objective: This study aims to examine the requirements of various users, such as researchers, clinicians, machine learning experts, and managers, in the development of a data portal for phenotypes (a concept library). Methods: This was a qualitative study using interviews and focus group discussion. One-to-one interviews were conducted with researchers, clinicians, machine learning experts, and senior research managers in health data science (N=6) to explore their specific needs in the development of a concept library. In addition, a focus group discussion with researchers (N=14) working with the Secured Anonymized Information Linkage databank, a national eHealth data linkage infrastructure, was held to perform a SWOT (strengths, weaknesses, opportunities, and threats) analysis for the phenotyping system and the proposed concept library. The interviews and focus group discussion were transcribed verbatim, and 2 thematic analyses were performed. Results: Most of the participants thought that the prototype concept library would be a very helpful resource for conducting repeatable research, but they specified that many requirements are needed before its development. Although all the participants stated that they were aware of some existing concept libraries, most of them expressed negative perceptions about them. The participants mentioned several facilitators that would stimulate them to share their work and reuse the work of others, and they pointed out several barriers that could inhibit them from sharing their work and reusing the work of others. The participants suggested some developments that they would like to see to improve reproducible research output using routine data. Conclusions: The study indicated that most interviewees valued a concept library for phenotypes. However, only half of the participants felt that they would contribute by providing definitions for the concept library, and they reported many barriers regarding sharing their work on a publicly accessible platform. Analysis of interviews and the focus group discussion revealed that different stakeholders have different requirements, facilitators, barriers, and concerns about a prototype concept library. ",
doi="10.2196/31021",
url="https://humanfactors.jmir.org/2022/1/e31021",
url="http://www.ncbi.nlm.nih.gov/pubmed/35289755"
}


@Article{info:doi/10.2196/28735,
author="Mendes, M. Jean P.
and Moura, R. Ivan
and Van de Ven, Pepijn
and Viana, Davi
and Silva, S. Francisco J.
and Coutinho, R. Luciano
and Teixeira, Silmar
and Rodrigues, C. Joel J. P.
and Teles, Soares Ariel",
title="Sensing Apps and Public Data Sets for Digital Phenotyping of Mental Health: Systematic Review",
journal="J Med Internet Res",
year="2022",
month="Feb",
day="17",
volume="24",
number="2",
pages="e28735",
keywords="mental health",
keywords="digital phenotyping",
keywords="sensing apps",
keywords="data sets",
keywords="sensor data",
abstract="Background: Mental disorders are normally diagnosed exclusively on the basis of symptoms, which are identified from patients' interviews and self-reported experiences. To make mental health diagnoses and monitoring more objective, different solutions have been proposed such as digital phenotyping of mental health (DPMH), which can expand the ability to identify and monitor health conditions based on the interactions of people with digital technologies. Objective: This article aims to identify and characterize the sensing applications and public data sets for DPMH from a technical perspective. Methods: We performed a systematic review of scientific literature and data sets. We searched 8 digital libraries and 20 data set repositories to find results that met the selection criteria. We conducted a data extraction process from the selected articles and data sets. For this purpose, a form was designed to extract relevant information, thus enabling us to answer the research questions and identify open issues and research trends. Results: A total of 31 sensing apps and 8 data sets were identified and reviewed. Sensing apps explore different context data sources (eg, positioning, inertial, ambient) to support DPMH studies. These apps are designed to analyze and process collected data to classify (n=11) and predict (n=6) mental states/disorders, and also to investigate existing correlations between context data and mental states/disorders (n=6). Moreover, general-purpose sensing apps are developed to focus only on contextual data collection (n=9). The reviewed data sets contain context data that model different aspects of human behavior, such as sociability, mood, physical activity, sleep, with some also being multimodal. Conclusions: This systematic review provides in-depth analysis regarding solutions for DPMH. Results show growth in proposals for DPMH sensing apps in recent years, as opposed to a scarcity of public data sets. The review shows that there are features that can be measured on smart devices that can act as proxies for mental status and well-being; however, it should be noted that the combined evidence for high-quality features for mental states remains limited. DPMH presents a great perspective for future research, mainly to reach the needed maturity for applications in clinical settings. ",
doi="10.2196/28735",
url="https://www.jmir.org/2022/2/e28735",
url="http://www.ncbi.nlm.nih.gov/pubmed/35175202"
}


@Article{info:doi/10.2196/30524,
author="Kilgallon, L. John
and Tewarie, Ashwini Ishaan
and Broekman, D. Marike L.
and Rana, Aakanksha
and Smith, R. Timothy",
title="Passive Data Use for Ethical Digital Public Health Surveillance in a Postpandemic World",
journal="J Med Internet Res",
year="2022",
month="Feb",
day="15",
volume="24",
number="2",
pages="e30524",
keywords="passive data",
keywords="public health surveillance",
keywords="digital public health surveillance",
keywords="pandemic response",
keywords="data privacy",
keywords="digital phenotyping",
keywords="smartphone",
keywords="mobile phone",
keywords="mHealth",
keywords="digital health",
keywords="informed consent",
keywords="data equity",
keywords="data ownership",
doi="10.2196/30524",
url="https://www.jmir.org/2022/2/e30524",
url="http://www.ncbi.nlm.nih.gov/pubmed/35166676"
}


@Article{info:doi/10.2196/31146,
author="Shen, X. Francis
and Silverman, C. Benjamin
and Monette, Patrick
and Kimble, Sara
and Rauch, L. Scott
and Baker, T. Justin",
title="An Ethics Checklist for Digital Health Research in Psychiatry: Viewpoint",
journal="J Med Internet Res",
year="2022",
month="Feb",
day="9",
volume="24",
number="2",
pages="e31146",
keywords="digital phenotyping",
keywords="computataional psychiatry",
keywords="ethics",
keywords="law",
keywords="privacy",
keywords="informed consent",
abstract="Background: Psychiatry has long needed a better and more scalable way to capture the dynamics of behavior and its disturbances, quantitatively across multiple data channels, at high temporal resolution in real time. By combining 24/7 data---on location, movement, email and text communications, and social media---with brain scans, genetics, genomics, neuropsychological batteries, and clinical interviews, researchers will have an unprecedented amount of objective, individual-level data. Analyzing these data with ever-evolving artificial intelligence could one day include bringing interventions to patients where they are in the real world in a convenient, efficient, effective, and timely way. Yet, the road to this innovative future is fraught with ethical dilemmas as well as ethical, legal, and social implications (ELSI). Objective: The goal of the Ethics Checklist is to promote careful design and execution of research. It is not meant to mandate particular research designs; indeed, at this early stage and without consensus guidance, there are a range of reasonable choices researchers may make. However, the checklist is meant to make those ethical choices explicit, and to require researchers to give reasons for their decisions related to ELSI issues. The Ethics Checklist is primarily focused on procedural safeguards, such as consulting with experts outside the research group and documenting standard operating procedures for clearly actionable data (eg, expressed suicidality) within written research protocols. Methods: We explored the ELSI of digital health research in psychiatry, with a particular focus on what we label ``deep phenotyping'' psychiatric research, which combines the potential for virtually boundless data collection and increasingly sophisticated techniques to analyze those data. We convened an interdisciplinary expert stakeholder workshop in May 2020, and this checklist emerges out of that dialogue. Results: Consistent with recent ELSI analyses, we find that existing ethical guidance and legal regulations are not sufficient for deep phenotyping research in psychiatry. At present, there are regulatory gaps, inconsistencies across research teams in ethics protocols, and a lack of consensus among institutional review boards on when and how deep phenotyping research should proceed. We thus developed a new instrument, an Ethics Checklist for Digital Health Research in Psychiatry (``the Ethics Checklist''). The Ethics Checklist is composed of 20 key questions, subdivided into 6 interrelated domains: (1) informed consent; (2) equity, diversity, and access; (3) privacy and partnerships; (4) regulation and law; (5) return of results; and (6) duty to warn and duty to report. Conclusions: Deep phenotyping research offers a vision for vastly more effective care for people with, or at risk for, psychiatric disease. The potential perils en route to realizing this vision are significant; however, and researchers must be willing to address the questions in the Ethics Checklist before embarking on each leg of the journey. ",
doi="10.2196/31146",
url="https://www.jmir.org/2022/2/e31146",
url="http://www.ncbi.nlm.nih.gov/pubmed/35138261"
}


@Article{info:doi/10.2196/30557,
author="Vaidyam, Aditya
and Halamka, John
and Torous, John",
title="Enabling Research and Clinical Use of Patient-Generated Health Data (the mindLAMP Platform): Digital Phenotyping Study",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Jan",
day="7",
volume="10",
number="1",
pages="e30557",
keywords="digital phenotyping",
keywords="mHealth",
keywords="apps",
keywords="FHIR",
keywords="digital health",
keywords="health data",
keywords="patient-generated health data",
keywords="mobile health",
keywords="smartphones",
keywords="wearables",
keywords="mobile apps",
keywords="mental health, mobile phone",
abstract="Background: There is a growing need for the integration of patient-generated health data (PGHD) into research and clinical care to enable personalized, preventive, and interactive care, but technical and organizational challenges, such as the lack of standards and easy-to-use tools, preclude the effective use of PGHD generated from consumer devices, such as smartphones and wearables. Objective: This study outlines how we used mobile apps and semantic web standards such as HTTP 2.0, Representational State Transfer, JSON (JavaScript Object Notation), JSON Schema, Transport Layer Security (version 1.3), Advanced Encryption Standard-256, OpenAPI, HTML5, and Vega, in conjunction with patient and provider feedback to completely update a previous version of mindLAMP. Methods: The Learn, Assess, Manage, and Prevent (LAMP) platform addresses the abovementioned challenges in enhancing clinical insight by supporting research, data analysis, and implementation efforts around PGHD as an open-source solution with freely accessible and shared code. Results: With a simplified programming interface and novel data representation that captures additional metadata, the LAMP platform enables interoperability with existing Fast Healthcare Interoperability Resources--based health care systems as well as consumer wearables and services such as Apple HealthKit and Google Fit. The companion Cortex data analysis and machine learning toolkit offer robust support for artificial intelligence, behavioral feature extraction, interactive visualizations, and high-performance data processing through parallelization and vectorization techniques. Conclusions: The LAMP platform incorporates feedback from patients and clinicians alongside a standards-based approach to address these needs and functions across a wide range of use cases through its customizable and flexible components. These range from simple survey-based research to international consortiums capturing multimodal data to simple delivery of mindfulness exercises through personalized, just-in-time adaptive interventions. ",
doi="10.2196/30557",
url="https://mhealth.jmir.org/2022/1/e30557",
url="http://www.ncbi.nlm.nih.gov/pubmed/34994710"
}


@Article{info:doi/10.2196/31316,
author="Yang, Lin
and Chan, Long Ka
and Yuen, M. John W.
and Wong, Y. Frances K.
and Han, Lefei
and Ho, Chak Hung
and Chang, P. Katherine K.
and Ho, Shan Yuen
and Siu, Yuen-Man Judy
and Tian, Linwei
and Wong, Sing Man",
title="Effects of Urban Green Space on Cardiovascular and Respiratory Biomarkers in Chinese Adults: Panel Study Using Digital Tracking Devices",
journal="JMIR Cardio",
year="2021",
month="Dec",
day="30",
volume="5",
number="2",
pages="e31316",
keywords="green space",
keywords="biomarker",
keywords="cardiovascular disease",
keywords="respiratory disease",
abstract="Background: The health benefits of urban green space have been widely reported in the literature; however, the biological mechanisms remain unexplored, and a causal relationship cannot be established between green space exposure and cardiorespiratory health. Objective: Our aim was to conduct a panel study using personal tracking devices to continuously collect individual exposure data from healthy Chinese adults aged 50 to 64 years living in Hong Kong. Methods: A panel of cardiorespiratory biomarkers was tested each week for a period of 5 consecutive weeks. Data on weekly exposure to green space, air pollution, and the physical activities of individual participants were collected by personal tracking devices. The effects of green space exposure measured by the normalized difference vegetation index (NDVI) at buffer zones of 100, 250, and 500 meters on a panel of cardiorespiratory biomarkers were estimated by a generalized linear mixed-effects model, with adjustment for confounding variables of sociodemographic characteristics, exposure to air pollutants and noise, exercise, and nutrient intake. Results: A total of 39 participants (mean age 56.4 years, range 50-63 years) were recruited and followed up for 5 consecutive weeks. After adjustment for sex, income, occupation, physical activities, dietary intake, noise, and air pollution, significant negative associations with the NDVI for the 250-meter buffer zone were found in total cholesterol (--21.6\% per IQR increase in NDVI, 95\% CI --32.7\% to --10.6\%), low-density lipoprotein (--14.9\%, 95\% CI --23.4\% to --6.4\%), glucose (--11.2\%, 95\% CI --21.9\% to --0.5\%), and high-sensitivity C-reactive protein (--41.3\%, 95\% CI --81.7\% to --0.9\%). Similar effect estimates were found for the 100-meter and 250-meter buffer zones. After adjustment for multiple testing, the effect estimates of glucose and high-sensitivity C-reactive protein were no longer significant. Conclusions: The health benefits of green space can be found in some metabolic and inflammatory biomarkers. Further studies are warranted to establish the causal relationship between green space and cardiorespiratory health. ",
doi="10.2196/31316",
url="https://cardio.jmir.org/2021/2/e31316",
url="http://www.ncbi.nlm.nih.gov/pubmed/34967754"
}


@Article{info:doi/10.2196/31890,
author="Elzinga, O. Willem
and Prins, Samantha
and Borghans, M. Laura G. J.
and Gal, Pim
and Vargas, A. Gabriel
and Groeneveld, J. Geert
and Doll, J. Robert",
title="Detection of Clenbuterol-Induced Changes in Heart Rate Using At-Home Recorded Smartwatch Data: Randomized Controlled Trial",
journal="JMIR Form Res",
year="2021",
month="Dec",
day="30",
volume="5",
number="12",
pages="e31890",
keywords="photoplethysmography",
keywords="smartwatch",
keywords="wearable",
keywords="at-home",
keywords="heart rate",
keywords="RCT",
keywords="wearable device",
keywords="digital health",
keywords="cardiovascular",
keywords="cardiology",
keywords="sensors",
keywords="heart rate sensor",
keywords="smart technology",
abstract="Background: Although electrocardiography is the gold standard for heart rate (HR) recording in clinical trials, the increasing availability of smartwatch-based HR monitors opens up possibilities for drug development studies. Smartwatches allow for inexpensive, unobtrusive, and continuous HR estimation for potential detection of treatment effects outside the clinic, during daily life. Objective: The aim of this study is to evaluate the repeatability and sensitivity of smartwatch-based HR estimates collected during a randomized clinical trial. Methods: The data were collected as part of a multiple-dose, investigator-blinded, randomized, placebo-controlled, parallel-group study of 12 patients with Parkinson disease. After a 6-day baseline period, 4 and 8 patients were treated for 7 days with an ascending dose of placebo and clenbuterol, respectively. Throughout the study, the smartwatch provided HR and sleep state estimates. The HR estimates were quantified as the 2.5th, 50th, and 97.5th percentiles within awake and asleep segments. Linear mixed models were used to calculate the following: (1) the intraclass correlation coefficient (ICC) of estimated sleep durations, (2) the ICC and minimum detectable effect (MDE) of the HR estimates, and (3) the effect sizes of the HR estimates. Results: Sleep duration was moderately repeatable (ICC=0.64) and was not significantly affected by study day (P=.83), clenbuterol (P=.43), and study day by clenbuterol (P=.73). Clenbuterol-induced changes were detected in the asleep HR as of the first night (+3.79 beats per minute [bpm], P=.04) and in the awake HR as of the third day (+8.79 bpm, P=.001). The median HR while asleep had the highest repeatability (ICC=0.70). The MDE (N=12) was found to be smaller when patients were asleep (6.8 bpm to 11.7 bpm) than while awake (10.7 bpm to 22.1 bpm). Overall, the effect sizes for clenbuterol-induced changes were higher while asleep (0.49 to 2.75) than while awake (0.08 to 1.94). Conclusions: We demonstrated the feasibility of using smartwatch-based HR estimates to detect clenbuterol-induced changes during clinical trials. The asleep HR estimates were most repeatable and sensitive to treatment effects. We conclude that smartwatch-based HR estimates obtained during daily living in a clinical trial can be used to detect and track treatment effects. Trial Registration: Netherlands Trials Register NL8002; https://www.trialregister.nl/trial/8002 ",
doi="10.2196/31890",
url="https://formative.jmir.org/2021/12/e31890",
url="http://www.ncbi.nlm.nih.gov/pubmed/34967757"
}


@Article{info:doi/10.2196/28620,
author="May, B. Sarah
and Giordano, P. Thomas
and Gottlieb, Assaf",
title="A Phenotyping Algorithm to Identify People With HIV in Electronic Health Record Data (HIV-Phen): Development and Evaluation Study",
journal="JMIR Form Res",
year="2021",
month="Nov",
day="25",
volume="5",
number="11",
pages="e28620",
keywords="phenotyping",
keywords="algorithms",
keywords="electronic health records",
keywords="people with HIV",
keywords="cohort identification",
abstract="Background: Identification of people with HIV from electronic health record (EHR) data is an essential first step in the study of important HIV outcomes, such as risk assessment. This task has been historically performed via manual chart review, but the increased availability of large clinical data sets has led to the emergence of phenotyping algorithms to automate this process. Existing algorithms for identifying people with HIV rely on a combination of International Classification of Disease codes and laboratory tests or closely mimic clinical testing guidelines for HIV diagnosis. However, we found that existing algorithms in the literature missed a significant proportion of people with HIV in our data. Objective: The aim of this study is to develop and evaluate HIV-Phen, an updated criteria-based HIV phenotyping algorithm. Methods: We developed an algorithm using HIV-specific laboratory tests and medications and compared it with previously published algorithms in national and local data sets to identify cohorts of people with HIV. Cohort demographics were compared with those reported in the national and local surveillance data. Chart reviews were performed on a subsample of patients from the local database to calculate the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the algorithm. Results: Our new algorithm identified substantially more people with HIV in both national (up to an 85.75\% increase) and local (up to an 83.20\% increase) EHR databases than the previously published algorithms. The demographic characteristics of people with HIV identified using our algorithm were similar to those reported in national and local HIV surveillance data. Our algorithm demonstrated improved sensitivity over existing algorithms (98\% vs 56\%-92\%) while maintaining a similar overall accuracy (96\% vs 80\%-96\%). Conclusions: We developed and evaluated an updated criteria-based phenotyping algorithm for identifying people with HIV in EHR data that demonstrates improved sensitivity over existing algorithms. ",
doi="10.2196/28620",
url="https://formative.jmir.org/2021/11/e28620",
url="http://www.ncbi.nlm.nih.gov/pubmed/34842532"
}


@Article{info:doi/10.2196/30249,
author="Kim, Euisung
and Han, Jieun
and Choi, Hojin
and Pri{\'e}, Yannick
and Vigier, Toinon
and Bulteau, Samuel
and Kwon, Hyun Gyu",
title="Examining the Academic Trends in Neuropsychological Tests for Executive Functions Using Virtual Reality: Systematic Literature Review",
journal="JMIR Serious Games",
year="2021",
month="Nov",
day="24",
volume="9",
number="4",
pages="e30249",
keywords="virtual reality",
keywords="neuropsychological test",
keywords="executive function",
keywords="cognitive ability",
keywords="brain disorder",
keywords="immersive",
keywords="digital health",
keywords="cognition",
keywords="academic trends",
keywords="neurology",
abstract="Background: In neuropsychology, fully immersive virtual reality (VR) has been spotlighted as a promising tool. It is considered that VR not only overcomes the existing limitation of neuropsychological tests but is also appropriate for treating executive functions (EFs) within activities of daily living (ADL) due to its high ecological validity. While fully immersive VR offers new possibilities of neuropsychological tests, there are few studies that overview the intellectual landscape and academic trends in the research related to mainly targeted EFs with fully immersive VR. Objective: The objective of this study is to get an overview of the research trends that use VR in neuropsychological tests and to analyze the research trends using fully immersive VR neuropsychological tests with experimental articles. Methods: This review was carried out according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Articles were searched in three web databases using keywords related to VR, EFs, and cognitive abilities. The study was conducted in two steps, keyword analysis and in-depth systematic review. In the web database search from 2000 to 2019, 1167 articles were initially collected, of which 234 articles in the eligibility phase were used to conduct keyword analysis and a total of 47 articles were included for systematic review. Results: In keyword analysis, the number of articles focused on dementia including the keywords ``MCI,'' ``SCD,'' and ``dementia'' were highlighted over the period, rather than other symptoms. In addition, we identified that the use of behavioral and physiological data in virtual environments (VEs) has dramatically increased in recent studies. In the systematic review, we focused on the purpose of study, assessment, treatment, and validation of usability and structure. We found that treatment studies and uncategorized studies including presence and cybersickness issues have emerged in the recent period. In addition, the target symptoms and range of participants were diversified. Conclusions: There has been a continuously increasing interest in dealing with neuropsychology by using fully immersive VR. Target cognitive abilities have been diversified, as well as target symptoms. Moreover, the concept of embodied cognition was transplanted in this research area. ",
doi="10.2196/30249",
url="https://games.jmir.org/2021/4/e30249",
url="http://www.ncbi.nlm.nih.gov/pubmed/34822341"
}


@Article{info:doi/10.2196/29267,
author="ter Harmsel, Annemieke
and van der Pol, Thimo
and Swinkels, Lise
and Goudriaan, E. Anna
and Popma, Arne
and Noordzij, L. Matthijs",
title="Development of a Wearable Biocueing App (Sense-IT) Among Forensic Psychiatric Outpatients With Aggressive Behavior: Design and Evaluation Study",
journal="JMIR Form Res",
year="2021",
month="Nov",
day="24",
volume="5",
number="11",
pages="e29267",
keywords="biocueing",
keywords="biosensing",
keywords="biofeedback",
keywords="aggression",
keywords="forensic psychiatry",
keywords="wearable technology",
keywords="mobile apps",
keywords="usability",
keywords="evaluation",
keywords="mHealth",
abstract="Background: The ability to regulate anger is often impaired in forensic psychiatric patients, frequently resulting in aggressive behavior. Although some treatment programs are partially successful in enhancing aggression regulation and reducing recidivism among specific subgroups, generalizable conclusions on the effectiveness of these interventions cannot be drawn to date. In forensic outpatient care, low treatment adherence and a predominant focus on cognitive control in most treatment programs may entail some of the factors impeding treatment. Technology-based interventions may address some of these treatment challenges. Objective: The aim of this study is to explore whether a new technology-based biocueing intervention, the Sense-IT app, can be a valuable addition to aggression regulation treatment programs in forensic outpatient care. The Sense-IT app, which provides the user with real-time physiological feedback and behavioral support, is developed to strengthen emotional awareness and facilitate real-life practice. In this study, we aim to develop and evaluate an updated version of the Sense-IT app that is suitable for forensic outpatients with aggressive behavior. Methods: First, we conducted a design study to assess the attitudes of forensic professionals and patients toward biocueing and to collect requirements for a biocueing app for this specific population. On the basis of this information, we developed an updated version of the Sense-IT app. In an evaluation study, 10 forensic outpatients used the app for 2 weeks. The app's acceptability, usability, and clinical outcomes (aggression, anger, and recognition of bodily signals related to anger) were measured before and after the intervention using both quantitative and qualitative measures. Results: The design study revealed a cautiously positive attitude toward the use of biocueing as an addition to aggression regulation therapy. The evaluation study among forensic outpatients demonstrated moderate acceptability and adequate usability for the new version of the Sense-IT app. Exploratory analysis revealed a significant decrease in trait aggression postintervention; no significant changes were found in other anger-related clinical outcomes. To further increase acceptability and usability, a stable functioning app with self-adjustable settings, the use of smartwatches with a longer battery life, and the use of the patient's own smartphone devices were recommended. Conclusions: This study, which is one of the first attempts to enroll and evaluate the real-life use of a biocueing intervention among forensic outpatients, emphasized the importance of involving both patients and therapists throughout the development and implementation process. In the future, experimental studies, including single-case experimental designs using ecological momentary assessment, should be performed to evaluate the effectiveness of the Sense-IT intervention on clinical outcomes. An open attitude toward new technology, allowing exploration of the potential benefits of the Sense-IT app case-by-case, and training of therapists in using the app are expected to facilitate its integration in therapy. ",
doi="10.2196/29267",
url="https://formative.jmir.org/2021/11/e29267",
url="http://www.ncbi.nlm.nih.gov/pubmed/34821567"
}


@Article{info:doi/10.2196/28204,
author="Motahari-Nezhad, Hossein
and P{\'e}ntek, M{\'a}rta
and Gul{\'a}csi, L{\'a}szl{\'o}
and Zrubka, Zsombor",
title="Outcomes of Digital Biomarker--Based Interventions: Protocol for a Systematic Review of Systematic Reviews",
journal="JMIR Res Protoc",
year="2021",
month="Nov",
day="24",
volume="10",
number="11",
pages="e28204",
keywords="digital biomarker",
keywords="outcome",
keywords="systematic review",
keywords="meta-analysis",
keywords="digital health",
keywords="mobile health",
keywords="Grading of Recommendations, Assessment, Development and Evaluation",
keywords="AMSTAR-2",
keywords="review",
keywords="biomarkers",
keywords="clinical outcome",
keywords="interventions",
keywords="wearables",
keywords="portables",
keywords="digestables",
keywords="implants",
abstract="Background: Digital biomarkers?are?defined?as objective, quantifiable, physiological, and behavioral data that are collected and measured using?digital?devices such as portables, wearables, implantables, or digestibles. For their widespread adoption in publicly financed health care systems, it is important to understand how their benefits translate into improved patient outcomes, which is essential for demonstrating their value. Objective: The paper presents the protocol for a systematic review that aims to assess the quality and strength of the evidence reported in systematic reviews regarding the impact of digital biomarkers on clinical outcomes compared to interventions without digital biomarkers. Methods: A comprehensive search for reviews from 2019 to 2020 will be conducted in PubMed and the Cochrane Library using keywords related to digital biomarkers and a filter for systematic reviews. Original full-text English publications of systematic reviews comparing clinical outcomes of interventions with and without digital biomarkers via meta-analysis will be included. The AMSTAR-2 tool will be used to assess the methodological quality of these reviews. To assess the quality of evidence, we will evaluate the systematic reviews using the Grading of Recommendations, Assessment, Development and Evaluation (GRADE) tool. To detect the possible presence of reporting bias, we will determine whether a protocol was published prior to the start of the studies. A qualitative summary of the results by digital biomarker technology and outcomes will be provided. Results: This protocol was submitted before data collection. Search, screening, and data extraction will commence in December 2021 in accordance with the published protocol. Conclusions: Our study will provide a comprehensive summary of the highest level of evidence available on digital biomarker interventions, providing practical guidance for health care providers. Our results will help identify clinical areas in which the use of digital biomarkers has led to favorable clinical outcomes. In addition, our findings will highlight areas of evidence gaps where the clinical benefits of digital biomarkers have not yet been demonstrated. International Registered Report Identifier (IRRID): PRR1-10.2196/28204 ",
doi="10.2196/28204",
url="https://www.researchprotocols.org/2021/11/e28204",
url="http://www.ncbi.nlm.nih.gov/pubmed/34821568"
}


@Article{info:doi/10.2196/30915,
author="Kiekens, Glenn
and Robinson, Kealagh
and Tatnell, Ruth
and Kirtley, J. Olivia",
title="Opening the Black Box of Daily Life in Nonsuicidal Self-injury Research: With Great Opportunity Comes Great Responsibility",
journal="JMIR Ment Health",
year="2021",
month="Nov",
day="19",
volume="8",
number="11",
pages="e30915",
keywords="real-time monitoring",
keywords="nonsuicidal self-injury",
keywords="NSSI",
keywords="experience sampling",
keywords="ecological momentary assessment",
keywords="digital psychiatry",
doi="10.2196/30915",
url="https://mental.jmir.org/2021/11/e30915",
url="http://www.ncbi.nlm.nih.gov/pubmed/34807835"
}


@Article{info:doi/10.2196/18359,
author="Gielis, Karsten
and Vanden Abeele, Marie-Elena
and De Croon, Robin
and Dierick, Paul
and Ferreira-Brito, Filipa
and Van Assche, Lies
and Verbert, Katrien
and Tournoy, Jos
and Vanden Abeele, Vero",
title="Dissecting Digital Card Games to Yield Digital Biomarkers for the Assessment of Mild Cognitive Impairment: Methodological Approach and Exploratory Study",
journal="JMIR Serious Games",
year="2021",
month="Nov",
day="4",
volume="9",
number="4",
pages="e18359",
keywords="mild cognitive impairment",
keywords="Klondike Solitaire",
keywords="card games",
keywords="generalized linear mixed effects analysis",
keywords="expert study",
keywords="monitoring",
keywords="screening",
keywords="cognition",
keywords="dementia",
keywords="older adults",
keywords="mobile phone",
abstract="Background: Mild cognitive impairment (MCI), the intermediate cognitive status between normal cognitive decline and pathological decline, is an important clinical construct for signaling possible prodromes of dementia. However, this condition is underdiagnosed. To assist monitoring and screening, digital biomarkers derived from commercial off-the-shelf video games may be of interest. These games maintain player engagement over a longer period of time and support longitudinal measurements of cognitive performance. Objective: This paper aims to explore how the player actions of Klondike Solitaire relate to cognitive functions and to what extent the digital biomarkers derived from these player actions are indicative of MCI. Methods: First, 11 experts in the domain of cognitive impairments were asked to correlate 21 player actions to 11 cognitive functions. Expert agreement was verified through intraclass correlation, based on a 2-way, fully crossed design with type consistency. On the basis of these player actions, 23 potential digital biomarkers of performance for Klondike Solitaire were defined. Next, 23 healthy participants and 23 participants living with MCI were asked to play 3 rounds of Klondike Solitaire, which took 17 minutes on average to complete. A generalized linear mixed model analysis was conducted to explore the differences in digital biomarkers between the healthy participants and those living with MCI, while controlling for age, tablet experience, and Klondike Solitaire experience. Results: All intraclass correlations for player actions and cognitive functions scored higher than 0.75, indicating good to excellent reliability. Furthermore, all player actions had, according to the experts, at least one cognitive function that was on average moderately to strongly correlated to a cognitive function. Of the 23 potential digital biomarkers, 12 (52\%) were revealed by the generalized linear mixed model analysis to have sizeable effects and significance levels. The analysis indicates sensitivity of the derived digital biomarkers to MCI. Conclusions: Commercial off-the-shelf games such as digital card games show potential as a complementary tool for screening and monitoring cognition. Trial Registration: ClinicalTrials.gov NCT02971124; https://clinicaltrials.gov/ct2/show/NCT02971124 ",
doi="10.2196/18359",
url="https://games.jmir.org/2021/4/e18359",
url="http://www.ncbi.nlm.nih.gov/pubmed/34734825"
}


@Article{info:doi/10.2196/26957,
author="Worth, Chris
and Harper, Simon
and Salomon-Estebanez, Maria
and O'Shea, Elaine
and Nutter, W. Paul
and Dunne, J. Mark
and Banerjee, Indraneel",
title="Clustering of Hypoglycemia Events in Patients With Hyperinsulinism: Extension of the Digital Phenotype Through Retrospective Data Analysis",
journal="J Med Internet Res",
year="2021",
month="Oct",
day="29",
volume="23",
number="10",
pages="e26957",
keywords="hyperinsulinism",
keywords="continuous glucose monitoring",
keywords="digital phenotype",
keywords="hypoglycemia",
keywords="nocturnal hypoglycemia",
abstract="Background: Hyperinsulinism (HI) due to excess and dysregulated insulin secretion is the most common cause of severe and recurrent hypoglycemia in childhood. High cerebral glucose use in the early hours results in a high risk of hypoglycemia in people with diabetes and carries a significant risk of brain injury. Prevention of hypoglycemia is the cornerstone of the management of HI, but the risk of hypoglycemia at night or the timing of hypoglycemia in children with HI has not been studied; thus, the digital phenotype remains incomplete and management suboptimal. Objective: This study aims to quantify the timing of hypoglycemia in patients with HI to describe glycemic variability and to extend the digital phenotype. This will facilitate future work using computational modeling to enable behavior change and reduce exposure of patients with HI to injurious hypoglycemic events. Methods: Patients underwent continuous glucose monitoring (CGM) with a Dexcom G4 or G6 CGM device as part of their clinical assessment for either HI (N=23) or idiopathic ketotic hypoglycemia (IKH; N=24). The CGM data were analyzed for temporal trends. Hypoglycemia was defined as glucose levels <3.5 mmol/L. Results: A total of 449 hypoglycemic events totaling 15,610 minutes were captured over 237 days from 47 patients (29 males; mean age 70 months, SD 53). The mean length of hypoglycemic events was 35 minutes. There was a clear tendency for hypoglycemia in the early hours (3-7 AM), particularly for patients with HI older than 10 months who experienced hypoglycemia 7.6\% (1480/19,370 minutes) of time in this period compared with 2.6\% (2405/92,840 minutes) of time outside this period (P<.001). This tendency was less pronounced in patients with HI who were younger than 10 months, patients with a negative genetic test result, and patients with IKH. Despite real-time CGM, there were 42 hypoglycemic events from 13 separate patients with HI lasting >30 minutes. Conclusions: This is the first study to have taken the first step in extending the digital phenotype of HI by describing the glycemic trends and identifying the timing of hypoglycemia measured by CGM. We have identified the early hours as a time of high hypoglycemia risk for patients with HI and demonstrated that simple provision of CGM data to patients is not sufficient to eliminate hypoglycemia. Future work in HI should concentrate on the early hours as a period of high risk for hypoglycemia and must target personalized hypoglycemia predictions. Focus must move to the human-computer interaction as an aspect of the digital phenotype that is susceptible to change rather than simple mathematical modeling to produce small improvements in hypoglycemia prediction accuracy. ",
doi="10.2196/26957",
url="https://www.jmir.org/2021/10/e26957",
url="http://www.ncbi.nlm.nih.gov/pubmed/34435596"
}


@Article{info:doi/10.2196/24872,
author="Rykov, Yuri
and Thach, Thuan-Quoc
and Bojic, Iva
and Christopoulos, George
and Car, Josip",
title="Digital Biomarkers for Depression Screening With Wearable Devices: Cross-sectional Study With Machine Learning Modeling",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Oct",
day="25",
volume="9",
number="10",
pages="e24872",
keywords="depression",
keywords="digital biomarkers",
keywords="screening",
keywords="wearable electronic device",
keywords="fitness tracker",
keywords="circadian rhythm",
keywords="rest-activity rhythm",
keywords="heart rate",
keywords="machine learning",
abstract="Background: Depression is a prevalent mental disorder that is undiagnosed and untreated in half of all cases. Wearable activity trackers collect fine-grained sensor data characterizing the behavior and physiology of users (ie, digital biomarkers), which could be used for timely, unobtrusive, and scalable depression screening. Objective: The aim of this study was to examine the predictive ability of digital biomarkers, based on sensor data from consumer-grade wearables, to detect risk of depression in a working population. Methods: This was a cross-sectional study of 290 healthy working adults. Participants wore Fitbit Charge 2 devices for 14 consecutive days and completed a health survey, including screening for depressive symptoms using the 9-item Patient Health Questionnaire (PHQ-9), at baseline and 2 weeks later. We extracted a range of known and novel digital biomarkers characterizing physical activity, sleep patterns, and circadian rhythms from wearables using steps, heart rate, energy expenditure, and sleep data. Associations between severity of depressive symptoms and digital biomarkers were examined with Spearman correlation and multiple regression analyses adjusted for potential confounders, including sociodemographic characteristics, alcohol consumption, smoking, self-rated health, subjective sleep characteristics, and loneliness. Supervised machine learning with statistically selected digital biomarkers was used to predict risk of depression (ie, symptom severity and screening status). We used varying cutoff scores from an acceptable PHQ-9 score range to define the depression group and different subsamples for classification, while the set of statistically selected digital biomarkers remained the same. For the performance evaluation, we used k-fold cross-validation and obtained accuracy measures from the holdout folds. Results: A total of 267 participants were included in the analysis. The mean age of the participants was 33 (SD 8.6, range 21-64) years. Out of 267 participants, there was a mild female bias displayed (n=170, 63.7\%). The majority of the participants were Chinese (n=211, 79.0\%), single (n=163, 61.0\%), and had a university degree (n=238, 89.1\%). We found that a greater severity of depressive symptoms was robustly associated with greater variation of nighttime heart rate between 2 AM and 4 AM and between 4 AM and 6 AM; it was also associated with lower regularity of weekday circadian rhythms based on steps and estimated with nonparametric measures of interdaily stability and autocorrelation as well as fewer steps-based daily peaks. Despite several reliable associations, our evidence showed limited ability of digital biomarkers to detect depression in the whole sample of working adults. However, in balanced and contrasted subsamples comprised of depressed and healthy participants with no risk of depression (ie, no or minimal depressive symptoms), the model achieved an accuracy of 80\%, a sensitivity of 82\%, and a specificity of 78\% in detecting subjects at high risk of depression. Conclusions: Digital biomarkers that have been discovered and are based on behavioral and physiological data from consumer wearables could detect increased risk of depression and have the potential to assist in depression screening, yet current evidence shows limited predictive ability. Machine learning models combining these digital biomarkers could discriminate between individuals with a high risk of depression and individuals with no risk. ",
doi="10.2196/24872",
url="https://mhealth.jmir.org/2021/10/e24872",
url="http://www.ncbi.nlm.nih.gov/pubmed/34694233"
}


@Article{info:doi/10.2196/29160,
author="Brogly, Chris
and Shoemaker, Kevin J.
and Lizotte, J. Daniel
and Kueper, K. Jacqueline
and Bauer, Michael",
title="A Mobile App to Identify Lifestyle Indicators Related to Undergraduate Mental Health (Smart Healthy Campus): Observational App-Based Ecological Momentary Assessment",
journal="JMIR Form Res",
year="2021",
month="Oct",
day="19",
volume="5",
number="10",
pages="e29160",
keywords="smartphones",
keywords="undergraduates",
keywords="mental health",
keywords="lifestyle",
keywords="postsecondary institutions",
keywords="mHealth",
keywords="mobile application",
keywords="ecological momentary assessment",
keywords="mobile phone",
abstract="Background: Undergraduate studies are challenging, and mental health issues can frequently occur in undergraduate students, straining campus resources that are already in demand for somatic problems. Cost-effective measures with ubiquitous devices, such as smartphones, offer the potential to deliver targeted interventions to monitor and affect lifestyle, which may result in improvements to student mental health. However, the avenues by which this can be done are not particularly well understood, especially in the Canadian context. Objective: The aim of this study is to deploy an initial version of the Smart Healthy Campus app at Western University, Canada, and to analyze corresponding data for associations between psychosocial factors (measured by a questionnaire) and behaviors associated with lifestyle (measured by smartphone sensors). Methods: This preliminary study was conducted as an observational app-based ecological momentary assessment. Undergraduate students were recruited over email, and sampling using a custom 7-item questionnaire occurred on a weekly basis. Results: First, the 7-item Smart Healthy Campus questionnaire, derived from fully validated questionnaires---such as the Brief Resilience Scale; General Anxiety Disorder-7; and Depression, Anxiety, and Stress Scale--21---was shown to significantly correlate with the mental health domains of these validated questionnaires, illustrating that it is a viable tool for a momentary assessment of an overview of undergraduate mental health. Second, data collected through the app were analyzed. There were 312 weekly responses and 813 sensor samples from 139 participants from March 2019 to March 2020; data collection concluded when COVID-19 was declared a pandemic. Demographic information was not collected in this preliminary study because of technical limitations. Approximately 69.8\% (97/139) of participants only completed one survey, possibly because of the absence of any incentive. Given the limited amount of data, analysis was not conducted with respect to time, so all data were analyzed as a single collection. On the basis of mean rank, students showing more positive mental health through higher questionnaire scores tended to spend more time completing questionnaires, showed more signs of physical activity based on pedometers, and had their devices running less and plugged in charging less when sampled. In addition, based on mean rank, students on campus tended to report more positive mental health through higher questionnaire scores compared with those who were sampled off campus. Some data from students found in or near residences were also briefly examined. Conclusions: Given these limited data, participants tended to report a more positive overview of mental health when on campus and when showing signs of higher levels of physical activity. These early findings suggest that device sensors related to physical activity and location are useful for monitoring undergraduate students and designing interventions. However, much more sensor data are needed going forward, especially given the sweeping changes in undergraduate studies due to COVID-19. ",
doi="10.2196/29160",
url="https://formative.jmir.org/2021/10/e29160",
url="http://www.ncbi.nlm.nih.gov/pubmed/34665145"
}


@Article{info:doi/10.2196/32656,
author="Shaukat-Jali, Ruksana
and van Zalk, Nejra
and Boyle, Edward David",
title="Detecting Subclinical Social Anxiety Using Physiological Data From a Wrist-Worn Wearable: Small-Scale Feasibility Study",
journal="JMIR Form Res",
year="2021",
month="Oct",
day="7",
volume="5",
number="10",
pages="e32656",
keywords="social anxiety",
keywords="wearable sensors",
keywords="physiological measurement",
keywords="machine learning",
keywords="young adults",
keywords="mental health",
keywords="mHealth",
keywords="new methods",
keywords="anxiety",
keywords="wearable",
keywords="sensor",
keywords="digital phenotyping",
keywords="digital biomarkers",
abstract="Background: Subclinical (ie, threshold) social anxiety can greatly affect young people's lives, but existing solutions appear inadequate considering its rising prevalence. Wearable sensors may provide a novel way to detect social anxiety and result in new opportunities for monitoring and treatment, which would be greatly beneficial for persons with social anxiety, society, and health care services. Nevertheless, indicators such as skin temperature measured by wrist-worn sensors have not been used in prior work on physiological social anxiety detection. Objective: This study aimed to investigate whether subclinical social anxiety in young adults can be detected using physiological data obtained from wearable sensors, including heart rate, skin temperature, and electrodermal activity (EDA). Methods: Young adults (N=12) with self-reported subclinical social anxiety (measured using the widely used self-reported version of the Liebowitz Social Anxiety Scale) participated in an impromptu speech task. Physiological data were collected using an E4 Empatica wearable device. Using the preprocessed data and following a supervised machine learning approach, various classification algorithms such as Support Vector Machine, Decision Tree, Random Forest, and K-Nearest Neighbours (KNN) were used to develop models for 3 different contexts. Models were trained to differentiate (1) between baseline and socially anxious states, (2) among baseline, anticipation anxiety, and reactive anxiety states, and (3) social anxiety among individuals with social anxiety of differing severity. The predictive capability of the singular modalities was also explored in each of the 3 supervised learning experiments. The generalizability of the developed models was evaluated using 10-fold cross-validation as a performance index. Results: With modalities combined, the developed models yielded accuracies between 97.54\% and 99.48\% when differentiating between baseline and socially anxious states. Models trained to differentiate among baseline, anticipation anxiety, and reactive anxiety states yielded accuracies between 95.18\% and 98.10\%. Furthermore, the models developed to differentiate between social anxiety experienced by individuals with anxiety of differing severity scores successfully classified with accuracies between 98.86\% and 99.52\%. Surprisingly, EDA was identified as the most effective singular modality when differentiating between baseline and social anxiety states, whereas ST was the most effective modality when differentiating anxiety among individuals with social anxiety of differing severity. Conclusions: The results indicate that it is possible to accurately detect social anxiety as well as distinguish between levels of severity in young adults by leveraging physiological data collected from wearable sensors. ",
doi="10.2196/32656",
url="https://formative.jmir.org/2021/10/e32656",
url="http://www.ncbi.nlm.nih.gov/pubmed/34617905"
}


@Article{info:doi/10.2196/24352,
author="Flanagan, Olivia
and Chan, Amy
and Roop, Partha
and Sundram, Frederick",
title="Using Acoustic Speech Patterns From Smartphones to Investigate Mood Disorders: Scoping Review",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Sep",
day="17",
volume="9",
number="9",
pages="e24352",
keywords="smartphone",
keywords="data science",
keywords="speech patterns",
keywords="mood disorders",
keywords="diagnosis",
keywords="monitoring",
abstract="Background: Mood disorders are commonly underrecognized and undertreated, as diagnosis is reliant on self-reporting and clinical assessments that are often not timely. Speech characteristics of those with mood disorders differs from healthy individuals. With the wide use of smartphones, and the emergence of machine learning approaches, smartphones can be used to monitor speech patterns to help the diagnosis and monitoring of mood disorders. Objective: The aim of this review is to synthesize research on using speech patterns from smartphones to diagnose and monitor mood disorders. Methods: Literature searches of major databases, Medline, PsycInfo, EMBASE, and CINAHL, initially identified 832 relevant articles using the search terms ``mood disorders'', ``smartphone'', ``voice analysis'', and their variants. Only 13 studies met inclusion criteria: use of a smartphone for capturing voice data, focus on diagnosing or monitoring a mood disorder(s), clinical populations recruited prospectively, and in the English language only. Articles were assessed by 2 reviewers, and data extracted included data type, classifiers used, methods of capture, and study results. Studies were analyzed using a narrative synthesis approach. Results: Studies showed that voice data alone had reasonable accuracy in predicting mood states and mood fluctuations based on objectively monitored speech patterns. While a fusion of different sensor modalities revealed the highest accuracy (97.4\%), nearly 80\% of included studies were pilot trials or feasibility studies without control groups and had small sample sizes ranging from 1 to 73 participants. Studies were also carried out over short or varying timeframes and had significant heterogeneity of methods in terms of the types of audio data captured, environmental contexts, classifiers, and measures to control for privacy and ambient noise. Conclusions: Approaches that allow smartphone-based monitoring of speech patterns in mood disorders are rapidly growing. The current body of evidence supports the value of speech patterns to monitor, classify, and predict mood states in real time. However, many challenges remain around the robustness, cost-effectiveness, and acceptability of such an approach and further work is required to build on current research and reduce heterogeneity of methodologies as well as clinical evaluation of the benefits and risks of such approaches. ",
doi="10.2196/24352",
url="https://mhealth.jmir.org/2021/9/e24352",
url="http://www.ncbi.nlm.nih.gov/pubmed/34533465"
}


@Article{info:doi/10.2196/29875,
author="Shandhi, Hasan Md Mobashir
and Goldsack, C. Jennifer
and Ryan, Kyle
and Bennion, Alexandra
and Kotla, V. Aditya
and Feng, Alina
and Jiang, Yihang
and Wang, Ke Will
and Hurst, Tina
and Patena, John
and Carini, Simona
and Chung, Jeanne
and Dunn, Jessilyn",
title="Recent Academic Research on Clinically Relevant Digital Measures: Systematic Review",
journal="J Med Internet Res",
year="2021",
month="Sep",
day="15",
volume="23",
number="9",
pages="e29875",
keywords="digital clinical measures",
keywords="academic research",
keywords="funding",
keywords="biosensor",
keywords="digital measures",
keywords="digital health",
keywords="health outcomes",
abstract="Background: Digital clinical measures collected via various digital sensing technologies such as smartphones, smartwatches, wearables, ingestibles, and implantables are increasingly used by individuals and clinicians to capture health outcomes or behavioral and physiological characteristics of individuals. Although academia is taking an active role in evaluating digital sensing products, academic contributions to advancing the safe, effective, ethical, and equitable use of digital clinical measures are poorly characterized. Objective: We performed a systematic review to characterize the nature of academic research on digital clinical measures and to compare and contrast the types of sensors used and the sources of funding support for specific subareas of this research. Methods: We conducted a PubMed search using a range of search terms to retrieve peer-reviewed articles reporting US-led academic research on digital clinical measures between January 2019 and February 2021. We screened each publication against specific inclusion and exclusion criteria. We then identified and categorized research studies based on the types of academic research, sensors used, and funding sources. Finally, we compared and contrasted the funding support for these specific subareas of research and sensor types. Results: The search retrieved 4240 articles of interest. Following the screening, 295 articles remained for data extraction and categorization. The top five research subareas included operations research (research analysis; n=225, 76\%), analytical validation (n=173, 59\%), usability and utility (data visualization; n=123, 42\%), verification (n=93, 32\%), and clinical validation (n=83, 28\%). The three most underrepresented areas of research into digital clinical measures were ethics (n=0, 0\%), security (n=1, 0.5\%), and data rights and governance (n=1, 0.5\%). Movement and activity trackers were the most commonly studied sensor type, and physiological (mechanical) sensors were the least frequently studied. We found that government agencies are providing the most funding for research on digital clinical measures (n=192, 65\%), followed by independent foundations (n=109, 37\%) and industries (n=56, 19\%), with the remaining 12\% (n=36) of these studies completely unfunded. Conclusions: Specific subareas of academic research related to digital clinical measures are not keeping pace with the rapid expansion and adoption of digital sensing products. An integrated and coordinated effort is required across academia, academic partners, and academic funders to establish the field of digital clinical measures as an evidence-based field worthy of our trust. ",
doi="10.2196/29875",
url="https://www.jmir.org/2021/9/e29875",
url="http://www.ncbi.nlm.nih.gov/pubmed/34524089"
}


@Article{info:doi/10.2196/26608,
author="Sahandi Far, Mehran
and Eickhoff, B. Simon
and Goni, Maria
and Dukart, Juergen",
title="Exploring Test-Retest Reliability and Longitudinal Stability of Digital Biomarkers for Parkinson Disease in the m-Power Data Set: Cohort Study",
journal="J Med Internet Res",
year="2021",
month="Sep",
day="13",
volume="23",
number="9",
pages="e26608",
keywords="health sciences",
keywords="medical research",
keywords="biomarkers",
keywords="diagnostic markers",
keywords="neurological disorders",
keywords="Parkinson disease",
keywords="mobile phone",
abstract="Background: Digital biomarkers (DB), as captured using sensors embedded in modern smart devices, are a promising technology for home-based sign and symptom monitoring in Parkinson disease (PD). Objective: Despite extensive application in recent studies, test-retest reliability and longitudinal stability of DB have not been well addressed in this context. We utilized the large-scale m-Power data set to establish the test-retest reliability and longitudinal stability of gait, balance, voice, and tapping tasks in an unsupervised and self-administered daily life setting in patients with PD and healthy controls (HC). Methods: Intraclass correlation coefficients were computed to estimate the test-retest reliability of features that also differentiate between patients with PD and healthy volunteers. In addition, we tested for longitudinal stability of DB measures in PD and HC, as well as for their sensitivity to PD medication effects. Results: Among the features differing between PD and HC, only a few tapping and voice features had good to excellent test-retest reliabilities and medium to large effect sizes. All other features performed poorly in this respect. Only a few features were sensitive to medication effects. The longitudinal analyses revealed significant alterations over time across a variety of features and in particular for the tapping task. Conclusions: These results indicate the need for further development of more standardized, sensitive, and reliable DB for application in self-administered remote studies in patients with PD. Motivational, learning, and other confounders may cause variations in performance that need to be considered in DB longitudinal applications. ",
doi="10.2196/26608",
url="https://www.jmir.org/2021/9/e26608",
url="http://www.ncbi.nlm.nih.gov/pubmed/34515645"
}


@Article{info:doi/10.2196/22844,
author="Meyerhoff, Jonah
and Liu, Tony
and Kording, P. Konrad
and Ungar, H. Lyle
and Kaiser, M. Susan
and Karr, J. Chris
and Mohr, C. David",
title="Evaluation of Changes in Depression, Anxiety, and Social Anxiety Using Smartphone Sensor Features: Longitudinal Cohort Study",
journal="J Med Internet Res",
year="2021",
month="Sep",
day="3",
volume="23",
number="9",
pages="e22844",
keywords="mHealth",
keywords="personal sensing",
keywords="digital phenotyping",
keywords="passive sensing",
keywords="ecological momentary assessment",
keywords="depression",
keywords="anxiety",
keywords="digital biomarkers",
keywords="mental health assessment",
keywords="mobile device",
keywords="mobile phone",
keywords="internet technology",
keywords="psychiatric disorders",
abstract="Background: The assessment of behaviors related to mental health typically relies on self-report data. Networked sensors embedded in smartphones can measure some behaviors objectively and continuously, with no ongoing effort. Objective: This study aims to evaluate whether changes in phone sensor--derived behavioral features were associated with subsequent changes in mental health symptoms. Methods: This longitudinal cohort study examined continuously collected phone sensor data and symptom severity data, collected every 3 weeks, over 16 weeks. The participants were recruited through national research registries. Primary outcomes included depression (8-item Patient Health Questionnaire), generalized anxiety (Generalized Anxiety Disorder 7-item scale), and social anxiety (Social Phobia Inventory) severity. Participants were adults who owned Android smartphones. Participants clustered into 4 groups: multiple comorbidities, depression and generalized anxiety, depression and social anxiety, and minimal symptoms. Results: A total of 282 participants were aged 19-69 years (mean 38.9, SD 11.9 years), and the majority were female (223/282, 79.1\%) and White participants (226/282, 80.1\%). Among the multiple comorbidities group, depression changes were preceded by changes in GPS features (Time: r=?0.23, P=.02; Locations: r=?0.36, P<.001), exercise duration (r=0.39; P=.03) and use of active apps (r=?0.31; P<.001). Among the depression and anxiety groups, changes in depression were preceded by changes in GPS features for Locations (r=?0.20; P=.03) and Transitions (r=?0.21; P=.03). Depression changes were not related to subsequent sensor-derived features. The minimal symptoms group showed no significant relationships. There were no associations between sensor-based features and anxiety and minimal associations between sensor-based features and social anxiety. Conclusions: Changes in sensor-derived behavioral features are associated with subsequent depression changes, but not vice versa, suggesting a directional relationship in which changes in sensed behaviors are associated with subsequent changes in symptoms. ",
doi="10.2196/22844",
url="https://www.jmir.org/2021/9/e22844",
url="http://www.ncbi.nlm.nih.gov/pubmed/34477562"
}


@Article{info:doi/10.2196/25907,
author="Brasier, Noe
and Osthoff, Michael
and De Ieso, Fiorangelo
and Eckstein, Jens",
title="Next-Generation Digital Biomarkers for Tuberculosis and Antibiotic Stewardship: Perspective on Novel Molecular Digital Biomarkers in Sweat, Saliva, and Exhaled Breath",
journal="J Med Internet Res",
year="2021",
month="Aug",
day="19",
volume="23",
number="8",
pages="e25907",
keywords="digital biomarkers",
keywords="active tuberculosis",
keywords="drug resistance",
keywords="wearable",
keywords="smart biosensors",
keywords="iSudorology",
keywords="infectious diseases",
doi="10.2196/25907",
url="https://www.jmir.org/2021/8/e25907",
url="http://www.ncbi.nlm.nih.gov/pubmed/34420925"
}


@Article{info:doi/10.2196/17411,
author="Patel, Vikas
and Orchanian-Cheff, Ani
and Wu, Robert",
title="Evaluating the Validity and Utility of Wearable Technology for Continuously Monitoring Patients in a Hospital Setting: Systematic Review",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Aug",
day="18",
volume="9",
number="8",
pages="e17411",
keywords="wearable",
keywords="inpatient",
keywords="continuous monitoring",
abstract="Background: The term posthospital syndrome has been used to describe the condition in which older patients are transiently frail after hospitalization and have a high chance of readmission. Since low activity and poor sleep during hospital stay may contribute to posthospital syndrome, the continuous monitoring of such parameters by using affordable wearables may help to reduce the prevalence of this syndrome. Although there have been systematic reviews of wearables for physical activity monitoring in hospital settings, there are limited data on the use of wearables for measuring other health variables in hospitalized patients. Objective: This systematic review aimed to evaluate the validity and utility of wearable devices for monitoring hospitalized patients. Methods: This review involved a comprehensive search of 7 databases and included articles that met the following criteria: inpatients must be aged >18 years, the wearable devices studied in the articles must be used to continuously monitor patients, and wearables should monitor biomarkers other than solely physical activity (ie, heart rate, respiratory rate, blood pressure, etc). Only English-language studies were included. From each study, we extracted basic demographic information along with the characteristics of the intervention. We assessed the risk of bias for studies that validated their wearable readings by using a modification of the Consensus-Based Standards for the Selection of Health Status Measurement Instruments. Results: Of the 2012 articles that were screened, 14 studies met the selection criteria. All included articles were observational in design. In total, 9 different commercial wearables for various body locations were examined in this review. The devices collectively measured 7 different health parameters across all studies (heart rate, sleep duration, respiratory rate, oxygen saturation, skin temperature, blood pressure, and fall risk). Only 6 studies validated their results against a reference device or standard. There was a considerable risk of bias in these studies due to the low number of patients in most of the studies (4/6, 67\%). Many studies that validated their results found that certain variables were inaccurate and had wide limits of agreement. Heart rate and sleep were the parameters with the most evidence for being valid for in-hospital monitoring. Overall, the mean patient completion rate across all 14 studies was >90\%. Conclusions: The included studies suggested that wearable devices show promise for monitoring the heart rate and sleep of patients in hospitals. Many devices were not validated in inpatient settings, and the readings from most of the devices that were validated in such settings had wide limits of agreement when compared to gold standards. Even some medical-grade devices were found to perform poorly in inpatient settings. Further research is needed to determine the accuracy of hospitalized patients' digital biomarker readings and eventually determine whether these wearable devices improve health outcomes. ",
doi="10.2196/17411",
url="https://mhealth.jmir.org/2021/8/e17411",
url="http://www.ncbi.nlm.nih.gov/pubmed/34406121"
}


@Article{info:doi/10.2196/28918,
author="Di Matteo, Daniel
and Fotinos, Kathryn
and Lokuge, Sachinthya
and Mason, Geneva
and Sternat, Tia
and Katzman, A. Martin
and Rose, Jonathan",
title="Automated Screening for Social Anxiety, Generalized Anxiety, and Depression From Objective Smartphone-Collected Data: Cross-sectional Study",
journal="J Med Internet Res",
year="2021",
month="Aug",
day="13",
volume="23",
number="8",
pages="e28918",
keywords="mobile sensing",
keywords="passive EMA",
keywords="passive sensing",
keywords="psychiatric assessment",
keywords="mood and anxiety disorders",
keywords="mobile apps",
keywords="mhealth",
keywords="mobile phone",
keywords="digital health",
keywords="digital phenotyping",
abstract="Background: The lack of access to mental health care could be addressed, in part, through the development of automated screening technologies for detecting the most common mental health disorders without the direct involvement of clinicians. Objective smartphone-collected data may contain sufficient information about individuals' behaviors to infer their mental states and therefore screen for anxiety disorders and depression. Objective: The objective of this study is to compare how a single set of recognized and novel features, extracted from smartphone-collected data, can be used for predicting generalized anxiety disorder (GAD), social anxiety disorder (SAD), and depression. Methods: An Android app was designed, together with a centralized server system, to collect periodic measurements of objective smartphone data. The types of data included samples of ambient audio, GPS location, screen state, and light sensor data. Subjects were recruited into a 2-week observational study in which the app was run on their personal smartphones. The subjects also completed self-report severity measures of SAD, GAD, and depression. The participants were 112 Canadian adults from a nonclinical population. High-level features were extracted from the data of 84 participants, and predictive models of SAD, GAD, and depression were built and evaluated. Results: Models of SAD and depression achieved a significantly greater screening accuracy than uninformative models (area under the receiver operating characteristic means of 0.64, SD 0.13 and 0.72, SD 0.12, respectively), whereas models of GAD failed to be predictive. Investigation of the model coefficients revealed key features that were predictive of SAD and depression. Conclusions: We demonstrate the ability of a common set of features to act as predictors in the models of both SAD and depression. This suggests that the types of behaviors that can be inferred from smartphone-collected data are broad indicators of mental health, which can be used to study, assess, and track psychopathology simultaneously across multiple disorders and diagnostic boundaries. ",
doi="10.2196/28918",
url="https://www.jmir.org/2021/8/e28918",
url="http://www.ncbi.nlm.nih.gov/pubmed/34397386"
}


@Article{info:doi/10.2196/29840,
author="Zhang, Yuezhou
and Folarin, A. Amos
and Sun, Shaoxiong
and Cummins, Nicholas
and Ranjan, Yatharth
and Rashid, Zulqarnain
and Conde, Pauline
and Stewart, Callum
and Laiou, Petroula
and Matcham, Faith
and Oetzmann, Carolin
and Lamers, Femke
and Siddi, Sara
and Simblett, Sara
and Rintala, Aki
and Mohr, C. David
and Myin-Germeys, Inez
and Wykes, Til
and Haro, Maria Josep
and Penninx, H. Brenda W. J.
and Narayan, A. Vaibhav
and Annas, Peter
and Hotopf, Matthew
and Dobson, B. Richard J.
and ",
title="Predicting Depressive Symptom Severity Through Individuals' Nearby Bluetooth Device Count Data Collected by Mobile Phones: Preliminary Longitudinal Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Jul",
day="30",
volume="9",
number="7",
pages="e29840",
keywords="mental health",
keywords="depression",
keywords="digital biomarkers",
keywords="digital phenotyping",
keywords="digital health",
keywords="Bluetooth",
keywords="hierarchical Bayesian model",
keywords="mobile health",
keywords="mHealth",
keywords="monitoring",
abstract="Background: Research in mental health has found associations between depression and individuals' behaviors and statuses, such as social connections and interactions, working status, mobility, and social isolation and loneliness. These behaviors and statuses can be approximated by the nearby Bluetooth device count (NBDC) detected by Bluetooth sensors in mobile phones. Objective: This study aimed to explore the value of the NBDC data in predicting depressive symptom severity as measured via the 8-item Patient Health Questionnaire (PHQ-8). Methods: The data used in this paper included 2886 biweekly PHQ-8 records collected from 316 participants recruited from three study sites in the Netherlands, Spain, and the United Kingdom as part of the EU Remote Assessment of Disease and Relapse-Central Nervous System (RADAR-CNS) study. From the NBDC data 2 weeks prior to each PHQ-8 score, we extracted 49 Bluetooth features, including statistical features and nonlinear features for measuring the periodicity and regularity of individuals' life rhythms. Linear mixed-effect models were used to explore associations between Bluetooth features and the PHQ-8 score. We then applied hierarchical Bayesian linear regression models to predict the PHQ-8 score from the extracted Bluetooth features. Results: A number of significant associations were found between Bluetooth features and depressive symptom severity. Generally speaking, along with depressive symptom worsening, one or more of the following changes were found in the preceding 2 weeks of the NBDC data: (1) the amount decreased, (2) the variance decreased, (3) the periodicity (especially the circadian rhythm) decreased, and (4) the NBDC sequence became more irregular. Compared with commonly used machine learning models, the proposed hierarchical Bayesian linear regression model achieved the best prediction metrics (R2=0.526) and a root mean squared error (RMSE) of 3.891. Bluetooth features can explain an extra 18.8\% of the variance in the PHQ-8 score relative to the baseline model without Bluetooth features (R2=0.338, RMSE=4.547). Conclusions: Our statistical results indicate that the NBDC data have the potential to reflect changes in individuals' behaviors and statuses concurrent with the changes in the depressive state. The prediction results demonstrate that the NBDC data have a significant value in predicting depressive symptom severity. These findings may have utility for the mental health monitoring practice in real-world settings. ",
doi="10.2196/29840",
url="https://mhealth.jmir.org/2021/7/e29840",
url="http://www.ncbi.nlm.nih.gov/pubmed/34328441"
}


@Article{info:doi/10.2196/27343,
author="Martinez-Martin, Nicole
and Greely, T. Henry
and Cho, K. Mildred",
title="Ethical Development of Digital Phenotyping Tools for Mental Health Applications: Delphi Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Jul",
day="28",
volume="9",
number="7",
pages="e27343",
keywords="ethics",
keywords="neuroethics",
keywords="digital phenotyping",
keywords="digital mental health",
keywords="Delphi study",
keywords="mental health",
keywords="machine learning",
keywords="artificial intelligence",
keywords="mobile phone",
abstract="Background: Digital phenotyping (also known as personal sensing, intelligent sensing, or body computing) involves the collection of biometric and personal data in situ from digital devices, such as smartphones, wearables, or social media, to measure behavior or other health indicators. The collected data are analyzed to generate moment-by-moment quantification of a person's mental state and potentially predict future mental states. Digital phenotyping projects incorporate data from multiple sources, such as electronic health records, biometric scans, or genetic testing. As digital phenotyping tools can be used to study and predict behavior, they are of increasing interest for a range of consumer, government, and health care applications. In clinical care, digital phenotyping is expected to improve mental health diagnoses and treatment. At the same time, mental health applications of digital phenotyping present significant areas of ethical concern, particularly in terms of privacy and data protection, consent, bias, and accountability. Objective: This study aims to develop consensus statements regarding key areas of ethical guidance for mental health applications of digital phenotyping in the United States. Methods: We used a modified Delphi technique to identify the emerging ethical challenges posed by digital phenotyping for mental health applications and to formulate guidance for addressing these challenges. Experts in digital phenotyping, data science, mental health, law, and ethics participated as panelists in the study. The panel arrived at consensus recommendations through an iterative process involving interviews and surveys. The panelists focused primarily on clinical applications for digital phenotyping for mental health but also included recommendations regarding transparency and data protection to address potential areas of misuse of digital phenotyping data outside of the health care domain. Results: The findings of this study showed strong agreement related to these ethical issues in the development of mental health applications of digital phenotyping: privacy, transparency, consent, accountability, and fairness. Consensus regarding the recommendation statements was strongest when the guidance was stated broadly enough to accommodate a range of potential applications. The privacy and data protection issues that the Delphi participants found particularly critical to address related to the perceived inadequacies of current regulations and frameworks for protecting sensitive personal information and the potential for sale and analysis of personal data outside of health systems. Conclusions: The Delphi study found agreement on a number of ethical issues to prioritize in the development of digital phenotyping for mental health applications. The Delphi consensus statements identified general recommendations and principles regarding the ethical application of digital phenotyping to mental health. As digital phenotyping for mental health is implemented in clinical care, there remains a need for empirical research and consultation with relevant stakeholders to further understand and address relevant ethical issues. ",
doi="10.2196/27343",
url="https://mhealth.jmir.org/2021/7/e27343",
url="http://www.ncbi.nlm.nih.gov/pubmed/34319252"
}


@Article{info:doi/10.2196/23229,
author="Ingvaldsen, Hegna Sigrid
and Tronvik, Erling
and Brenner, Eiliv
and Winnberg, Ingunn
and Olsen, Alexander
and Gravdahl, Bruvik G{\o}ril
and Stubberud, Anker",
title="A Biofeedback App for Migraine: Development and Usability Study",
journal="JMIR Form Res",
year="2021",
month="Jul",
day="28",
volume="5",
number="7",
pages="e23229",
keywords="mHealth",
keywords="headache",
keywords="wearables",
keywords="smartphone",
abstract="Background: Biofeedback is effective in treating migraines. It is believed to have a beneficial effect on autonomous nervous system activity and render individuals resilient to stressors that may trigger a migraine. However, widespread use of biofeedback is hampered by the need for a trained therapist and specialized equipment. Emerging digital health technology, including smartphones and wearables (mHealth), enables new ways of administering biofeedback. Currently, mHealth interventions for migraine appear feasible, but development processes and usability testing remain insufficient. Objective: The objective of this study was to evaluate and improve the feasibility and usability of an mHealth biofeedback treatment app for adults with migraine. Methods: In a prospective development and usability study, 18 adults with migraine completed a 4-week testing period of self-administered therapist-independent biofeedback treatment consisting of a smartphone app connected to wearable sensors (Cerebri, Nordic Brain Tech AS). The app included biofeedback training, instructions for self-delivery, and a headache diary. Two wearable sensors were used to measure surface electromyographic voltage at the trapezius muscle and peripheral skin temperature and heart rate at the right second fingertip. Participants were instructed to complete a daily headache diary entry and biofeedback session of 10 minutes duration. The testing period was preceded by a preusability expectation interview and succeeded by a postusability experience interview. In addition, an evaluation questionnaire was completed at weeks 2 and 4. Adherence was calculated as the proportion of 10-minute sessions completed within the first 28 days of treatment. Usability and feasibility were analyzed and summarized quantitatively and qualitatively. Results: A total of 391 biofeedback sessions were completed with a median of 25 (IQR 17-28) per participant. The mean adherence rate was 0.76 (SD 0.26). The evaluation questionnaire revealed that functionality and design had the highest scores, whereas engagement and biofeedback were lower. Qualitative preexpectation analysis revealed that participants expected to become better familiar with physical signals and gain more understanding of their migraine attacks and noted that the app should be simple and understandable. Postusability analysis indicated that participants had an overall positive user experience with some suggestions for improvement regarding the design of the wearables and app content. The intervention was safe and tolerable. One case of prespecified adverse events was recorded in which a patient developed a skin rash from the sticky surface electromyography electrodes. Conclusions: The app underwent a rigorous development process that indicated an overall positive user experience, good usability, and high adherence rate. This study highlights the value of usability testing in the development of mHealth apps. ",
doi="10.2196/23229",
url="https://formative.jmir.org/2021/7/e23229",
url="http://www.ncbi.nlm.nih.gov/pubmed/34319243"
}


@Article{info:doi/10.2196/29191,
author="Tamura, Kosuke
and Curlin, Kaveri
and Neally, J. Sam
and Vijayakumar, P. Nithya
and Mitchell, M. Valerie
and Collins, S. Billy
and Gutierrez-Huerta, Cristhian
and Troendle, F. James
and Baumer, Yvonne
and Osei Baah, Foster
and Turner, S. Briana
and Gray, Veronica
and Tirado, A. Brian
and Ortiz-Chaparro, Erika
and Berrigan, David
and Mehta, N. Nehal
and Vaccarino, Viola
and Zenk, N. Shannon
and Powell-Wiley, M. Tiffany",
title="Geospatial Analysis of Neighborhood Environmental Stress in Relation to Biological Markers of Cardiovascular Health and Health Behaviors in Women: Protocol for a Pilot Study",
journal="JMIR Res Protoc",
year="2021",
month="Jul",
day="22",
volume="10",
number="7",
pages="e29191",
keywords="wearables",
keywords="global positioning system",
keywords="ecological momentary assessment",
keywords="accelerometer",
keywords="biomarkers of stress",
keywords="mobile phone",
abstract="Background: Innovative analyses of cardiovascular (CV) risk markers and health behaviors linked to neighborhood stressors are essential to further elucidate the mechanisms by which adverse neighborhood social conditions lead to poor CV outcomes. We propose to objectively measure physical activity (PA), sedentary behavior, and neighborhood stress using accelerometers, GPS, and real-time perceived ecological momentary assessment via smartphone apps and to link these to biological measures in a sample of White and African American women in Washington, DC, neighborhoods. Objective: The primary aim of this study is to test the hypothesis that living in adverse neighborhood social conditions is associated with higher stress-related neural activity among 60 healthy women living in high or low socioeconomic status neighborhoods in Washington, DC. Sub-aim 1 of this study is to test the hypothesis that the association is moderated by objectively measured PA using an accelerometer. A secondary objective is to test the hypothesis that residing in adverse neighborhood social environment conditions is related to differences in vascular function. Sub-aim 2 of this study is to test the hypothesis that the association is moderated by objectively measured PA. The third aim of this study is to test the hypothesis that adverse neighborhood social environment conditions are related to differences in immune system activation. Methods: The proposed study will be cross-sectional, with a sample of at least 60 women (30 healthy White women and 30 healthy Black women) from Wards 3 and 5 in Washington, DC. A sample of the women (n=30) will be recruited from high-income areas in Ward 3 from census tracts within a 15\% of Ward 3's range for median household income. The other participants (n=30) will be recruited from low-income areas in Wards 5 from census tracts within a 15\% of Ward 5's range for median household income. Finally, participants from Wards 3 and 5 will be matched based on age, race, and BMI. Participants will wear a GPS unit and accelerometer and report their stress and mood in real time using a smartphone. We will then examine the associations between GPS-derived neighborhood variables, stress-related neural activity measures, and adverse biological markers. Results: The National Institutes of Health Institutional Review Board has approved this study. Recruitment will begin in the summer of 2021. Conclusions: Findings from this research could inform the development of multilevel behavioral interventions and policies to better manage environmental factors that promote immune system activation or psychosocial stress while concurrently working to increase PA, thereby influencing CV health. International Registered Report Identifier (IRRID): PRR1-10.2196/29191 ",
doi="10.2196/29191",
url="https://www.researchprotocols.org/2021/7/e29191",
url="http://www.ncbi.nlm.nih.gov/pubmed/34292168"
}


@Article{info:doi/10.2196/26540,
author="Opoku Asare, Kennedy
and Terhorst, Yannik
and Vega, Julio
and Peltonen, Ella
and Lagerspetz, Eemil
and Ferreira, Denzil",
title="Predicting Depression From Smartphone Behavioral Markers Using Machine Learning Methods, Hyperparameter Optimization, and Feature Importance Analysis: Exploratory Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Jul",
day="12",
volume="9",
number="7",
pages="e26540",
keywords="mHealth",
keywords="mental health",
keywords="mobile phone",
keywords="digital biomarkers",
keywords="digital phenotyping",
keywords="smartphone",
keywords="supervised machine learning",
keywords="depression",
abstract="Background: Depression is a prevalent mental health challenge. Current depression assessment methods using self-reported and clinician-administered questionnaires have limitations. Instrumenting smartphones to passively and continuously collect moment-by-moment data sets to quantify human behaviors has the potential to augment current depression assessment methods for early diagnosis, scalable, and longitudinal monitoring of depression. Objective: The objective of this study was to investigate the feasibility of predicting depression with human behaviors quantified from smartphone data sets, and to identify behaviors that can influence depression. Methods: Smartphone data sets and self-reported 8-item Patient Health Questionnaire (PHQ-8) depression assessments were collected from 629 participants in an exploratory longitudinal study over an average of 22.1 days (SD 17.90; range 8-86). We quantified 22 regularity, entropy, and SD behavioral markers from the smartphone data. We explored the relationship between the behavioral features and depression using correlation and bivariate linear mixed models (LMMs). We leveraged 5 supervised machine learning (ML) algorithms with hyperparameter optimization, nested cross-validation, and imbalanced data handling to predict depression. Finally, with the permutation importance method, we identified influential behavioral markers in predicting depression. Results: Of the 629 participants from at least 56 countries, 69 (10.97\%) were females, 546 (86.8\%) were males, and 14 (2.2\%) were nonbinary. Participants' age distribution is as follows: 73/629 (11.6\%) were aged between 18 and 24, 204/629 (32.4\%) were aged between 25 and 34, 156/629 (24.8\%) were aged between 35 and 44, 166/629 (26.4\%) were aged between 45 and 64, and 30/629 (4.8\%) were aged 65 years and over. Of the 1374 PHQ-8 assessments, 1143 (83.19\%) responses were nondepressed scores (PHQ-8 score <10), while 231 (16.81\%) were depressed scores (PHQ-8 score ?10), as identified based on PHQ-8 cut-off. A significant positive Pearson correlation was found between screen status--normalized entropy and depression (r=0.14, P<.001). LMM demonstrates an intraclass correlation of 0.7584 and a significant positive association between screen status--normalized entropy and depression ($\beta$=.48, P=.03). The best ML algorithms achieved the following metrics: precision, 85.55\%-92.51\%; recall, 92.19\%-95.56\%; F1, 88.73\%-94.00\%; area under the curve receiver operating characteristic, 94.69\%-99.06\%; Cohen $\kappa$, 86.61\%-92.90\%; and accuracy, 96.44\%-98.14\%. Including age group and gender as predictors improved the ML performances. Screen and internet connectivity features were the most influential in predicting depression. Conclusions: Our findings demonstrate that behavioral markers indicative of depression can be unobtrusively identified from smartphone sensors' data. Traditional assessment of depression can be augmented with behavioral markers from smartphones for depression diagnosis and monitoring. ",
doi="10.2196/26540",
url="https://mhealth.jmir.org/2021/7/e26540",
url="http://www.ncbi.nlm.nih.gov/pubmed/34255713"
}


@Article{info:doi/10.2196/24543,
author="Caine, A. Joshua
and Klein, Britt
and Edwards, L. Stephen",
title="The Impact of a Novel Mimicry Task for Increasing Emotion Recognition in Adults with Autism Spectrum Disorder and Alexithymia: Protocol for a Randomized Controlled Trial",
journal="JMIR Res Protoc",
year="2021",
month="Jun",
day="17",
volume="10",
number="6",
pages="e24543",
keywords="alexithymia hypothesis",
keywords="training facial expression emotion recognition",
keywords="mimicry task",
keywords="autism spectrum disorder",
keywords="interoception",
keywords="facial expression",
keywords="emotion",
keywords="emotion recognition",
keywords="autism",
keywords="spectrum disorder",
keywords="mimicry",
keywords="therapy",
keywords="protocol",
keywords="expression",
keywords="disability",
abstract="Background: Impaired facial emotion expression recognition (FEER) has typically been considered a correlate of autism spectrum disorder (ASD). Now, the alexithymia hypothesis is suggesting that this emotion processing problem is instead related to alexithymia, which frequently co-occurs with ASD. By combining predictive coding theories of ASD and simulation theories of emotion recognition, it is suggested that facial mimicry may improve the training of FEER in ASD and alexithymia. Objective: This study aims to evaluate a novel mimicry task to improve FEER in adults with and without ASD and alexithymia. Additionally, this study will aim to determine the contributions of alexithymia and ASD to FEER ability and assess which of these 2 populations benefit from this training task. Methods: Recruitment will primarily take place through an ASD community group with emphasis put on snowball recruiting. Included will be 64 consenting adults equally divided between participants without an ASD and participants with an ASD. Participants will be screened online using the Kessler Psychological Distress Scale (K-10; cut-off score of 22), Autism Spectrum Quotient (AQ-10), and Toronto Alexithymia Scale (TAS-20) followed by a clinical interview with a provisional psychologist at the Federation University psychology clinic. The clinical interview will include assessment of ability, anxiety, and depression as well as discussion of past ASD diagnosis and confirmatory administration of the Autism Mental Status Exam (AMSE). Following the clinical interview, the participant will complete the Bermond-Vorst Alexithymia Questionnaire (BVAQ) and then undertake a baseline assessment of FEER. Consenting participants will then be assigned using a permuted blocked randomization method into either the control task condition or the mimicry task condition. A brief measure of satisfaction of the task and a debriefing session will conclude the study. Results: The study has Federation University Human Research Ethics Committee approval and is registered with the Australian New Zealand Clinical Trials. Participant recruitment is predicted to begin in the third quarter of 2021. Conclusions: This study will be the first to evaluate the use of a novel facial mimicry task condition to increase FEER in adults with ASD and alexithymia. If efficacious, this task could prove useful as a cost-effective adjunct intervention that could be used at home and thus remove barriers to entry. This study will also explore the unique effectiveness of this task in people without an ASD, with an ASD, and with alexithymia. Trial Registration: Australian New Zealand Clinical Trial Registry ACTRN12619000705189p; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=377455 International Registered Report Identifier (IRRID): PRR1-10.2196/24543 ",
doi="10.2196/24543",
url="https://www.researchprotocols.org/2021/6/e24543/",
url="http://www.ncbi.nlm.nih.gov/pubmed/34170257"
}


@Article{info:doi/10.2196/27218,
author="Kim, Meelim
and Yang, Jaeyeong
and Ahn, Woo-Young
and Choi, Jin Hyung",
title="Machine Learning Analysis to Identify Digital Behavioral Phenotypes for Engagement and Health Outcome Efficacy of an mHealth Intervention for Obesity: Randomized Controlled Trial",
journal="J Med Internet Res",
year="2021",
month="Jun",
day="24",
volume="23",
number="6",
pages="e27218",
keywords="digital phenotype",
keywords="clinical efficacy",
keywords="in-app engagement",
keywords="machine learning analysis",
keywords="mobile phone",
abstract="Background: The digital health care community has been urged to enhance engagement and clinical outcomes by analyzing multidimensional digital phenotypes. Objective: This study aims to use a machine learning approach to investigate the performance of multivariate phenotypes in predicting the engagement rate and health outcomes of digital cognitive behavioral therapy. Methods: We leveraged both conventional phenotypes assessed by validated psychological questionnaires and multidimensional digital phenotypes within time-series data from a mobile app of 45 participants undergoing digital cognitive behavioral therapy for 8 weeks. We conducted a machine learning analysis to discriminate the important characteristics. Results: A higher engagement rate was associated with higher weight loss at 8 weeks (r=?0.59; P<.001) and 24 weeks (r=?0.52; P=.001). Applying the machine learning approach, lower self-esteem on the conventional phenotype and higher in-app motivational measures on digital phenotypes commonly accounted for both engagement and health outcomes. In addition, 16 types of digital phenotypes (ie, lower intake of high-calorie food and evening snacks and higher interaction frequency with mentors) predicted engagement rates (mean R2 0.416, SD 0.006). The prediction of short-term weight change (mean R2 0.382, SD 0.015) was associated with 13 different digital phenotypes (ie, lower intake of high-calorie food and carbohydrate and higher intake of low-calorie food). Finally, 8 measures of digital phenotypes (ie, lower intake of carbohydrate and evening snacks and higher motivation) were associated with a long-term weight change (mean R2 0.590, SD 0.011). Conclusions: Our findings successfully demonstrated how multiple psychological constructs, such as emotional, cognitive, behavioral, and motivational phenotypes, elucidate the mechanisms and clinical efficacy of a digital intervention using the machine learning method. Accordingly, our study designed an interpretable digital phenotype model, including multiple aspects of motivation before and during the intervention, predicting both engagement and clinical efficacy. This line of research may shed light on the development of advanced prevention and personalized digital therapeutics. Trial Registration: ClinicalTrials.gov NCT03465306; https://clinicaltrials.gov/ct2/show/NCT03465306 ",
doi="10.2196/27218",
url="https://www.jmir.org/2021/6/e27218/",
url="http://www.ncbi.nlm.nih.gov/pubmed/34184991"
}


@Article{info:doi/10.2196/24666,
author="Sch{\"u}tz, Narayan
and Saner, Hugo
and Botros, Angela
and Pais, Bruno
and Santschi, Val{\'e}rie
and Buluschek, Philipp
and Gatica-Perez, Daniel
and Urwyler, Prabitha
and M{\"u}ri, M. Ren{\'e}
and Nef, Tobias",
title="Contactless Sleep Monitoring for Early Detection of Health Deteriorations in Community-Dwelling Older Adults: Exploratory Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Jun",
day="11",
volume="9",
number="6",
pages="e24666",
keywords="sleep restlessness",
keywords="telemonitoring",
keywords="digital biomarkers",
keywords="contactless sensing",
keywords="pervasive computing",
keywords="home-monitoring",
keywords="older adults",
keywords="toss and turns",
keywords="sleep monitoring",
keywords="body movements in bed",
abstract="Background: Population aging is posing multiple social and economic challenges to society. One such challenge is the social and economic burden related to increased health care expenditure caused by early institutionalizations. The use of modern pervasive computing technology makes it possible to continuously monitor the health status of community-dwelling older adults at home. Early detection of health issues through these technologies may allow for reduced treatment costs and initiation of targeted preventive measures leading to better health outcomes. Sleep is a key factor when it comes to overall health and many health issues manifest themselves with associated sleep deteriorations. Sleep quality and sleep disorders such as sleep apnea syndrome have been extensively studied using various wearable devices at home or in the setting of sleep laboratories. However, little research has been conducted evaluating the potential of contactless and continuous sleep monitoring in detecting early signs of health problems in community-dwelling older adults. Objective: In this work we aim to evaluate which contactlessly measurable sleep parameter is best suited to monitor perceived and actual health status changes in older adults. Methods: We analyzed real-world longitudinal (up to 1 year) data from 37 community-dwelling older adults including more than 6000 nights of measured sleep. Sleep parameters were recorded by a pressure sensor placed beneath the mattress, and corresponding health status information was acquired through weekly questionnaires and reports by health care personnel. A total of 20 sleep parameters were analyzed, including common sleep metrics such as sleep efficiency, sleep onset delay, and sleep stages but also vital signs in the form of heart and breathing rate as well as movements in bed. Association with self-reported health, evaluated by EuroQol visual analog scale (EQ-VAS) ratings, were quantitatively evaluated using individual linear mixed-effects models. Translation to objective, real-world health incidents was investigated through manual retrospective case-by-case analysis. Results: Using EQ-VAS rating based self-reported perceived health, we identified body movements in bed---measured by the number toss-and-turn events---as the most predictive sleep parameter (t score=--0.435, P value [adj]=<.001). Case-by-case analysis further substantiated this finding, showing that increases in number of body movements could often be explained by reported health incidents. Real world incidents included heart failure, hypertension, abdominal tumor, seasonal flu, gastrointestinal problems, and urinary tract infection. Conclusions: Our results suggest that nightly body movements in bed could potentially be a highly relevant as well as easy to interpret and derive digital biomarker to monitor a wide range of health deteriorations in older adults. As such, it could help in detecting health deteriorations early on and provide timelier, more personalized, and precise treatment options. ",
doi="10.2196/24666",
url="https://mhealth.jmir.org/2021/6/e24666",
url="http://www.ncbi.nlm.nih.gov/pubmed/34114966"
}


@Article{info:doi/10.2196/23130,
author="Kim, Heon Ho
and An, Il Jae
and Park, Rang Yu",
title="A Prediction Model for Detecting Developmental Disabilities in Preschool-Age Children Through Digital Biomarker-Driven Deep Learning in Serious Games: Development Study",
journal="JMIR Serious Games",
year="2021",
month="Jun",
day="4",
volume="9",
number="2",
pages="e23130",
keywords="developmental delay",
keywords="diagnosis prediction",
keywords="deep learning",
keywords="serious games",
keywords="digital health",
keywords="digital phenotyping",
keywords="digital biomarkers",
abstract="Background: Early detection of developmental disabilities in children is essential because early intervention can improve the prognosis of children. Meanwhile, a growing body of evidence has indicated a relationship between developmental disability and motor skill, and thus, motor skill is considered in the early diagnosis of developmental disability. However, there are challenges to assessing motor skill in the diagnosis of developmental disorder, such as a lack of specialists and time constraints, and thus it is commonly conducted through informal questions or surveys to parents. Objective: This study sought to evaluate the possibility of using drag-and-drop data as a digital biomarker and to develop a classification model based on drag-and-drop data with which to classify children with developmental disabilities. Methods: We collected drag-and-drop data from children with typical development and developmental disabilities from May 1, 2018, to May 1, 2020, via a mobile application (DoBrain). We used touch coordinates and extracted kinetic variables from these coordinates. A deep learning algorithm was developed to predict potential development disabilities in children. For interpretability of the model results, we identified which coordinates contributed to the classification results by applying gradient-weighted class activation mapping. Results: Of the 370 children in the study, 223 had typical development, and 147 had developmental disabilities. In all games, the number of changes in the acceleration sign based on the direction of progress both in the x- and y-axes showed significant differences between the 2 groups (P<.001; effect size >0.5). The deep learning convolutional neural network model showed that drag-and-drop data can help diagnose developmental disabilities, with an area under the receiving operating characteristics curve of 0.817. A gradient class activation map, which can interpret the results of a deep learning model, was visualized with the game results for specific children. Conclusions: Through the results of the deep learning model, we confirmed that drag-and-drop data can be a new digital biomarker for the diagnosis of developmental disabilities. ",
doi="10.2196/23130",
url="https://games.jmir.org/2021/2/e23130",
url="http://www.ncbi.nlm.nih.gov/pubmed/34085944"
}


@Article{info:doi/10.2196/25199,
author="Galatzer-Levy, Isaac
and Abbas, Anzar
and Ries, Anja
and Homan, Stephanie
and Sels, Laura
and Koesmahargyo, Vidya
and Yadav, Vijay
and Colla, Michael
and Scheerer, Hanne
and Vetter, Stefan
and Seifritz, Erich
and Scholz, Urte
and Kleim, Birgit",
title="Validation of Visual and Auditory Digital Markers of Suicidality in Acutely Suicidal Psychiatric Inpatients: Proof-of-Concept Study",
journal="J Med Internet Res",
year="2021",
month="Jun",
day="3",
volume="23",
number="6",
pages="e25199",
keywords="digital phenotyping",
keywords="digital biomarkers",
keywords="digital health",
keywords="depression",
keywords="suicidal ideation",
keywords="digital markers",
keywords="digital",
keywords="facial",
keywords="suicide",
keywords="suicide risk",
keywords="visual",
keywords="auditory",
abstract="Background: Multiple symptoms of suicide risk have been assessed based on visual and auditory information, including flattened affect, reduced movement, and slowed speech. Objective quantification of such symptomatology from novel data sources can increase the sensitivity, scalability, and timeliness of suicide risk assessment. Objective: We aimed to examine measurements extracted from video interviews using open-source deep learning algorithms to quantify facial, vocal, and movement behaviors in relation to suicide risk severity in recently admitted patients following a suicide attempt. Methods: We utilized video to quantify facial, vocal, and movement markers associated with mood, emotion, and motor functioning from a structured clinical conversation in 20 patients admitted to a psychiatric hospital following a suicide risk attempt. Measures were calculated using open-source deep learning algorithms for processing facial expressivity, head movement, and vocal characteristics. Derived digital measures of flattened affect, reduced movement, and slowed speech were compared to suicide risk with the Beck Scale for Suicide Ideation controlling for age and sex, using multiple linear regression. Results: Suicide severity was associated with multiple visual and auditory markers, including speech prevalence ($\beta$=?0.68, P=.02, r2=0.40), overall expressivity ($\beta$=?0.46, P=.10, r2=0.27), and head movement measured as head pitch variability ($\beta$=?1.24, P=.006, r2=0.48) and head yaw variability ($\beta$=?0.54, P=.06, r2=0.32). Conclusions: Digital measurements of facial affect, movement, and speech prevalence demonstrated strong effect sizes and linear associations with the severity of suicidal ideation. ",
doi="10.2196/25199",
url="https://www.jmir.org/2021/6/e25199",
url="http://www.ncbi.nlm.nih.gov/pubmed/34081022"
}


@Article{info:doi/10.2196/23461,
author="Ibrahim, Ahmed
and Zhang, Heng
and Clinch, Sarah
and Poliakoff, Ellen
and Parsia, Bijan
and Harper, Simon",
title="Digital Phenotypes for Understanding Individuals' Compliance With COVID-19 Policies and Personalized Nudges: Longitudinal Observational Study",
journal="JMIR Form Res",
year="2021",
month="May",
day="27",
volume="5",
number="5",
pages="e23461",
keywords="behavior",
keywords="compliance",
keywords="COVID-19",
keywords="digital phenotyping",
keywords="nudges",
keywords="personalization",
keywords="policy",
keywords="sensor",
keywords="smartphone",
abstract="Background: Governments promote behavioral policies such as social distancing and phased reopening to control the spread of COVID-19. Digital phenotyping helps promote the compliance with these policies through the personalized behavioral knowledge it produces. Objective: This study investigated the value of smartphone-derived digital phenotypes in (1) analyzing individuals' compliance with COVID-19 policies through behavioral responses and (2) suggesting ways to personalize communication through those policies. Methods: We conducted longitudinal experiments that started before the outbreak of COVID-19 and continued during the pandemic. A total of 16 participants were recruited before the pandemic, and a smartphone sensing app was installed for each of them. We then assessed individual compliance with COVID-19 policies and their impact on habitual behaviors. Results: Our results show a significant change in people's mobility (P<.001) as a result of COVID-19 regulations, from an average of 10 visited places every week to approximately 2 places a week. We also discussed our results within the context of nudges used by the National Health Service in the United Kingdom to promote COVID-19 regulations. Conclusions: Our findings show that digital phenotyping has substantial value in understanding people's behavior during a pandemic. Behavioral features extracted from digital phenotypes can facilitate the personalization of and compliance with behavioral policies. A rule-based messaging system can be implemented to deliver nudges on the basis of digital phenotyping. ",
doi="10.2196/23461",
url="https://formative.jmir.org/2021/5/e23461",
url="http://www.ncbi.nlm.nih.gov/pubmed/33999832"
}


@Article{info:doi/10.2196/27271,
author="Larimer, Karen
and Wegerich, Stephan
and Splan, Joel
and Chestek, David
and Prendergast, Heather
and Vanden Hoek, Terry",
title="Personalized Analytics and a Wearable Biosensor Platform for Early Detection of COVID-19 Decompensation (DeCODe): Protocol for the Development of the COVID-19 Decompensation Index",
journal="JMIR Res Protoc",
year="2021",
month="May",
day="26",
volume="10",
number="5",
pages="e27271",
keywords="analytic",
keywords="artificial intelligence",
keywords="biomarker",
keywords="cloud",
keywords="COVID-19",
keywords="decompensation",
keywords="detection",
keywords="development",
keywords="index",
keywords="monitoring",
keywords="outcome",
keywords="remote monitoring",
keywords="symptom validation",
keywords="wearable",
abstract="Background: During the COVID-19 pandemic, novel digital health technologies have the potential to improve our understanding of SARS-CoV-2 and COVID-19, improve care delivery, and produce better health outcomes. The National Institutes of Health called on digital health leaders to contribute to a high-quality data repository that will support researchers to make discoveries that are otherwise not possible with small, limited data sets. Objective: To this end, we seek to develop a COVID-19 digital biomarker for early detection of physiological exacerbation or decompensation. We propose the development and validation of a COVID-19 decompensation Index (CDI) in a 2-phase study that builds on existing wearable biosensor-derived analytics generated by physIQ's end-to-end cloud platform for continuous physiological monitoring with wearable biosensors. This effort serves to achieve two primary objectives: (1) to collect adequate data to help develop the CDI and (2) to collect rich deidentified clinical data correlating with outcomes and symptoms related to COVID-19 progression. Our secondary objectives include evaluation of the feasibility and usability of pinpointIQ, a digital platform through which data are gathered, analyzed, and displayed. Methods: This is a prospective, nonrandomized, open-label, 2-phase study. Phase I will involve data collection for the digital data hub of the National Institutes of Health as well as data to support the preliminary development of the CDI. Phase II will involve data collection for the hub and contribute to continued refinement and validation of the CDI. While this study will focus on the development of a CDI, the digital platform will also be evaluated for feasibility and usability while clinicians deliver care to continuously monitored patients enrolled in the study. Results: Our target CDI will be a binary classifier trained to distinguish participants with and those without decompensation. The primary performance metric for CDI will be the area under the receiver operating characteristic curve with a minimum performance criterion of ?0.75 ($\alpha$=.05; power [1--$\beta$]=0.80). Furthermore, we will determine the sex or gender and race or ethnicity of the participants, which would account for differences in the CDI performance, as well as the lead time---time to predict decompensation---and its relationship with the ultimate disease severity based on the World Health Organization COVID-19 ordinal scale. Conclusions: Using machine learning techniques on a large data set of patients with COVID-19 could provide valuable insights into the pathophysiology of COVID-19 and a digital biomarker for COVID-19 decompensation. Through this study, we intend to develop a tool that can uniquely reflect physiological data of a diverse population and contribute to high-quality data that will help researchers better understand COVID-19. Trial Registration: ClinicalTrials.gov NCT04575532; https://www.clinicaltrials.gov/ct2/show/NCT04575532 International Registered Report Identifier (IRRID): DERR1-10.2196/27271 ",
doi="10.2196/27271",
url="https://www.researchprotocols.org/2021/5/e27271",
url="http://www.ncbi.nlm.nih.gov/pubmed/33949966"
}


@Article{info:doi/10.2196/24348,
author="Oladeji, Olubusola
and Zhang, Chi
and Moradi, Tiam
and Tarapore, Dharmesh
and Stokes, C. Andrew
and Marivate, Vukosi
and Sengeh, D. Moinina
and Nsoesie, O. Elaine",
title="Monitoring Information-Seeking Patterns and Obesity Prevalence in Africa With Internet Search Data: Observational Study",
journal="JMIR Public Health Surveill",
year="2021",
month="Apr",
day="29",
volume="7",
number="4",
pages="e24348",
keywords="obesity",
keywords="overweight",
keywords="Africa",
keywords="chronic diseases",
keywords="hypertension",
keywords="digital phenotype",
keywords="infodemiology",
keywords="infoveillance",
abstract="Background: The prevalence of chronic conditions such as obesity, hypertension, and diabetes is increasing in African countries. Many chronic diseases have been linked to risk factors such as poor diet and physical inactivity. Data for these behavioral risk factors are usually obtained from surveys, which can be delayed by years. Behavioral data from digital sources, including social media and search engines, could be used for timely monitoring of behavioral risk factors. Objective: The objective of our study was to propose the use of digital data from internet sources for monitoring changes in behavioral risk factors in Africa. Methods: We obtained the adjusted volume of search queries submitted to Google for 108 terms related to diet, exercise, and disease from 2010 to 2016. We also obtained the obesity and overweight prevalence for 52 African countries from the World Health Organization (WHO) for the same period. Machine learning algorithms (ie, random forest, support vector machine, Bayes generalized linear model, gradient boosting, and an ensemble of the individual methods) were used to identify search terms and patterns that correlate with changes in obesity and overweight prevalence across Africa. Out-of-sample predictions were used to assess and validate the model performance. Results: The study included 52 African countries. In 2016, the WHO reported an overweight prevalence ranging from 20.9\% (95\% credible interval [CI] 17.1\%-25.0\%) to 66.8\% (95\% CI 62.4\%-71.0\%) and an obesity prevalence ranging from 4.5\% (95\% CI 2.9\%-6.5\%) to 32.5\% (95\% CI 27.2\%-38.1\%) in Africa. The highest obesity and overweight prevalence were noted in the northern and southern regions. Google searches for diet-, exercise-, and obesity-related terms explained 97.3\% (root-mean-square error [RMSE] 1.15) of the variation in obesity prevalence across all 52 countries. Similarly, the search data explained 96.6\% (RMSE 2.26) of the variation in the overweight prevalence. The search terms yoga, exercise, and gym were most correlated with changes in obesity and overweight prevalence in countries with the highest prevalence. Conclusions: Information-seeking patterns for diet- and exercise-related terms could indicate changes in attitudes toward and engagement in risk factors or healthy behaviors. These trends could capture population changes in risk factor prevalence, inform digital and physical interventions, and supplement official data from surveys. ",
doi="10.2196/24348",
url="https://publichealth.jmir.org/2021/4/e24348",
url="http://www.ncbi.nlm.nih.gov/pubmed/33913815"
}


@Article{info:doi/10.2196/27975,
author="Low, A. Carissa
and Li, Meng
and Vega, Julio
and Durica, C. Krina
and Ferreira, Denzil
and Tam, Vernissia
and Hogg, Melissa
and Zeh III, Herbert
and Doryab, Afsaneh
and Dey, K. Anind",
title="Digital Biomarkers of Symptom Burden Self-Reported by Perioperative Patients Undergoing Pancreatic Surgery: Prospective Longitudinal Study",
journal="JMIR Cancer",
year="2021",
month="Apr",
day="27",
volume="7",
number="2",
pages="e27975",
keywords="mobile sensing",
keywords="symptom",
keywords="cancer",
keywords="surgery",
keywords="wearable device",
keywords="smartphone",
keywords="mobile phone",
abstract="Background: Cancer treatments can cause a variety of symptoms that impair quality of life and functioning but are frequently missed by clinicians. Smartphone and wearable sensors may capture behavioral and physiological changes indicative of symptom burden, enabling passive and remote real-time monitoring of fluctuating symptoms Objective: The aim of this study was to examine whether smartphone and Fitbit data could be used to estimate daily symptom burden before and after pancreatic surgery. Methods: A total of 44 patients scheduled for pancreatic surgery participated in this prospective longitudinal study and provided sufficient sensor and self-reported symptom data for analyses. Participants collected smartphone sensor and Fitbit data and completed daily symptom ratings starting at least two weeks before surgery, throughout their inpatient recovery, and for up to 60 days after postoperative discharge. Day-level behavioral features reflecting mobility and activity patterns, sleep, screen time, heart rate, and communication were extracted from raw smartphone and Fitbit data and used to classify the next day as high or low symptom burden, adjusted for each individual's typical level of reported symptoms. In addition to the overall symptom burden, we examined pain, fatigue, and diarrhea specifically. Results: Models using light gradient boosting machine (LightGBM) were able to correctly predict whether the next day would be a high symptom day with 73.5\% accuracy, surpassing baseline models. The most important sensor features for discriminating high symptom days were related to physical activity bouts, sleep, heart rate, and location. LightGBM models predicting next-day diarrhea (79.0\% accuracy), fatigue (75.8\% accuracy), and pain (79.6\% accuracy) performed similarly. Conclusions: Results suggest that digital biomarkers may be useful in predicting patient-reported symptom burden before and after cancer surgery. Although model performance in this small sample may not be adequate for clinical implementation, findings support the feasibility of collecting mobile sensor data from older patients who are acutely ill as well as the potential clinical value of mobile sensing for passive monitoring of patients with cancer and suggest that data from devices that many patients already own and use may be useful in detecting worsening perioperative symptoms and triggering just-in-time symptom management interventions. ",
doi="10.2196/27975",
url="https://cancer.jmir.org/2021/2/e27975",
url="http://www.ncbi.nlm.nih.gov/pubmed/33904822"
}


@Article{info:doi/10.2196/20996,
author="Jagesar, R. Raj
and Vorstman, A. Jacob
and Kas, J. Martien",
title="Requirements and Operational Guidelines for Secure and Sustainable Digital Phenotyping: Design and Development Study",
journal="J Med Internet Res",
year="2021",
month="Apr",
day="7",
volume="23",
number="4",
pages="e20996",
keywords="digital phenotyping",
keywords="mobile behavioral monitoring",
keywords="passive behavioral monitoring",
keywords="smartphone-based behavioral monitoring",
keywords="research data management",
keywords="psychoinformatics",
keywords="mobile phone",
abstract="Background: Digital phenotyping, the measurement of human behavioral phenotypes using personal devices, is rapidly gaining popularity. Novel initiatives, ranging from software prototypes to user-ready research platforms, are innovating the field of biomedical research and health care apps. One example is the BEHAPP project, which offers a fully managed digital phenotyping platform as a service. The innovative potential of digital phenotyping strategies resides among others in their capacity to objectively capture measurable and quantitative components of human behavior, such as diurnal rhythm, movement patterns, and communication, in a real-world setting. The rapid development of this field underscores the importance of reliability and safety of the platforms on which these novel tools are operated. Large-scale studies and regulated research spaces (eg, the pharmaceutical industry) have strict requirements for the software-based solutions they use. Security and sustainability are key to ensuring continuity and trust. However, the majority of behavioral monitoring initiatives have not originated primarily in these regulated research spaces, which may be why these components have been somewhat overlooked, impeding the further development and implementation of such platforms in a secure and sustainable way. Objective: This study aims to provide a primer on the requirements and operational guidelines for the development and operation of a secure behavioral monitoring platform. Methods: We draw from disciplines such as privacy law, information, and computer science to identify a set of requirements and operational guidelines focused on security and sustainability. Taken together, the requirements and guidelines form the foundation of the design and implementation of the BEHAPP behavioral monitoring platform. Results: We present the base BEHAPP data collection and analysis flow and explain how the various concepts from security and sustainability are addressed in the design. Conclusions: Digital phenotyping initiatives are steadily maturing. This study helps the field and surrounding stakeholders to reflect upon and progress toward secure and sustainable operation of digital phenotyping--driven research. ",
doi="10.2196/20996",
url="https://www.jmir.org/2021/4/e20996",
url="http://www.ncbi.nlm.nih.gov/pubmed/33825695"
}


@Article{info:doi/10.2196/27121,
author="Banholzer, Nicolas
and Feuerriegel, Stefan
and Fleisch, Elgar
and Bauer, Friedrich Georg
and Kowatsch, Tobias",
title="Computer Mouse Movements as an Indicator of Work Stress: Longitudinal Observational Field Study",
journal="J Med Internet Res",
year="2021",
month="Apr",
day="2",
volume="23",
number="4",
pages="e27121",
keywords="work stress",
keywords="psychological stress",
keywords="stress indicator",
keywords="computer mouse movements",
keywords="human-computer interactions",
abstract="Background: Work stress affects individual health and well-being. These negative effects could be mitigated through regular monitoring of employees' stress. Such monitoring becomes even more important as the digital transformation of the economy implies profound changes in working conditions. Objective: The goal of this study was to investigate the association between computer mouse movements and work stress in the field. Methods: We hypothesized that stress is associated with a speed-accuracy trade-off in computer mouse movements. To test this hypothesis, we conducted a longitudinal field study at a large business organization, where computer mouse movements from regular work activities were monitored over 7 weeks; the study included 70 subjects and 1829 observations. A Bayesian regression model was used to estimate whether self-reported acute work stress was associated with a speed-accuracy trade-off in computer mouse movements. Results: There was a negative association between stress and the two-way interaction term of mouse speed and accuracy (mean ?0.32, 95\% highest posterior density interval ?0.58 to ?0.08), which means that stress was associated with a speed-accuracy trade-off. The estimated association was not sensitive to different processing of the data and remained negative after controlling for the demographics, health, and personality traits of subjects. Conclusions: Self-reported acute stress is associated with computer mouse movements, specifically in the form of a speed-accuracy trade-off. This finding suggests that the regular analysis of computer mouse movements could indicate work stress. ",
doi="10.2196/27121",
url="https://www.jmir.org/2021/4/e27121",
url="http://www.ncbi.nlm.nih.gov/pubmed/33632675"
}


@Article{info:doi/10.2196/24465,
author="S{\"u}kei, Emese
and Norbury, Agnes
and Perez-Rodriguez, Mercedes M.
and Olmos, M. Pablo
and Art{\'e}s, Antonio",
title="Predicting Emotional States Using Behavioral Markers Derived From Passively Sensed Data: Data-Driven Machine Learning Approach",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Mar",
day="22",
volume="9",
number="3",
pages="e24465",
keywords="mental health",
keywords="affect",
keywords="mobile health",
keywords="mobile phone",
keywords="digital phenotype",
keywords="machine learning",
keywords="Bayesian analysis",
keywords="probabilistic models",
keywords="personalized models",
abstract="Background: Mental health disorders affect multiple aspects of patients' lives, including mood, cognition, and behavior. eHealth and mobile health (mHealth) technologies enable rich sets of information to be collected noninvasively, representing a promising opportunity to construct behavioral markers of mental health. Combining such data with self-reported information about psychological symptoms may provide a more comprehensive and contextualized view of a patient's mental state than questionnaire data alone. However, mobile sensed data are usually noisy and incomplete, with significant amounts of missing observations. Therefore, recognizing the clinical potential of mHealth tools depends critically on developing methods to cope with such data issues. Objective: This study aims to present a machine learning--based approach for emotional state prediction that uses passively collected data from mobile phones and wearable devices and self-reported emotions. The proposed methods must cope with high-dimensional and heterogeneous time-series data with a large percentage of missing observations. Methods: Passively sensed behavior and self-reported emotional state data from a cohort of 943 individuals (outpatients recruited from community clinics) were available for analysis. All patients had at least 30 days' worth of naturally occurring behavior observations, including information about physical activity, geolocation, sleep, and smartphone app use. These regularly sampled but frequently missing and heterogeneous time series were analyzed with the following probabilistic latent variable models for data averaging and feature extraction: mixture model (MM) and hidden Markov model (HMM). The extracted features were then combined with a classifier to predict emotional state. A variety of classical machine learning methods and recurrent neural networks were compared. Finally, a personalized Bayesian model was proposed to improve performance by considering the individual differences in the data and applying a different classifier bias term for each patient. Results: Probabilistic generative models proved to be good preprocessing and feature extractor tools for data with large percentages of missing observations. Models that took into account the posterior probabilities of the MM and HMM latent states outperformed those that did not by more than 20\%, suggesting that the underlying behavioral patterns identified were meaningful for individuals' overall emotional state. The best performing generalized models achieved a 0.81 area under the curve of the receiver operating characteristic and 0.71 area under the precision-recall curve when predicting self-reported emotional valence from behavior in held-out test data. Moreover, the proposed personalized models demonstrated that accounting for individual differences through a simple hierarchical model can substantially improve emotional state prediction performance without relying on previous days' data. Conclusions: These findings demonstrate the feasibility of designing machine learning models for predicting emotional states from mobile sensing data capable of dealing with heterogeneous data with large numbers of missing observations. Such models may represent valuable tools for clinicians to monitor patients' mood states. ",
doi="10.2196/24465",
url="https://mhealth.jmir.org/2021/3/e24465",
url="http://www.ncbi.nlm.nih.gov/pubmed/33749612"
}


@Article{info:doi/10.2196/23364,
author="Lam, Benjamin
and Catt, Michael
and Cassidy, Sophie
and Bacardit, Jaume
and Darke, Philip
and Butterfield, Sam
and Alshabrawy, Ossama
and Trenell, Michael
and Missier, Paolo",
title="Using Wearable Activity Trackers to Predict Type 2 Diabetes: Machine Learning--Based Cross-sectional Study of the UK Biobank Accelerometer Cohort",
journal="JMIR Diabetes",
year="2021",
month="Mar",
day="19",
volume="6",
number="1",
pages="e23364",
keywords="accelerometry",
keywords="digital technology",
keywords="machine learning",
keywords="physical activity",
keywords="type 2 diabetes",
keywords="digital biomarkers",
keywords="digital phenotyping",
keywords="mobile phone",
abstract="Background: Between 2013 and 2015, the UK Biobank collected accelerometer traces from 103,712 volunteers aged between 40 and 69 years using wrist-worn triaxial accelerometers for 1 week. This data set has been used in the past to verify that individuals with chronic diseases exhibit reduced activity levels compared with healthy populations. However, the data set is likely to be noisy, as the devices were allocated to participants without a set of inclusion criteria, and the traces reflect free-living conditions. Objective: This study aims to determine the extent to which accelerometer traces can be used to distinguish individuals with type 2 diabetes (T2D) from normoglycemic controls and to quantify their limitations. Methods: Machine learning classifiers were trained using different feature sets to segregate individuals with T2D from normoglycemic individuals. Multiple criteria, based on a combination of self-assessment UK Biobank variables and primary care health records linked to UK Biobank participants, were used to identify 3103 individuals with T2D in this population. The remaining nondiabetic 19,852 participants were further scored on their physical activity impairment severity based on other conditions found in their primary care data, and those deemed likely physically impaired at the time were excluded. Physical activity features were first extracted from the raw accelerometer traces data set for each participant using an algorithm that extends the previously developed Biobank Accelerometry Analysis toolkit from Oxford University. These features were complemented by a selected collection of sociodemographic and lifestyle features available from UK Biobank. Results: We tested 3 types of classifiers, with an area under the receiver operating characteristic curve (AUC) close to 0.86 (95\% CI 0.85-0.87) for all 3 classifiers and F1 scores in the range of 0.80-0.82 for T2D-positive individuals and 0.73-0.74 for T2D-negative controls. Results obtained using nonphysically impaired controls were compared with highly physically impaired controls to test the hypothesis that nondiabetic conditions reduce classifier performance. Models built using a training set that included highly impaired controls with other conditions had worse performance (AUC 0.75-0.77; 95\% CI 0.74-0.78; F1 scores in the range of 0.76-0.77 for T2D positives and 0.63-0.65 for controls). Conclusions: Granular measures of free-living physical activity can be used to successfully train machine learning models that are able to discriminate between individuals with T2D and normoglycemic controls, although with limitations because of the intrinsic noise in the data sets. From a broader clinical perspective, these findings motivate further research into the use of physical activity traces as a means of screening individuals at risk of diabetes and for early detection, in conjunction with routinely used risk scores, provided that appropriate quality control is enforced on the data collection protocol. ",
doi="10.2196/23364",
url="https://diabetes.jmir.org/2021/1/e23364",
url="http://www.ncbi.nlm.nih.gov/pubmed/33739298"
}


@Article{info:doi/10.2196/23984,
author="Wang, Xuancong
and Vouk, Nikola
and Heaukulani, Creighton
and Buddhika, Thisum
and Martanto, Wijaya
and Lee, Jimmy
and Morris, JT Robert",
title="HOPES: An Integrative Digital Phenotyping Platform for Data Collection, Monitoring, and Machine Learning",
journal="J Med Internet Res",
year="2021",
month="Mar",
day="15",
volume="23",
number="3",
pages="e23984",
keywords="digital phenotyping",
keywords="eHealth",
keywords="mHealth",
keywords="mobile phone",
keywords="phenotype",
keywords="data collection",
keywords="outpatient monitoring",
keywords="machine learning",
doi="10.2196/23984",
url="https://www.jmir.org/2021/3/e23984",
url="http://www.ncbi.nlm.nih.gov/pubmed/33720028"
}


@Article{info:doi/10.2196/24365,
author="Bai, Ran
and Xiao, Le
and Guo, Yu
and Zhu, Xuequan
and Li, Nanxi
and Wang, Yashen
and Chen, Qinqin
and Feng, Lei
and Wang, Yinghua
and Yu, Xiangyi
and Wang, Chunxue
and Hu, Yongdong
and Liu, Zhandong
and Xie, Haiyong
and Wang, Gang",
title="Tracking and Monitoring Mood Stability of Patients With Major Depressive Disorder by Machine Learning Models Using Passive Digital Data: Prospective Naturalistic Multicenter Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Mar",
day="8",
volume="9",
number="3",
pages="e24365",
keywords="digital phenotype",
keywords="major depressive disorder",
keywords="machine learning",
keywords="mobile phone",
abstract="Background: Major depressive disorder (MDD) is a common mental illness characterized by persistent sadness and a loss of interest in activities. Using smartphones and wearable devices to monitor the mental condition of patients with MDD has been examined in several studies. However, few studies have used passively collected data to monitor mood changes over time. Objective: The aim of this study is to examine the feasibility of monitoring mood status and stability of patients with MDD using machine learning models trained by passively collected data, including phone use data, sleep data, and step count data. Methods: We constructed 950 data samples representing time spans during three consecutive Patient Health Questionnaire-9 assessments. Each data sample was labeled as Steady or Mood Swing, with subgroups Steady-remission, Steady-depressed, Mood Swing-drastic, and Mood Swing-moderate based on patients' Patient Health Questionnaire-9 scores from three visits. A total of 252 features were extracted, and 4 feature selection models were applied; 6 different combinations of types of data were experimented with using 6 different machine learning models. Results: A total of 334 participants with MDD were enrolled in this study. The highest average accuracy of classification between Steady and Mood Swing was 76.67\% (SD 8.47\%) and that of recall was 90.44\% (SD 6.93\%), with features from all types of data being used. Among the 6 combinations of types of data we experimented with, the overall best combination was using call logs, sleep data, step count data, and heart rate data. The accuracies of predicting between Steady-remission and Mood Swing-drastic, Steady-remission and Mood Swing-moderate, and Steady-depressed and Mood Swing-drastic were over 80\%, and the accuracy of predicting between Steady-depressed and Mood Swing-moderate and the overall Steady to Mood Swing classification accuracy were over 75\%. Comparing all 6 aforementioned combinations, we found that the overall prediction accuracies between Steady-remission and Mood Swing (drastic and moderate) are better than those between Steady-depressed and Mood Swing (drastic and moderate). Conclusions: Our proposed method could be used to monitor mood changes in patients with MDD with promising accuracy by using passively collected data, which can be used as a reference by doctors for adjusting treatment plans or for warning patients and their guardians of a relapse. Trial Registration: Chinese Clinical Trial Registry ChiCTR1900021461; http://www.chictr.org.cn/showprojen.aspx?proj=36173 ",
doi="10.2196/24365",
url="https://mhealth.jmir.org/2021/3/e24365",
url="http://www.ncbi.nlm.nih.gov/pubmed/33683207"
}


@Article{info:doi/10.2196/25019,
author="Wen, Hongyi
and Sobolev, Michael
and Vitale, Rachel
and Kizer, James
and Pollak, P. J.
and Muench, Frederick
and Estrin, Deborah",
title="mPulse Mobile Sensing Model for Passive Detection of Impulsive Behavior: Exploratory Prediction Study",
journal="JMIR Ment Health",
year="2021",
month="Jan",
day="27",
volume="8",
number="1",
pages="e25019",
keywords="mobile sensing",
keywords="digital phenotyping",
keywords="impulse control",
keywords="impulsivity",
keywords="self-regulation",
keywords="self-control",
keywords="mobile health",
keywords="mHealth",
abstract="Background: Mobile health technology has demonstrated the ability of smartphone apps and sensors to collect data pertaining to patient activity, behavior, and cognition. It also offers the opportunity to understand how everyday passive mobile metrics such as battery life and screen time relate to mental health outcomes through continuous sensing. Impulsivity is an underlying factor in numerous physical and mental health problems. However, few studies have been designed to help us understand how mobile sensors and self-report data can improve our understanding of impulsive behavior. Objective: The objective of this study was to explore the feasibility of using mobile sensor data to detect and monitor self-reported state impulsivity and impulsive behavior passively via a cross-platform mobile sensing application. Methods: We enrolled 26 participants who were part of a larger study of impulsivity to take part in a real-world, continuous mobile sensing study over 21 days on both Apple operating system (iOS) and Android platforms. The mobile sensing system (mPulse) collected data from call logs, battery charging, and screen checking. To validate the model, we used mobile sensing features to predict common self-reported impulsivity traits, objective mobile behavioral and cognitive measures, and ecological momentary assessment (EMA) of state impulsivity and constructs related to impulsive behavior (ie, risk-taking, attention, and affect). Results: Overall, the findings suggested that passive measures of mobile phone use such as call logs, battery charging, and screen checking can predict different facets of trait and state impulsivity and impulsive behavior. For impulsivity traits, the models significantly explained variance in sensation seeking, planning, and lack of perseverance traits but failed to explain motor, urgency, lack of premeditation, and attention traits. Passive sensing features from call logs, battery charging, and screen checking were particularly useful in explaining and predicting trait-based sensation seeking. On a daily level, the model successfully predicted objective behavioral measures such as present bias in delay discounting tasks, commission and omission errors in a cognitive attention task, and total gains in a risk-taking task. Our models also predicted daily EMA questions on positivity, stress, productivity, healthiness, and emotion and affect. Perhaps most intriguingly, the model failed to predict daily EMA designed to measure previous-day impulsivity using face-valid questions. Conclusions: The study demonstrated the potential for developing trait and state impulsivity phenotypes and detecting impulsive behavior from everyday mobile phone sensors. Limitations of the current research and suggestions for building more precise passive sensing models are discussed. Trial Registration: ClinicalTrials.gov NCT03006653; https://clinicaltrials.gov/ct2/show/NCT03006653 ",
doi="10.2196/25019",
url="http://mental.jmir.org/2021/1/e25019/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33502330"
}


@Article{info:doi/10.2196/17116,
author="Lopez-Castroman, Jorge
and Abad-Tortosa, Diana
and Cobo Aguilera, Aurora
and Courtet, Philippe
and Barrig{\'o}n, Luisa Maria
and Art{\'e}s, Antonio
and Baca-Garc{\'i}a, Enrique",
title="Psychiatric Profiles of eHealth Users Evaluated Using Data Mining Techniques: Cohort Study",
journal="JMIR Ment Health",
year="2021",
month="Jan",
day="20",
volume="8",
number="1",
pages="e17116",
keywords="mental disorders",
keywords="suicide prevention",
keywords="suicidal ideation",
keywords="data mining",
keywords="digital phenotyping",
abstract="Background: New technologies are changing access to medical records and the relationship between physicians and patients. Professionals can now use e-mental health tools to provide prompt and personalized responses to patients with mental illness. However, there is a lack of knowledge about the digital phenotypes of patients who use e-mental health apps. Objective: This study aimed to reveal the profiles of users of a mental health app through machine learning techniques. Methods: We applied a nonparametric model, the Sparse Poisson Factorization Model, to discover latent features in the response patterns of 2254 psychiatric outpatients to a short self-assessment on general health. The assessment was completed through a mental health app after the first login. Results: The results showed the following four different profiles of patients: (1) all patients had feelings of worthlessness, aggressiveness, and suicidal ideas; (2) one in four reported low energy and difficulties to cope with problems; (3) less than a quarter described depressive symptoms with extremely high scores in suicidal thoughts and aggressiveness; and (4) a small number, possibly with the most severe conditions, reported a combination of all these features. Conclusions: User profiles did not overlap with clinician-made diagnoses. Since each profile seems to be associated with a different level of severity, the profiles could be useful for the prediction of behavioral risks among users of e-mental health apps. ",
doi="10.2196/17116",
url="http://mental.jmir.org/2021/1/e17116/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33470943"
}


@Article{info:doi/10.2196/24333,
author="Goltermann, Janik
and Emden, Daniel
and Leehr, Johanna Elisabeth
and Dohm, Katharina
and Redlich, Ronny
and Dannlowski, Udo
and Hahn, Tim
and Opel, Nils",
title="Smartphone-Based Self-Reports of Depressive Symptoms Using the Remote Monitoring Application in Psychiatry (ReMAP): Interformat Validation Study",
journal="JMIR Ment Health",
year="2021",
month="Jan",
day="12",
volume="8",
number="1",
pages="e24333",
keywords="mobile monitoring",
keywords="smartphone",
keywords="digital biomarkers",
keywords="digital phenotyping",
keywords="course of illness",
keywords="psychometric quality",
keywords="mood disorders",
keywords="depression",
keywords="affective disorders",
keywords="mobile phone",
abstract="Background: Smartphone-based symptom monitoring has gained increased attention in psychiatric research as a cost-efficient tool for prospective and ecologically valid assessments based on participants' self-reports. However, a meaningful interpretation of smartphone-based assessments requires knowledge about their psychometric properties, especially their validity. Objective: The goal of this study is to systematically investigate the validity of smartphone-administered assessments of self-reported affective symptoms using the Remote Monitoring Application in Psychiatry (ReMAP). Methods: The ReMAP app was distributed to 173 adult participants of ongoing, longitudinal psychiatric phenotyping studies, including healthy control participants, as well as patients with affective disorders and anxiety disorders; the mean age of the sample was 30.14 years (SD 11.92). The Beck Depression Inventory (BDI) and single-item mood and sleep information were assessed via the ReMAP app and validated with non--smartphone-based BDI scores and clinician-rated depression severity using the Hamilton Depression Rating Scale (HDRS). Results: We found overall high comparability between smartphone-based and non--smartphone-based BDI scores (intraclass correlation coefficient=0.921; P<.001). Smartphone-based BDI scores further correlated with non--smartphone-based HDRS ratings of depression severity in a subsample (r=0.783; P<.001; n=51). Higher agreement between smartphone-based and non--smartphone-based assessments was found among affective disorder patients as compared to healthy controls and anxiety disorder patients. Highly comparable agreement between delivery formats was found across age and gender groups. Similarly, smartphone-based single-item self-ratings of mood correlated with BDI sum scores (r=--0.538; P<.001; n=168), while smartphone-based single-item sleep duration correlated with the sleep item of the BDI (r=--0.310; P<.001; n=166). Conclusions: These findings demonstrate that smartphone-based monitoring of depressive symptoms via the ReMAP app provides valid assessments of depressive symptomatology and, therefore, represents a useful tool for prospective digital phenotyping in affective disorder patients in clinical and research applications. ",
doi="10.2196/24333",
url="https://mental.jmir.org/2021/1/e24333",
url="http://www.ncbi.nlm.nih.gov/pubmed/33433392"
}


@Article{info:doi/10.2196/19046,
author="Wang, Yameng
and Ren, Xiaotong
and Liu, Xiaoqian
and Zhu, Tingshao",
title="Examining the Correlation Between Depression and Social Behavior on Smartphones Through Usage Metadata: Empirical Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Jan",
day="6",
volume="9",
number="1",
pages="e19046",
keywords="depression",
keywords="digital phenotyping",
keywords="social behavior",
keywords="smartphone usage",
keywords="mobile sensing",
abstract="Background: As smartphone has been widely used, understanding how depression correlates with social behavior on smartphones can be beneficial for early diagnosis of depression. An enormous amount of research relied on self-report questionnaires, which is not objective. Only recently the increased availability of rich data about human behavior in digital space has provided new perspectives for the investigation of individual differences. Objective: The objective of this study was to explore depressed Chinese individuals' social behavior in digital space through metadata collected via smartphones. Methods: A total of 120 participants were recruited to carry a smartphone with a metadata collection app (MobileSens). At the end of metadata collection, they were instructed to complete the Center for Epidemiological Studies-Depression Scale (CES-D). We then separated participants into nondepressed and depressed groups based on their scores on CES-D. From the metadata of smartphone usage, we extracted 44 features, including traditional social behaviors such as making calls and sending SMS text messages, and the usage of social apps (eg, WeChat and Sina Weibo, 2 popular social apps in China). The 2-way ANOVA (nondepressed vs depressed {\texttimes} male vs female) and multiple logistic regression analysis were conducted to investigate differences in social behaviors on smartphones among users. Results: The results found depressed users received less calls from contacts (all day: F1,116=3.995, P=.048, $\eta$2=0.033; afternoon: F1,116=5.278, P=.02, $\eta$2=0.044), and used social apps more frequently (all day: F1,116=6.801, P=.01, $\eta$2=0.055; evening: F1,116=6.902, P=.01, $\eta$2=0.056) than nondepressed ones. In the depressed group, females used Weibo more frequently than males (all day: F1,116=11.744, P=.001, $\eta$2=0.092; morning: F1,116=9.105, P=.003, $\eta$2=0.073; afternoon: F1,116=14.224, P<.001, $\eta$2=0.109; evening: F1,116=9.052, P=.003, $\eta$2=0.072). Moreover, usage of social apps in the evening emerged as a predictor of depressive symptoms for all participants (odds ratio [OR] 1.007, 95\% CI 1.001-1.013; P=.02) and male (OR 1.013, 95\% CI 1.003-1.022; P=.01), and usage of Weibo in the morning emerged as a predictor for female (OR 1.183, 95\% CI 1.015-1.378; P=.03). Conclusions: This paper finds that there exists a certain correlation between depression and social behavior on smartphones. The result may be useful to improve social interaction for depressed individuals in the daily lives and may be insightful for early diagnosis of depression. ",
doi="10.2196/19046",
url="https://mhealth.jmir.org/2021/1/e19046",
url="http://www.ncbi.nlm.nih.gov/pubmed/33404512"
}


@Article{info:doi/10.2196/21703,
author="Tseng, WS Vincent
and Costa, Reis Jean Dos
and Jung, F. Malte
and Choudhury, Tanzeem",
title="Using Smartphone Sensor Data to Assess Inhibitory Control in the Wild: Longitudinal Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Dec",
day="4",
volume="8",
number="12",
pages="e21703",
keywords="self-control",
keywords="mobile phone",
abstract="Background: Inhibitory control, or inhibition, is one of the core executive functions of humans. It contributes to our attention, performance, and physical and mental well-being. Our inhibitory control is modulated by various factors and therefore fluctuates over time. Being able to continuously and unobtrusively assess our inhibitory control and understand the mediating factors may allow us to design intelligent systems that help manage our inhibitory control and ultimately our well-being. Objective: The aim of this study is to investigate whether we can assess individuals' inhibitory control using an unobtrusive and scalable approach to identify digital markers that are predictive of changes in inhibitory control. Methods: We developed InhibiSense, an app that passively collects the following information: users' behaviors based on their phone use and sensor data, the ground truths of their inhibition control measured with stop-signal tasks (SSTs) and ecological momentary assessments (EMAs), and heart rate information transmitted from a wearable heart rate monitor (Polar H10). We conducted a 4-week in-the-wild study, where participants were asked to install InhibiSense on their phone and wear a Polar H10. We used generalized estimating equation (GEE) and gradient boosting tree models fitted with features extracted from participants' phone use and sensor data to predict their stop-signal reaction time (SSRT), an objective metric used to measure an individual's inhibitory control, and identify the predictive digital markers. Results: A total of 12 participants completed the study, and 2189 EMAs and SST responses were collected. The results from the GEE models suggest that the top digital markers positively associated with an individual's SSRT include phone use burstiness (P=.005), the mean duration between 2 consecutive phone use sessions (P=.02), the change rate of battery level when the phone was not charged (P=.04), and the frequency of incoming calls (P=.03). The top digital markers negatively associated with SSRT include the standard deviation of acceleration (P<.001), the frequency of short phone use sessions (P<.001), the mean duration of incoming calls (P<.001), the mean decibel level of ambient noise (P=.007), and the percentage of time in which the phone was connected to the internet through a mobile network (P=.001). No significant correlation between the participants' objective and subjective measurement of inhibitory control was found. Conclusions: We identified phone-based digital markers that were predictive of changes in inhibitory control and how they were positively or negatively associated with a person's inhibitory control. The results of this study corroborate the findings of previous studies, which suggest that inhibitory control can be assessed continuously and unobtrusively in the wild. We discussed some potential applications of the system and how technological interventions can be designed to help manage inhibitory control. ",
doi="10.2196/21703",
url="https://mhealth.jmir.org/2020/12/e21703",
url="http://www.ncbi.nlm.nih.gov/pubmed/33275106"
}


@Article{info:doi/10.2196/22493,
author="Davoudi, Anahita
and Lee, S. Natalie
and Chivers, Corey
and Delaney, Timothy
and Asch, L. Elizabeth
and Reitz, Catherine
and Mehta, J. Shivan
and Chaiyachati, H. Krisda
and Mowery, L. Danielle",
title="Patient Interaction Phenotypes With an Automated Remote Hypertension Monitoring Program and Their Association With Blood Pressure Control: Observational Study",
journal="J Med Internet Res",
year="2020",
month="Dec",
day="3",
volume="22",
number="12",
pages="e22493",
keywords="text messaging",
keywords="hypertension",
keywords="telemedicine",
keywords="cluster analysis",
abstract="Background: Automated texting platforms have emerged as a tool to facilitate communication between patients and health care providers with variable effects on achieving target blood pressure (BP). Understanding differences in the way patients interact with these communication platforms can inform their use and design for hypertension management. Objective: Our primary aim was to explore the unique phenotypes of patient interactions with an automated text messaging platform for BP monitoring. Our secondary aim was to estimate associations between interaction phenotypes and BP control. Methods: This study was a secondary analysis of data from a randomized controlled trial for adults with poorly controlled hypertension. A total of 201 patients with established primary care were assigned to the automated texting platform; messages exchanged throughout the 4-month program were analyzed. We used the k-means clustering algorithm to characterize two different interaction phenotypes: program conformity and engagement style. First, we identified unique clusters signifying differences in program conformity based on the frequency over time of error alerts, which were generated to patients when they deviated from the requested text message format (eg, \#\#\#/\#\# for BP). Second, we explored overall engagement styles, defined by error alerts and responsiveness to text prompts, unprompted messages, and word count averages. Finally, we applied the chi-square test to identify associations between each interaction phenotype and achieving the target BP. Results: We observed 3 categories of program conformity based on their frequency of error alerts: those who immediately and consistently submitted texts without system errors (perfect users, 51/201), those who did so after an initial learning period (adaptive users, 66/201), and those who consistently submitted messages generating errors to the platform (nonadaptive users, 38/201). Next, we observed 3 categories of engagement style: the enthusiast, who tended to submit unprompted messages with high word counts (17/155); the student, who inconsistently engaged (35/155); and the minimalist, who engaged only when prompted (103/155). Of all 6 phenotypes, we observed a statistically significant association between patients demonstrating the minimalist communication style (high adherence, few unprompted messages, limited information sharing) and achieving target BP (P<.001). Conclusions: We identified unique interaction phenotypes among patients engaging with an automated text message platform for remote BP monitoring. Only the minimalist communication style was associated with achieving target BP. Identifying and understanding interaction phenotypes may be useful for tailoring future automated texting interactions and designing future interventions to achieve better BP control. ",
doi="10.2196/22493",
url="https://www.jmir.org/2020/12/e22493",
url="http://www.ncbi.nlm.nih.gov/pubmed/33270032"
}


@Article{info:doi/10.2196/medinform.6924,
author="Capurro, Daniel
and Barbe, Mario
and Daza, Claudio
and Santa Maria, Josefa
and Trincado, Javier",
title="Temporal Design Patterns for Digital Phenotype Cohort Selection in Critical Care: Systematic Literature Assessment and Qualitative Synthesis",
journal="JMIR Med Inform",
year="2020",
month="Nov",
day="24",
volume="8",
number="11",
pages="e6924",
keywords="digital phenotyping",
keywords="clinical data",
keywords="temporal abstraction",
abstract="Background: Inclusion criteria for observational studies frequently contain temporal entities and relations. The use of digital phenotypes to create cohorts in electronic health record--based observational studies requires rich functionality to capture these temporal entities and relations. However, such functionality is not usually available or requires complex database queries and specialized expertise to build them. Objective: The purpose of this study is to systematically assess observational studies reported in critical care literature to capture design requirements and functionalities for a graphical temporal abstraction-based digital phenotyping tool. Methods: We iteratively extracted attributes describing patients, interventions, and clinical outcomes. We qualitatively synthesized studies, identifying all temporal and nontemporal entities and relations. Results: We extracted data from 28 primary studies and 367 temporal and nontemporal entities. We generated a synthesis of entities, relations, and design patterns. Conclusions: We report on the observed types of clinical temporal entities and their relations as well as design requirements for a temporal abstraction-based digital phenotyping system. The results can be used to inform the development of such a system. ",
doi="10.2196/medinform.6924",
url="http://medinform.jmir.org/2020/11/e6924/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33231554"
}


@Article{info:doi/10.2196/18246,
author="McDonnell, Michelle
and Owen, Edward Jason
and Bantum, O'Carroll Erin",
title="Identification of Emotional Expression With Cancer Survivors: Validation of Linguistic Inquiry and Word Count",
journal="JMIR Form Res",
year="2020",
month="Oct",
day="30",
volume="4",
number="10",
pages="e18246",
keywords="linguistic analysis",
keywords="emotion",
keywords="validation",
abstract="Background: Given the high volume of text-based communication such as email, Facebook, Twitter, and additional web-based and mobile apps, there are unique opportunities to use text to better understand underlying psychological constructs such as emotion. Emotion recognition in text is critical to commercial enterprises (eg, understanding the valence of customer reviews) and to current and emerging clinical applications (eg, as markers of clinical progress and risk of suicide), and the Linguistic Inquiry and Word Count (LIWC) is a commonly used program. Objective: Given the wide use of this program, the purpose of this study is to update previous validation results with two newer versions of LIWC. Methods: Tests of proportions were conducted using the total number of emotion words identified by human coders for each emotional category as the reference group. In addition to tests of proportions, we calculated F scores to evaluate the accuracy of LIWC 2001, LIWC 2007, and LIWC 2015. Results: Results indicate that LIWC 2001, LIWC 2007, and LIWC 2015 each demonstrate good sensitivity for identifying emotional expression, whereas LIWC 2007 and LIWC 2015 were significantly more sensitive than LIWC 2001 for identifying emotional expression and positive emotion; however, more recent versions of LIWC were also significantly more likely to overidentify emotional content than LIWC 2001. LIWC 2001 demonstrated significantly better precision (F score) for identifying overall emotion, negative emotion, and anxiety compared with LIWC 2007 and LIWC 2015. Conclusions: Taken together, these results suggest that LIWC 2001 most accurately reflects the emotional identification of human coders. ",
doi="10.2196/18246",
url="https://formative.jmir.org/2020/10/e18246",
url="http://www.ncbi.nlm.nih.gov/pubmed/33124986"
}


@Article{info:doi/10.2196/21369,
author="Choo, Hyunwoo
and Kim, Myeongchan
and Choi, Jiyun
and Shin, Jaewon
and Shin, Soo-Yong",
title="Influenza Screening via Deep Learning Using a Combination of Epidemiological and Patient-Generated Health Data: Development and Validation Study",
journal="J Med Internet Res",
year="2020",
month="Oct",
day="29",
volume="22",
number="10",
pages="e21369",
keywords="influenza",
keywords="screening tool",
keywords="patient-generated health data",
keywords="mobile health",
keywords="mHealth",
keywords="deep learning",
abstract="Background: Screening for influenza in primary care is challenging due to the low sensitivity of rapid antigen tests and the lack of proper screening tests. Objective: The aim of this study was to develop a machine learning--based screening tool using patient-generated health data (PGHD) obtained from a mobile health (mHealth) app. Methods: We trained a deep learning model based on a gated recurrent unit to screen influenza using PGHD, including each patient's fever pattern and drug administration records. We used meteorological data and app-based surveillance of the weekly number of patients with influenza. We defined a single episode as the set of consecutive days, including the day the user was diagnosed with influenza or another disease. Any record a user entered 24 hours after his or her last record was considered to be the start of a new episode. Each episode contained data on the user's age, gender, weight, and at least one body temperature record. The total number of episodes was 6657. Of these, there were 3326 episodes within which influenza was diagnosed. We divided these episodes into 80\% training sets (2664/3330) and 20\% test sets (666/3330). A 5-fold cross-validation was used on the training set. Results: We achieved reliable performance with an accuracy of 82\%, a sensitivity of 84\%, and a specificity of 80\% in the test set. After the effect of each input variable was evaluated, app-based surveillance was observed to be the most influential variable. The correlation between the duration of input data and performance was not statistically significant (P=.09). Conclusions: These findings suggest that PGHD from an mHealth app could be a complementary tool for influenza screening. In addition, PGHD, along with traditional clinical data, could be used to improve health conditions. ",
doi="10.2196/21369",
url="http://www.jmir.org/2020/10/e21369/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33118941"
}


@Article{info:doi/10.2196/21814,
author="Hsu, Michael
and Ahern, K. David
and Suzuki, Joji",
title="Digital Phenotyping to Enhance Substance Use Treatment During the COVID-19 Pandemic",
journal="JMIR Ment Health",
year="2020",
month="Oct",
day="26",
volume="7",
number="10",
pages="e21814",
keywords="digital phenotyping",
keywords="digital psychiatry",
keywords="addiction",
keywords="psychiatry",
keywords="coronavirus",
keywords="COVID-19",
keywords="digital health",
keywords="treatment",
keywords="drugs",
keywords="substance use disorder",
doi="10.2196/21814",
url="http://mental.jmir.org/2020/10/e21814/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33031044"
}


@Article{info:doi/10.2196/22743,
author="Goel, Rahul
and An, Michael
and Alayrangues, Hugo
and Koneshloo, Amirhossein
and Lincoln, Thierry Emmanuel
and Paredes, Enrique Pablo",
title="Stress Tracker---Detecting Acute Stress From a Trackpad: Controlled Study",
journal="J Med Internet Res",
year="2020",
month="Oct",
day="23",
volume="22",
number="10",
pages="e22743",
keywords="precision health",
keywords="well-being",
keywords="trackpad",
keywords="computer input device",
keywords="computer interaction",
keywords="stress sensing",
keywords="affective interfaces",
keywords="mental health",
abstract="Background: Stress is a risk factor associated with physiological and mental health problems. Unobtrusive, continuous stress sensing would enable precision health monitoring and proactive interventions, but current sensing methods are often inconvenient, expensive, or suffer from limited adherence. Prior work has shown the possibility to detect acute stress using biomechanical models derived from passive logging of computer input devices. Objective: Our objective is to detect acute stress from passive movement measurements of everyday interactions on a laptop trackpad: (1) click, (2) steer, and (3) drag and drop. Methods: We built upon previous work, detecting acute stress through the biomechanical analyses of canonical computer mouse interactions and extended it to study similar interactions with the trackpad. A total of 18 participants carried out 40 trials each of three different types of movement---(1) click, (2) steer, and (3) drag and drop---under both relaxed and stressed conditions. Results: The mean and SD of the contact area under the finger were higher when clicking trials were performed under stressed versus relaxed conditions (mean area: P=.009, effect size=0.76; SD area: P=.01, effect size=0.69). Further, our results show that as little as 4 clicks on a trackpad can be used to detect binary levels of acute stress (ie, whether it is present or not). Conclusions: We present evidence that scalable, inexpensive, and unobtrusive stress sensing can be done via repurposing passive monitoring of computer trackpad usage. ",
doi="10.2196/22743",
url="http://www.jmir.org/2020/10/e22743/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33095176"
}


@Article{info:doi/10.2196/19263,
author="Pantel, Tori Jean
and Hajjir, Nurulhuda
and Danyel, Magdalena
and Elsner, Jonas
and Abad-Perez, Teresa Angela
and Hansen, Peter
and Mundlos, Stefan
and Spielmann, Malte
and Horn, Denise
and Ott, Claus-Eric
and Mensah, Atta Martin",
title="Efficiency of Computer-Aided Facial Phenotyping (DeepGestalt) in Individuals With and Without a Genetic Syndrome: Diagnostic Accuracy Study",
journal="J Med Internet Res",
year="2020",
month="Oct",
day="22",
volume="22",
number="10",
pages="e19263",
keywords="facial phenotyping",
keywords="DeepGestalt",
keywords="facial recognition",
keywords="Face2Gene",
keywords="medical genetics",
keywords="diagnostic accuracy",
keywords="genetic syndrome",
keywords="machine learning",
abstract="Background: Collectively, an estimated 5\% of the population have a genetic disease. Many of them feature characteristics that can be detected by facial phenotyping. Face2Gene CLINIC is an online app for facial phenotyping of patients with genetic syndromes. DeepGestalt, the neural network driving Face2Gene, automatically prioritizes syndrome suggestions based on ordinary patient photographs, potentially improving the diagnostic process. Hitherto, studies on DeepGestalt's quality highlighted its sensitivity in syndromic patients. However, determining the accuracy of a diagnostic methodology also requires testing of negative controls. Objective: The aim of this study was to evaluate DeepGestalt's accuracy with photos of individuals with and without a genetic syndrome. Moreover, we aimed to propose a machine learning--based framework for the automated differentiation of DeepGestalt's output on such images. Methods: Frontal facial images of individuals with a diagnosis of a genetic syndrome (established clinically or molecularly) from a convenience sample were reanalyzed. Each photo was matched by age, sex, and ethnicity to a picture featuring an individual without a genetic syndrome. Absence of a facial gestalt suggestive of a genetic syndrome was determined by physicians working in medical genetics. Photos were selected from online reports or were taken by us for the purpose of this study. Facial phenotype was analyzed by DeepGestalt version 19.1.7, accessed via Face2Gene CLINIC. Furthermore, we designed linear support vector machines (SVMs) using Python 3.7 to automatically differentiate between the 2 classes of photographs based on DeepGestalt's result lists. Results: We included photos of 323 patients diagnosed with 17 different genetic syndromes and matched those with an equal number of facial images without a genetic syndrome, analyzing a total of 646 pictures. We confirm DeepGestalt's high sensitivity (top 10 sensitivity: 295/323, 91\%). DeepGestalt's syndrome suggestions in individuals without a craniofacially dysmorphic syndrome followed a nonrandom distribution. A total of 17 syndromes appeared in the top 30 suggestions of more than 50\% of nondysmorphic images. DeepGestalt's top scores differed between the syndromic and control images (area under the receiver operating characteristic [AUROC] curve 0.72, 95\% CI 0.68-0.76; P<.001). A linear SVM running on DeepGestalt's result vectors showed stronger differences (AUROC 0.89, 95\% CI 0.87-0.92; P<.001). Conclusions: DeepGestalt fairly separates images of individuals with and without a genetic syndrome. This separation can be significantly improved by SVMs running on top of DeepGestalt, thus supporting the diagnostic process of patients with a genetic syndrome. Our findings facilitate the critical interpretation of DeepGestalt's results and may help enhance it and similar computer-aided facial phenotyping tools. ",
doi="10.2196/19263",
url="http://www.jmir.org/2020/10/e19263/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33090109"
}


@Article{info:doi/10.2196/19068,
author="Evers, JW Luc
and Raykov, P. Yordan
and Krijthe, H. Jesse
and Silva de Lima, L{\'i}gia Ana
and Badawy, Reham
and Claes, Kasper
and Heskes, M. Tom
and Little, A. Max
and Meinders, J. Marjan
and Bloem, R. Bastiaan",
title="Real-Life Gait Performance as a Digital Biomarker for Motor Fluctuations: The Parkinson@Home Validation Study",
journal="J Med Internet Res",
year="2020",
month="Oct",
day="9",
volume="22",
number="10",
pages="e19068",
keywords="digital biomarkers",
keywords="remote patient monitoring",
keywords="wearable sensors",
keywords="real-life gait",
keywords="Parkinson disease",
keywords="biomarker",
keywords="patient monitoring",
keywords="wearables",
keywords="gait",
abstract="Background: Wearable sensors have been used successfully to characterize bradykinetic gait in patients with Parkinson disease (PD), but most studies to date have been conducted in highly controlled laboratory environments. Objective: This paper aims to assess whether sensor-based analysis of real-life gait can be used to objectively and remotely monitor motor fluctuations in PD. Methods: The Parkinson@Home validation study provides a new reference data set for the development of digital biomarkers to monitor persons with PD in daily life. Specifically, a group of 25 patients with PD with motor fluctuations and 25 age-matched controls performed unscripted daily activities in and around their homes for at least one hour while being recorded on video. Patients with PD did this twice: once after overnight withdrawal of dopaminergic medication and again 1 hour after medication intake. Participants wore sensors on both wrists and ankles, on the lower back, and in the front pants pocket, capturing movement and contextual data. Gait segments of 25 seconds were extracted from accelerometer signals based on manual video annotations. The power spectral density of each segment and device was estimated using Welch's method, from which the total power in the 0.5- to 10-Hz band, width of the dominant frequency, and cadence were derived. The ability to discriminate between before and after medication intake and between patients with PD and controls was evaluated using leave-one-subject-out nested cross-validation. Results: From 18 patients with PD (11 men; median age 65 years) and 24 controls (13 men; median age 68 years), ?10 gait segments were available. Using logistic LASSO (least absolute shrinkage and selection operator) regression, we classified whether the unscripted gait segments occurred before or after medication intake, with mean area under the receiver operator curves (AUCs) varying between 0.70 (ankle of least affected side, 95\% CI 0.60-0.81) and 0.82 (ankle of most affected side, 95\% CI 0.72-0.92) across sensor locations. Combining all sensor locations did not significantly improve classification (AUC 0.84, 95\% CI 0.75-0.93). Of all signal properties, the total power in the 0.5- to 10-Hz band was most responsive to dopaminergic medication. Discriminating between patients with PD and controls was generally more difficult (AUC of all sensor locations combined: 0.76, 95\% CI 0.62-0.90). The video recordings revealed that the positioning of the hands during real-life gait had a substantial impact on the power spectral density of both the wrist and pants pocket sensor. Conclusions: We present a new video-referenced data set that includes unscripted activities in and around the participants' homes. Using this data set, we show the feasibility of using sensor-based analysis of real-life gait to monitor motor fluctuations with a single sensor location. Future work may assess the value of contextual sensors to control for real-world confounders. ",
doi="10.2196/19068",
url="https://www.jmir.org/2020/10/e19068",
url="http://www.ncbi.nlm.nih.gov/pubmed/33034562"
}


@Article{info:doi/10.2196/19223,
author="Wang, Hailiang
and Zhao, Yang
and Yu, Lisha
and Liu, Jiaxing
and Zwetsloot, Maria Inez
and Cabrera, Javier
and Tsui, Kwok-Leung",
title="A Personalized Health Monitoring System for Community-Dwelling Elderly People in Hong Kong: Design, Implementation, and Evaluation Study",
journal="J Med Internet Res",
year="2020",
month="Sep",
day="30",
volume="22",
number="9",
pages="e19223",
keywords="telehealth monitoring",
keywords="personalized health",
keywords="technology acceptance",
keywords="digital biomarkers",
keywords="digital phenotyping",
keywords="wearables",
keywords="falls detection",
keywords="fitness tracker",
keywords="sensors",
keywords="elderly population",
abstract="Background: Telehealth is an effective means to assist existing health care systems, particularly for the current aging society. However, most extant telehealth systems employ individual data sources by offline data processing, which may not recognize health deterioration in a timely way. Objective: Our study objective was two-fold: to design and implement an integrated, personalized telehealth system on a community-based level; and to evaluate the system from the perspective of user acceptance. Methods: The system was designed to capture and record older adults' health-related information (eg, daily activities, continuous vital signs, and gait behaviors) through multiple measuring tools. State-of-the-art data mining techniques can be integrated to detect statistically significant changes in daily records, based on which a decision support system could emit warnings to older adults, their family members, and their caregivers for appropriate interventions to prevent further health deterioration. A total of 45 older adults recruited from 3 elderly care centers in Hong Kong were instructed to use the system for 3 months. Exploratory data analysis was conducted to summarize the collected datasets. For system evaluation, we used a customized acceptance questionnaire to examine users' attitudes, self-efficacy, perceived usefulness, perceived ease of use, and behavioral intention on the system. Results: A total of 179 follow-up sessions were conducted in the 3 elderly care centers. The results of exploratory data analysis showed some significant differences in the participants' daily records and vital signs (eg, steps, body temperature, and systolic blood pressure) among the 3 centers. The participants perceived that using the system is a good idea (ie, attitude: mean 5.67, SD 1.06), comfortable (ie, self-efficacy: mean 4.92, SD 1.11), useful to improve their health (ie, perceived usefulness: mean 4.99, SD 0.91), and easy to use (ie, perceived ease of use: mean 4.99, SD 1.00). In general, the participants showed a positive intention to use the first version of our personalized telehealth system in their future health management (ie, behavioral intention: mean 4.45, SD 1.78). Conclusions: The proposed health monitoring system provides an example design for monitoring older adults' health status based on multiple data sources, which can help develop reliable and accurate predictive analytics. The results can serve as a guideline for researchers and stakeholders (eg, policymakers, elderly care centers, and health care providers) who provide care for older adults through such a telehealth system. ",
doi="10.2196/19223",
url="http://www.jmir.org/2020/9/e19223/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32996887"
}


@Article{info:doi/10.2196/18086,
author="Thota, Darshan",
title="Evaluating the Relationship Between Fitbit Sleep Data and Self-Reported Mood, Sleep, and Environmental Contextual Factors in Healthy Adults: Pilot Observational Cohort Study",
journal="JMIR Form Res",
year="2020",
month="Sep",
day="29",
volume="4",
number="9",
pages="e18086",
keywords="Fitbit",
keywords="sleep",
keywords="healthy",
keywords="mood",
keywords="context",
keywords="waking",
abstract="Background: Mental health disorders can disrupt a person's sleep, resulting in lower quality of life. Early identification and referral to mental health services are critical for active duty service members returning from forward-deployed missions. Although technologies like wearable computing devices have the potential to help address this problem, research on the role of technologies like Fitbit in mental health services is in its infancy. Objective: If Fitbit proves to be an appropriate clinical tool in a military setting, it could provide potential cost savings, improve clinician access to patient data, and create real-time treatment options for the greater active duty service member population. The purpose of this study was to determine if the Fitbit device can be used to identify indicators of mental health disorders by measuring the relationship between Fitbit sleep data, self-reported mood, and environmental contextual factors that may disrupt sleep. Methods: This observational cohort study was conducted at the Madigan Army Medical Center. The study included 17 healthy adults who wore a Fitbit Flex for 2 weeks and completed a daily self-reported mood and sleep log. Daily Fitbit data were obtained for each participant. Contextual factors were collected with interim and postintervention surveys. This study had 3 specific aims: (1) Determine the correlation between daily Fitbit sleep data and daily self-reported sleep, (2) Determine the correlation between number of waking events and self-reported mood, and (3) Explore the qualitative relationships between Fitbit waking events and self-reported contextual factors for sleep. Results: There was no significant difference in the scores for the pre-intevention Pittsburg Sleep Quality Index (PSQI; mean 5.88 points, SD 3.71 points) and postintervention PSQI (mean 5.33 points, SD 2.83 points). The Wilcoxon signed-ranks test showed that the difference between the pre-intervention PSQI and postintervention PSQI survey data was not statistically significant (Z=0.751, P=.05). The Spearman correlation between Fitbit sleep time and self-reported sleep time was moderate (r=0.643, P=.005). The Spearman correlation between number of waking events and self-reported mood was weak (r=0.354, P=.163). Top contextual factors disrupting sleep were ``pain,'' ``noises,'' and ``worries.'' A subanalysis of participants reporting ``worries'' found evidence of potential stress resilience and outliers in waking events. Conclusions: Findings contribute valuable evidence on the strength of the Fitbit Flex device as a proxy that is consistent with self-reported sleep data. Mood data alone do not predict number of waking events. Mood and Fitbit data combined with further screening tools may be able to identify markers of underlying mental health disease. ",
doi="10.2196/18086",
url="http://formative.jmir.org/2020/9/e18086/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32990631"
}


@Article{info:doi/10.2196/17818,
author="Sultana, Madeena
and Al-Jefri, Majed
and Lee, Joon",
title="Using Machine Learning and Smartphone and Smartwatch Data to Detect Emotional States and Transitions: Exploratory Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Sep",
day="29",
volume="8",
number="9",
pages="e17818",
keywords="mHealth",
keywords="mental health",
keywords="emotion detection",
keywords="emotional transition detection",
keywords="spatiotemporal context",
keywords="supervised machine learning",
keywords="artificial intelligence",
keywords="mobile phone",
keywords="digital biomarkers",
keywords="digital phenotyping",
abstract="Background: Emotional state in everyday life is an essential indicator of health and well-being. However, daily assessment of emotional states largely depends on active self-reports, which are often inconvenient and prone to incomplete information. Automated detection of emotional states and transitions on a daily basis could be an effective solution to this problem. However, the relationship between emotional transitions and everyday context remains to be unexplored. Objective: This study aims to explore the relationship between contextual information and emotional transitions and states to evaluate the feasibility of detecting emotional transitions and states from daily contextual information using machine learning (ML) techniques. Methods: This study was conducted on the data of 18 individuals from a publicly available data set called ExtraSensory. Contextual and sensor data were collected using smartphone and smartwatch sensors in a free-living condition, where the number of days for each person varied from 3 to 9. Sensors included an accelerometer, a gyroscope, a compass, location services, a microphone, a phone state indicator, light, temperature, and a barometer. The users self-reported approximately 49 discrete emotions at different intervals via a smartphone app throughout the data collection period. We mapped the 49 reported discrete emotions to the 3 dimensions of the pleasure, arousal, and dominance model and considered 6 emotional states: discordant, pleased, dissuaded, aroused, submissive, and dominant. We built general and personalized models for detecting emotional transitions and states every 5 min. The transition detection problem is a binary classification problem that detects whether a person's emotional state has changed over time, whereas state detection is a multiclass classification problem. In both cases, a wide range of supervised ML algorithms were leveraged, in addition to data preprocessing, feature selection, and data imbalance handling techniques. Finally, an assessment was conducted to shed light on the association between everyday context and emotional states. Results: This study obtained promising results for emotional state and transition detection. The best area under the receiver operating characteristic (AUROC) curve for emotional state detection reached 60.55\% in the general models and an average of 96.33\% across personalized models. Despite the highly imbalanced data, the best AUROC curve for emotional transition detection reached 90.5\% in the general models and an average of 88.73\% across personalized models. In general, feature analyses show that spatiotemporal context, phone state, and motion-related information are the most informative factors for emotional state and transition detection. Our assessment showed that lifestyle has an impact on the predictability of emotion. Conclusions: Our results demonstrate a strong association of daily context with emotional states and transitions as well as the feasibility of detecting emotional states and transitions using data from smartphone and smartwatch sensors. ",
doi="10.2196/17818",
url="http://mhealth.jmir.org/2020/9/e17818/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32990638"
}


@Article{info:doi/10.2196/19201,
author="Schneider, Stefan
and Junghaenel, U. Doerte
and Gutsche, Tania
and Mak, Wa Hio
and Stone, A. Arthur",
title="Comparability of Emotion Dynamics Derived From Ecological Momentary Assessments, Daily Diaries, and the Day Reconstruction Method: Observational Study",
journal="J Med Internet Res",
year="2020",
month="Sep",
day="24",
volume="22",
number="9",
pages="e19201",
keywords="ecological momentary assessment",
keywords="daily diaries",
keywords="day reconstruction method",
keywords="emotion dynamics",
keywords="emotion variability",
keywords="mobile phone",
abstract="Background: Interest in the measurement of the temporal dynamics of people's emotional lives has risen substantially in psychological and medical research. Emotions fluctuate and change over time, and measuring the ebb and flow of people's affective experiences promises enhanced insights into people's health and functioning. Researchers have used a variety of intensive longitudinal assessment (ILA) methods to create measures of emotion dynamics, including ecological momentary assessments (EMAs), end-of-day (EOD) diaries, and the day reconstruction method (DRM). To date, it is unclear whether they can be used interchangeably or whether ostensibly similar emotion dynamics captured by the methods differ in meaningful ways. Objective: This study aims to examine the extent to which different ILA methods yield comparable measures of intraindividual emotion dynamics. Methods: Data from 90 participants aged 50 years or older were collected in a probability-based internet panel, the Understanding America Study, and analyzed. Participants provided positive and negative affect ratings using 3 ILA methods: (1) smartphone-based EMA, administered 6 times per day over 1 week, (2) web-based EOD diaries, administered daily over the same week, and (3) web-based DRM, administered once during that week. We calculated 11 measures of emotion dynamics (addressing mean levels, variability, instability, and inertia separately for positive and negative affect, as well as emotion network density, mixed emotions, and emotional dialecticism) from each ILA method. The analyses examined mean differences and correlations of scores addressing the same emotion dynamic across the ILA methods. We also compared the patterns of intercorrelations among the emotion dynamics and their relationships with health outcomes (general health, pain, and fatigue) across ILA methods. Results: Emotion dynamics derived from EMAs and EOD diaries demonstrated moderate-to-high correspondence for measures of mean emotion levels ($\rho$?0.95), variability ($\rho$?0.68), instability ($\rho$?0.51), mixed emotions ($\rho$=0.92), and emotional dialecticism ($\rho$=0.57), and low correspondence for measures of inertia ($\rho$?0.17) and emotion network density ($\rho$=0.36). DRM-derived measures showed correlations with EMAs and EOD diaries that were high for mean emotion levels and mixed emotions ($\rho$?0.74), moderate for variability ($\rho$=0.38-.054), and low to moderate for other measures ($\rho$=0.03-0.41). Intercorrelations among the emotion dynamics showed high convergence across EMAs and EOD diaries, and moderate convergence between the DRM and EMAs as well as EOD diaries. Emotion dynamics from all 3 ILA methods produced very similar patterns of relationships with health outcomes. Conclusions: EMAs and EOD diaries provide corresponding information about individual differences in various emotion dynamics, whereas the DRM provides corresponding information about emotion levels and (to a lesser extent) variability, but not about more complex emotion dynamics. Our results caution researchers against viewing these ILA methods as universally interchangeable. ",
doi="10.2196/19201",
url="http://www.jmir.org/2020/9/e19201/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32969835"
}


@Article{info:doi/10.2196/19579,
author="Campbell, M. Laura
and Paolillo, W. Emily
and Heaton, Anne
and Tang, Bin
and Depp, A. Colin
and Granholm, Eric
and Heaton, K. Robert
and Swendsen, Joel
and Moore, J. David
and Moore, C. Raeanne",
title="Daily Activities Related to Mobile Cognitive Performance in Middle-Aged and Older Adults: An Ecological Momentary Cognitive Assessment Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Sep",
day="24",
volume="8",
number="9",
pages="e19579",
keywords="ecological momentary assessment",
keywords="daily functioning",
keywords="telemedicine",
keywords="digital health",
keywords="neuropsychological test",
keywords="cognition",
keywords="HIV",
keywords="aging",
keywords="mobile phone",
abstract="Background: Daily activities have been associated with neurocognitive performance. However, much of this research has used in-person neuropsychological testing that requires participants to travel to a laboratory or clinic, which may not always be feasible and does not allow for the examination of real-time relationships between cognition and behavior. Thus, there is a need to understand the real-time relationship between activities in the real world and neurocognitive functioning to improve tracking of symptoms or disease states and aid in the early identification of neurocognitive deficits among at-risk individuals. Objective: We used a smartphone-based ecological momentary cognitive assessment (EMCA) platform to examine real-time relationships between daily activities and neurocognitive performance (executive functioning and verbal learning) in the everyday environment of middle-aged and older adults with and without HIV. Methods: A total of 103 adults aged 50-74 years (67 persons with HIV; mean age 59 years, SD 6.4) were recruited from the University of California, San Diego HIV Neurobehavioral Research Program and the San Diego community. Participants completed our EMCA protocol for 14 days. Participants reported their current daily activities 4 times per day; following 2 of the 4 daily ecological momentary assessment (EMA) surveys, participants were administered the mobile Color-Word Interference Test (mCWIT) and mobile Verbal Learning Test (mVLT), each once per day. Activities were categorized into cognitively stimulating activities, passive leisure activities, and instrumental activities of daily living (IADLs). We used multilevel modeling to examine the same-survey and lagged within-person and between-person effects of each activity type on mobile cognitive performance. Results: On average, participants completed 91\% of the EMA surveys, 85\% of the mCWIT trials, and 80\% of the mVLT trials, and they reported engaging in cognitively stimulating activities on 17\% of surveys, passive leisure activities on 33\% of surveys, and IADLs on 20\% of surveys. Adherence and activity percentages did not differ by HIV status. Within-persons, engagement in cognitively stimulating activities was associated with better mCWIT performance ($\beta$=?1.12; P=.007), whereas engagement in passive leisure activities was associated with worse mCWIT performance ($\beta$=.94; P=.005). There were no lagged associations. At the aggregate between-person level, a greater percentage of time spent in cognitively stimulating activities was associated with better mean mVLT performance ($\beta$=.07; P=.02), whereas a greater percentage of time spent in passive leisure activities was associated with worse mean mVLT performance ($\beta$=?.07; P=.01). IADLs were not associated with mCWIT or mVLT performance. Conclusions: Smartphones present unique opportunities for assessing neurocognitive performance and behavior in middle-aged and older adults' own environment. Measurement of cognition and daily functioning outside of clinical settings may generate novel insights on the dynamic association of daily behaviors and neurocognitive performance and may add new dimensions to understanding the complexity of human behavior. ",
doi="10.2196/19579",
url="http://mhealth.jmir.org/2020/9/e19579/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32969829"
}


@Article{info:doi/10.2196/20488,
author="Gazi, H. Asim
and Gurel, Z. Nil
and Richardson, S. Kristine L.
and Wittbrodt, T. Matthew
and Shah, J. Amit
and Vaccarino, Viola
and Bremner, Douglas J.
and Inan, T. Omer",
title="Digital Cardiovascular Biomarker Responses to Transcutaneous Cervical Vagus Nerve Stimulation: State-Space Modeling, Prediction, and Simulation",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Sep",
day="22",
volume="8",
number="9",
pages="e20488",
keywords="vagus nerve stimulation",
keywords="noninvasive",
keywords="wearable sensing",
keywords="digital biomarkers",
keywords="dynamic models",
keywords="state space",
keywords="biomarker",
keywords="cardiovascular",
keywords="neuromodulation",
keywords="bioelectronic medicine",
abstract="Background: Transcutaneous cervical vagus nerve stimulation (tcVNS) is a promising alternative to implantable stimulation of the vagus nerve. With demonstrated potential in myriad applications, ranging from systemic inflammation reduction to traumatic stress attenuation, closed-loop tcVNS during periods of risk could improve treatment efficacy and reduce ineffective delivery. However, achieving this requires a deeper understanding of biomarker changes over time. Objective: The aim of the present study was to reveal the dynamics of relevant cardiovascular biomarkers, extracted from wearable sensing modalities, in response to tcVNS. Methods: Twenty-four human subjects were recruited for a randomized double-blind clinical trial, for whom electrocardiography and photoplethysmography were used to measure heart rate and photoplethysmogram amplitude responses to tcVNS, respectively. Modeling these responses in state-space, we (1) compared the biomarkers in terms of their predictability and active vs sham differentiation, (2) studied the latency between stimulation onset and measurable effects, and (3) visualized the true and model-simulated biomarker responses to tcVNS. Results: The models accurately predicted future heart rate and photoplethysmogram amplitude values with root mean square errors of approximately one-fifth the standard deviations of the data. Moreover, (1) the photoplethysmogram amplitude showed superior predictability (P=.03) and active vs sham separation compared to heart rate; (2) a consistent delay of greater than 5 seconds was found between tcVNS onset and cardiovascular effects; and (3) dynamic characteristics differentiated responses to tcVNS from the sham stimulation. Conclusions: This work furthers the state of the art by modeling pertinent biomarker responses to tcVNS. Through subsequent analysis, we discovered three key findings with implications related to (1) wearable sensing devices for bioelectronic medicine, (2) the dominant mechanism of action for tcVNS-induced effects on cardiovascular physiology, and (3) the existence of dynamic biomarker signatures that can be leveraged when titrating therapy in closed loop. Trial Registration: ClinicalTrials.gov NCT02992899; https://clinicaltrials.gov/ct2/show/NCT02992899 International Registered Report Identifier (IRRID): RR2-10.1016/j.brs.2019.08.002 ",
doi="10.2196/20488",
url="http://mhealth.jmir.org/2020/9/e20488/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32960179"
}


@Article{info:doi/10.2196/19348,
author="Birnbaum, Leo Michael
and Kulkarni, ``Param'' Prathamesh
and Van Meter, Anna
and Chen, Victor
and Rizvi, F. Asra
and Arenare, Elizabeth
and De Choudhury, Munmun
and Kane, M. John",
title="Utilizing Machine Learning on Internet Search Activity to Support the Diagnostic Process and Relapse Detection in Young Individuals With Early Psychosis: Feasibility Study",
journal="JMIR Ment Health",
year="2020",
month="Sep",
day="1",
volume="7",
number="9",
pages="e19348",
keywords="schizophrenia spectrum disorders",
keywords="internet search activity",
keywords="Google",
keywords="diagnostic prediction",
keywords="relapse prediction",
keywords="machine learning",
keywords="digital data",
keywords="digital phenotyping",
keywords="digital biomarkers",
abstract="Background: Psychiatry is nearly entirely reliant on patient self-reporting, and there are few objective and reliable tests or sources of collateral information available to help diagnostic and assessment procedures. Technology offers opportunities to collect objective digital data to complement patient experience and facilitate more informed treatment decisions. Objective: We aimed to develop computational algorithms based on internet search activity designed to support diagnostic procedures and relapse identification in individuals with schizophrenia spectrum disorders. Methods: We extracted 32,733 time-stamped search queries across 42 participants with schizophrenia spectrum disorders and 74 healthy volunteers between the ages of 15 and 35 (mean 24.4 years, 44.0\% male), and built machine-learning diagnostic and relapse classifiers utilizing the timing, frequency, and content of online search activity. Results: Classifiers predicted a diagnosis of schizophrenia spectrum disorders with an area under the curve value of 0.74 and predicted a psychotic relapse in individuals with schizophrenia spectrum disorders with an area under the curve of 0.71. Compared with healthy participants, those with schizophrenia spectrum disorders made fewer searches and their searches consisted of fewer words. Prior to a relapse hospitalization, participants with schizophrenia spectrum disorders were more likely to use words related to hearing, perception, and anger, and were less likely to use words related to health. Conclusions: Online search activity holds promise for gathering objective and easily accessed indicators of psychiatric symptoms. Utilizing search activity as collateral behavioral health information would represent a major advancement in efforts to capitalize on objective digital data to improve mental health monitoring. ",
doi="10.2196/19348",
url="https://mental.jmir.org/2020/9/e19348",
url="http://www.ncbi.nlm.nih.gov/pubmed/32870161"
}


@Article{info:doi/10.2196/19962,
author="Adler, A. Daniel
and Ben-Zeev, Dror
and Tseng, W-S Vincent
and Kane, M. John
and Brian, Rachel
and Campbell, T. Andrew
and Hauser, Marta
and Scherer, A. Emily
and Choudhury, Tanzeem",
title="Predicting Early Warning Signs of Psychotic Relapse From Passive Sensing Data: An Approach Using Encoder-Decoder Neural Networks",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Aug",
day="31",
volume="8",
number="8",
pages="e19962",
keywords="psychotic disorders",
keywords="schizophrenia",
keywords="mHealth",
keywords="mental health",
keywords="mobile health",
keywords="smartphone applications",
keywords="machine learning",
keywords="passive sensing",
keywords="digital biomarkers",
keywords="digital phenotyping",
keywords="artificial intelligence",
keywords="deep learning",
keywords="mobile phone",
abstract="Background: Schizophrenia spectrum disorders (SSDs) are chronic conditions, but the severity of symptomatic experiences and functional impairments vacillate over the course of illness. Developing unobtrusive remote monitoring systems to detect early warning signs of impending symptomatic relapses would allow clinicians to intervene before the patient's condition worsens. Objective: In this study, we aim to create the first models, exclusively using passive sensing data from a smartphone, to predict behavioral anomalies that could indicate early warning signs of a psychotic relapse. Methods: Data used to train and test the models were collected during the CrossCheck study. Hourly features derived from smartphone passive sensing data were extracted from 60 patients with SSDs (42 nonrelapse and 18 relapse >1 time throughout the study) and used to train models and test performance. We trained 2 types of encoder-decoder neural network models and a clustering-based local outlier factor model to predict behavioral anomalies that occurred within the 30-day period before a participant's date of relapse (the near relapse period). Models were trained to recreate participant behavior on days of relative health (DRH, outside of the near relapse period), following which a threshold to the recreation error was applied to predict anomalies. The neural network model architecture and the percentage of relapse participant data used to train all models were varied. Results: A total of 20,137 days of collected data were analyzed, with 726 days of data (0.037\%) within any 30-day near relapse period. The best performing model used a fully connected neural network autoencoder architecture and achieved a median sensitivity of 0.25 (IQR 0.15-1.00) and specificity of 0.88 (IQR 0.14-0.96; a median 108\% increase in behavioral anomalies near relapse). We conducted a post hoc analysis using the best performing model to identify behavioral features that had a medium-to-large effect (Cohen d>0.5) in distinguishing anomalies near relapse from DRH among 4 participants who relapsed multiple times throughout the study. Qualitative validation using clinical notes collected during the original CrossCheck study showed that the identified features from our analysis were presented to clinicians during relapse events. Conclusions: Our proposed method predicted a higher rate of anomalies in patients with SSDs within the 30-day near relapse period and can be used to uncover individual-level behaviors that change before relapse. This approach will enable technologists and clinicians to build unobtrusive digital mental health tools that can predict incipient relapse in SSDs. ",
doi="10.2196/19962",
url="https://mhealth.jmir.org/2020/8/e19962",
url="http://www.ncbi.nlm.nih.gov/pubmed/32865506"
}


@Article{info:doi/10.2196/18818,
author="Darg{\'e}l, A. Aroldo
and Mosconi, Elise
and Masson, Marc
and Plaze, Marion
and Taieb, Fabien
and Von Platen, Cassandra
and Buivan, Phuc Tan
and Pouleriguen, Guillaume
and Sanchez, Marie
and Fournier, St{\'e}phane
and Lledo, Pierre-Marie
and Henry, Chantal",
title="Toi M{\^e}me, a Mobile Health Platform for Measuring Bipolar Illness Activity: Protocol for a Feasibility Study",
journal="JMIR Res Protoc",
year="2020",
month="Aug",
day="18",
volume="9",
number="8",
pages="e18818",
keywords="bipolar disorder",
keywords="digital phenotyping, smartphone app",
keywords="ecological momentary assessment",
keywords="mHealth",
keywords="mood instability",
keywords="cognitive speed",
keywords="affective response",
keywords="big data, machine learning",
abstract="Background: The diagnosis and management of bipolar disorder are limited by the absence of available biomarkers. Patients with bipolar disorder frequently present with mood instability even during remission, which is likely associated with the risk of relapse, impaired functioning, and suicidal behavior, indicating that the illness is active. Objective: This research protocol aimed to investigate the correlations between clinically rated mood symptoms and mood/behavioral data automatically collected using the Toi M{\^e}me app in patients with bipolar disorder presenting with different mood episodes. This study also aimed to assess the feasibility of this app for self-monitoring subjective and objective mood/behavior parameters in those patients. Methods: This open-label, nonrandomized trial will enroll 93 (31 depressive, 31 euthymic, and 31 hypomanic) adults diagnosed with bipolar disorder type I/II (Diagnostic and Statistical Manual of Mental Disorders, 5th edition criteria) and owning an iPhone. Clinical evaluations will be performed by psychiatrists at the baseline and after 2 weeks, 1 month, 2 months, and 3 months during the follow-up. Rather than only accessing the daily mood symptoms, the Toi M{\^e}me app also integrates ecological momentary assessments through 2 gamified tests to assess cognition speed (QUiCKBRAIN) and affective responses (PLAYiMOTIONS) in real-life contexts, continuously measures daily motor activities (eg, number of steps, distance) using the smartphone's motion sensors, and performs a comprehensive weekly assessment. Results: Recruitment began in April 2018 and the completion of the study is estimated to be in December 2021. As of April 2019, 25 participants were enrolled in the study. The first results are expected to be submitted for publication in 2020. This project has been funded by the Perception and Memory Unit of the Pasteur Institute (Paris) and it has received the final ethical/research approvals in April 2018 (ID-RCB: 2017-A02450-53). Conclusions: Our results will add to the evidence of exploring other alternatives toward a more integrated approach in the management of bipolar disorder, including digital phenotyping, to develop an ethical and clinically meaningful framework for investigating, diagnosing, and treating individuals at risk of developing bipolar disorder or currently experiencing bipolar disorder. Further prospective studies on the validity of automatically generated smartphone data are needed for better understanding the longitudinal pattern of mood instability in bipolar disorder as well as to establish the reliability, efficacy, and cost-effectiveness of such an app intervention for patients with bipolar disorder. Trial Registration: ClinicalTrials.gov NCT03508427; https://clinicaltrials.gov/ct2/show/NCT03508427 International Registered Report Identifier (IRRID): DERR1-10.2196/18818 ",
doi="10.2196/18818",
url="http://www.researchprotocols.org/2020/8/e18818/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32638703"
}


@Article{info:doi/10.2196/18751,
author="Di Matteo, Daniel
and Fotinos, Kathryn
and Lokuge, Sachinthya
and Yu, Julia
and Sternat, Tia
and Katzman, A. Martin
and Rose, Jonathan",
title="The Relationship Between Smartphone-Recorded Environmental Audio and Symptomatology of Anxiety and Depression: Exploratory Study",
journal="JMIR Form Res",
year="2020",
month="Aug",
day="13",
volume="4",
number="8",
pages="e18751",
keywords="depression",
keywords="anxiety",
keywords="mobile phone",
keywords="ecological momentary assessment",
keywords="mobile apps",
keywords="mobile health",
keywords="digital signal processing",
keywords="acoustics",
keywords="speech recognition software",
abstract="Background: Objective and continuous severity measures of anxiety and depression are highly valuable and would have many applications in psychiatry and psychology. A collective source of data for objective measures are the sensors in a person's smartphone, and a particularly rich source is the microphone that can be used to sample the audio environment. This may give broad insight into activity, sleep, and social interaction, which may be associated with quality of life and severity of anxiety and depression. Objective: This study aimed to explore the properties of passively recorded environmental audio from a subject's smartphone to find potential correlates of symptom severity of social anxiety disorder, generalized anxiety disorder, depression, and general impairment. Methods: An Android app was designed, together with a centralized server system, to collect periodic measurements of the volume of sounds in the environment and to detect the presence or absence of English-speaking voices. Subjects were recruited into a 2-week observational study during which the app was run on their personal smartphone to collect audio data. Subjects also completed self-report severity measures of social anxiety disorder, generalized anxiety disorder, depression, and functional impairment. Participants were 112 Canadian adults from a nonclinical population. High-level features were extracted from the environmental audio of 84 participants with sufficient data, and correlations were measured between the 4 audio features and the 4 self-report measures. Results: The regularity in daily patterns of activity and inactivity inferred from the environmental audio volume was correlated with the severity of depression (r=?0.37; P<.001). A measure of sleep disturbance inferred from the environmental audio volume was also correlated with the severity of depression (r=0.23; P=.03). A proxy measure of social interaction based on the detection of speaking voices in the environmental audio was correlated with depression (r=?0.37; P<.001) and functional impairment (r=?0.29; P=.01). None of the 4 environmental audio-based features tested showed significant correlations with the measures of generalized anxiety or social anxiety. Conclusions: In this study group, the environmental audio was shown to contain signals that were associated with the severity of depression and functional impairment. Associations with the severity of social anxiety disorder and generalized anxiety disorder were much weaker in comparison and not statistically significant at the 5\% significance level. This work also confirmed previous work showing that the presence of voices is associated with depression. Furthermore, this study suggests that sparsely sampled audio volume could provide potentially relevant insight into subjects' mental health. ",
doi="10.2196/18751",
url="https://formative.jmir.org/2020/8/e18751",
url="http://www.ncbi.nlm.nih.gov/pubmed/32788153"
}


@Article{info:doi/10.2196/18136,
author="Kim, Woon Ko
and Lee, Yun Sung
and Choi, Jongdoo
and Chin, Juhee
and Lee, Hwa Byung
and Na, L. Duk
and Choi, Hyun Jee",
title="A Comprehensive Evaluation of the Process of Copying a Complex Figure in Early- and Late-Onset Alzheimer Disease: A Quantitative Analysis of Digital Pen Data",
journal="J Med Internet Res",
year="2020",
month="Aug",
day="12",
volume="22",
number="8",
pages="e18136",
keywords="alzheimer disease",
keywords="Rey-Osterrieth Complex Figure",
keywords="digital biomarkers",
keywords="copying process",
abstract="Background: The Rey-Osterrieth Complex Figure Test (RCFT) is a neuropsychological test that is widely used to assess visual memory and visuoconstructional deficits in patients with cognitive impairment, including Alzheimer disease (AD). Patients with AD have an increased tendency for exhibiting extraordinary behaviors in the RCFT for selecting the drawing area, organizing the figure, and deciding the order of images, among other activities. However, the conventional scoring system based on pen and paper has a limited ability to reflect these detailed behaviors. Objective: This study aims to establish a scoring system that addresses not only the spatial arrangement of the finished drawing but also the drawing process of patients with AD by using digital pen data. Methods: A digital pen and tablet were used to copy complex figures. The stroke patterns and kinetics of normal controls (NCs) and patients with early-onset AD (EOAD) and late-onset AD (LOAD) were analyzed by comparing the pen tip trajectory, spatial arrangement, and similarity of the finished drawings. Results: Patients with AD copied the figure in a more fragmented way with a longer pause than NCs (EOAD: P=.045; LOAD: P=.01). Patients with AD showed an increased tendency to draw the figures closer toward the target image in comparison with the NCs (EOAD: P=.005; LOAD: P=.01) Patients with AD showed the lower accuracy than NCs (EOAD: P=.004; LOAD: P=.002). Patients with EOAD and LOAD showed similar but slightly different drawing behaviors, especially in space use and in the initial stage of drawing. Conclusions: The digitalized complex figure test evaluated copying performance quantitatively and further elucidated the patients' ongoing process during copying. We believe that this novel approach can be used as a digital biomarker of AD. In addition, the repeatability of the test will delineate the process of executive functions and constructional organization abilities with disease progression. ",
doi="10.2196/18136",
url="https://www.jmir.org/2020/8/e18136",
url="http://www.ncbi.nlm.nih.gov/pubmed/32491988"
}


@Article{info:doi/10.2196/15506,
author="Betthauser, M. Lisa
and Stearns-Yoder, A. Kelly
and McGarity, Suzanne
and Smith, Victoria
and Place, Skyler
and Brenner, A. Lisa",
title="Mobile App for Mental Health Monitoring and Clinical Outreach in Veterans: Mixed Methods Feasibility and Acceptability Study",
journal="J Med Internet Res",
year="2020",
month="Aug",
day="11",
volume="22",
number="8",
pages="e15506",
keywords="veterans",
keywords="mobile app",
keywords="smartphone",
keywords="mental health",
keywords="acceptability",
keywords="feasibility",
abstract="Background: Advances in mobile health (mHealth) technology have made it possible for patients and health care providers to monitor and track behavioral health symptoms in real time. Ideally, mHealth apps include both passive and interactive monitoring and demonstrate high levels of patient engagement. Digital phenotyping, the measurement of individual technology usage, provides insight into individual behaviors associated with mental health. Objective: Researchers at a Veterans Affairs Medical Center and Cogito Corporation sought to explore the feasibility and acceptability of an mHealth app, the Cogito Companion. Methods: A mixed methodological approach was used to investigate the feasibility and acceptability of the app. Veterans completed clinical interviews and self-report measures, at baseline and at a 3-month follow-up. During the data collection period, participants were provided access to the Cogito Companion smartphone app. The mobile app gathered passive and active behavioral health indicators. Data collected (eg, vocal features and digital phenotyping of everyday social signals) are analyzed in real time. Passive data collected include location via global positioning system (GPS), phone calls, and SMS text message metadata.  Four primary model scores were identified as being predictive of the presence or absence of depression or posttraumatic stress disorder (PTSD). Veterans Affairs clinicians monitored a provider dashboard and conducted clinical outreach when indicated. Results: Findings suggest that use of the Cogito Companion app was feasible and acceptable. Veterans (n=83) were interested in and used the app; however, active use declined over time. Nonetheless, data were passively collected, and outreach occurred throughout the study period. On the Client Satisfaction Questionnaire--8, 79\% (53/67) of the sample reported scores demonstrating acceptability of the app (mean 26.2, SD 4.3). Many veterans reported liking specific app features (day-to-day monitoring) and the sense of connection they felt with the study clinicians who conducted outreach. Only a small percentage (4/67, 6\%) reported concerns regarding personal privacy. Conclusions: Feasibility and acceptability of the Cogito Corporation platform to monitor mental health symptoms, behaviors, and facilitate follow-up in a sample of veterans were supported. Clinically, platforms such as the Cogito Companion system may serve as  useful methods to promote monitoring, thereby facilitating early identification of risk and mitigating negative psychiatric outcomes, such as suicide. ",
doi="10.2196/15506",
url="https://www.jmir.org/2020/8/e15506",
url="http://www.ncbi.nlm.nih.gov/pubmed/32779572"
}


@Article{info:doi/10.2196/18453,
author="Olmert, Tony
and Cooper, D. Jason
and Han, Sarah Sung Yeon
and Barton-Owen, Giles
and Farrag, Lynn
and Bell, Emily
and Friend, V. Lauren
and Ozcan, Sureyya
and Rustogi, Nitin
and Preece, L. Rhian
and Eljasz, Pawel
and Tomasik, Jakub
and Cowell, Daniel
and Bahn, Sabine",
title="A Combined Digital and Biomarker Diagnostic Aid for Mood Disorders (the Delta Trial): Protocol for an Observational Study",
journal="JMIR Res Protoc",
year="2020",
month="Aug",
day="10",
volume="9",
number="8",
pages="e18453",
keywords="proteomics",
keywords="early diagnosis",
keywords="mood disorders",
keywords="bipolar disorder",
keywords="major depressive disorders",
abstract="Background: Mood disorders affect hundreds of millions of people worldwide, imposing a substantial medical and economic burden. Existing diagnostic methods for mood disorders often result in a delay until accurate diagnosis, exacerbating the challenges of these disorders. Advances in digital tools for psychiatry and understanding the biological basis of mood disorders offer the potential for novel diagnostic methods that facilitate early and accurate diagnosis of patients. Objective: The Delta Trial was launched to develop an algorithm-based diagnostic aid combining symptom data and proteomic biomarkers to reduce the misdiagnosis of bipolar disorder (BD) as a major depressive disorder (MDD) and achieve more accurate and earlier MDD diagnosis. Methods: Participants for this ethically approved trial were recruited through the internet, mainly through Facebook advertising. Participants were then screened for eligibility, consented to participate, and completed an adaptive digital questionnaire that was designed and created for the trial on a purpose-built digital platform. A subset of these participants was selected to provide dried blood spot (DBS) samples and undertake a World Health Organization World Mental Health Composite International Diagnostic Interview (CIDI). Inclusion and exclusion criteria were chosen to maximize the safety of a trial population that was both relevant to the trial objectives and generalizable. To provide statistical power and validation sets for the primary and secondary objectives, 840 participants were required to complete the digital questionnaire, submit DBS samples, and undertake a CIDI. Results: The Delta Trial is now complete. More than 3200 participants completed the digital questionnaire, 924 of whom also submitted DBS samples and a CIDI, whereas a total of 1780 participants completed a 6-month follow-up questionnaire and 1542 completed a 12-month follow-up questionnaire. The analysis of the trial data is now underway. Conclusions: If a diagnostic aid is able to improve the diagnosis of BD and MDD, it may enable earlier treatment for patients with mood disorders. International Registered Report Identifier (IRRID): DERR1-10.2196/18453 ",
doi="10.2196/18453",
url="https://www.researchprotocols.org/2020/8/e18453",
url="http://www.ncbi.nlm.nih.gov/pubmed/32773373"
}


@Article{info:doi/10.2196/13611,
author="Wang, Max
and Ge, Wenbo
and Apthorp, Deborah
and Suominen, Hanna",
title="Robust Feature Engineering for Parkinson Disease Diagnosis: New Machine Learning Techniques",
journal="JMIR Biomed Eng",
year="2020",
month="Jul",
day="27",
volume="5",
number="1",
pages="e13611",
keywords="machine learning",
keywords="mobile phone",
keywords="nonlinear dynamics",
keywords="Parkinson disease",
keywords="signal processing, computer-assisted",
keywords="speech",
keywords="biomarkers",
abstract="Background: Parkinson disease (PD) is a common neurodegenerative disorder that affects between 7 and 10 million people worldwide. No objective test for PD currently exists, and studies suggest misdiagnosis rates of up to 34\%. Machine learning (ML) presents an opportunity to improve diagnosis; however, the size and nature of data sets make it difficult to generalize the performance of ML models to real-world applications. Objective: This study aims to consolidate prior work and introduce new techniques in feature engineering and ML for diagnosis based on vowel phonation. Additional features and ML techniques were introduced, showing major performance improvements on the large mPower vocal phonation data set. Methods: We used 1600 randomly selected /aa/ phonation samples from the entire data set to derive rules for filtering out faulty samples from the data set. The application of these rules, along with a joint age-gender balancing filter, results in a data set of 511 PD patients and 511 controls. We calculated features on a 1.5-second window of audio, beginning at the 1-second mark, for a support vector machine. This was evaluated with 10-fold cross-validation (CV), with stratification for balancing the number of patients and controls for each CV fold. Results: We showed that the features used in prior literature do not perform well when extrapolated to the much larger mPower data set. Owing to the natural variation in speech, the separation of patients and controls is not as simple as previously believed. We presented significant performance improvements using additional novel features (with 88.6\% certainty, derived from a Bayesian correlated t test) in separating patients and controls, with accuracy exceeding 58\%. Conclusions: The results are promising, showing the potential for ML in detecting symptoms imperceptible to a neurologist. ",
doi="10.2196/13611",
url="https://biomedeng.jmir.org/2020/1/e13611"
}


@Article{info:doi/10.2196/14328,
author="Weizenbaum, Emma
and Torous, John
and Fulford, Daniel",
title="Cognition in Context: Understanding the Everyday Predictors of Cognitive Performance in a New Era of Measurement",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jul",
day="23",
volume="8",
number="7",
pages="e14328",
keywords="smartphone",
keywords="mobile phone",
keywords="neuropsychology",
keywords="individualized medicine",
abstract="Background: Research suggests that variability in attention and working memory scores, as seen across time points, may be a sensitive indicator of impairment compared with a singular score at one point in time. Given that fluctuation in cognitive performance is a meaningful metric of real-world function and trajectory, it is valuable to understand the internal state-based and environmental factors that could be driving these fluctuations in performance. Objective: In this viewpoint, we argue for the use of repeated mobile assessment as a way to better understand how context shapes moment-to-moment cognitive performance. To elucidate potential factors that give rise to intraindividual variability, we highlight existing literature that has linked both internal and external modifying variables to a number of cognitive domains. We identify ways in which these variables could be measured using mobile assessment to capture them in ecologically meaningful settings (ie, in daily life). Finally, we describe a number of studies that have already begun to use mobile assessment to measure changes in real time cognitive performance in people's daily environments and the ways in which this burgeoning methodology may continue to advance the field. Methods: This paper describes selected literature on contextual factors that examined how experimentally induced or self-reported contextual variables (ie, affect, motivation, time of day, environmental noise, physical activity, and social activity) related to tests of cognitive performance. We also selected papers that used mobile assessment of cognition; these papers were chosen for their use of high-frequency time-series measurement of cognition using a mobile device. Results: Upon review of the relevant literature, it is evident that contextual factors have the potential to meaningfully impact cognitive performance when measured in laboratory and daily life environments. Although this research has shed light on the question of what gives rise to real-life variability in cognitive function (eg, affect and activity), many of the studies were limited by traditional methods of data collection (eg, involving retrospective recall). Furthermore, cognition has often been measured in one domain or in one age group, which does not allow us to extrapolate results to other cognitive domains and across the life span. On the basis of the literature reviewed, mobile assessment of cognition shows high levels of feasibility and validity and could be a useful method for capturing individual cognitive variability in real-world contexts via passive and active measures. Conclusions: We propose that, through the use of mobile assessment, there is an opportunity to combine multiple sources of contextual and cognitive data. These data have the potential to provide individualized digital signatures that could improve diagnostic precision and lead to meaningful clinical outcomes in a wide range of psychiatric and neurological disorders. ",
doi="10.2196/14328",
url="https://mhealth.jmir.org/2020/7/e14328",
url="http://www.ncbi.nlm.nih.gov/pubmed/32706680"
}


@Article{info:doi/10.2196/15901,
author="Haines-Delmont, Alina
and Chahal, Gurdit
and Bruen, Jane Ashley
and Wall, Abbie
and Khan, Tara Christina
and Sadashiv, Ramesh
and Fearnley, David",
title="Testing Suicide Risk Prediction Algorithms Using Phone Measurements With Patients in Acute Mental Health Settings: Feasibility Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jun",
day="26",
volume="8",
number="6",
pages="e15901",
keywords="suicide",
keywords="suicidal ideation",
keywords="smartphone",
keywords="cell phone",
keywords="machine learning",
keywords="nearest neighbor algorithm",
keywords="digital phenotyping",
abstract="Background: Digital phenotyping and machine learning are currently being used to augment or even replace traditional analytic procedures in many domains, including health care. Given the heavy reliance on smartphones and mobile devices around the world, this readily available source of data is an important and highly underutilized source that has the potential to improve mental health risk prediction and prevention and advance mental health globally. Objective: This study aimed to apply machine learning in an acute mental health setting for suicide risk prediction. This study uses a nascent approach, adding to existing knowledge by using data collected through a smartphone in place of clinical data, which have typically been collected from health care records. Methods: We created a smartphone app called Strength Within Me, which was linked to Fitbit, Apple Health kit, and Facebook, to collect salient clinical information such as sleep behavior and mood, step frequency and count, and engagement patterns with the phone from a cohort of inpatients with acute mental health (n=66). In addition, clinical research interviews were used to assess mood, sleep, and suicide risk. Multiple machine learning algorithms were tested to determine the best fit. Results: K-nearest neighbors (KNN; k=2) with uniform weighting and the Euclidean distance metric emerged as the most promising algorithm, with 68\% mean accuracy (averaged over 10,000 simulations of splitting the training and testing data via 10-fold cross-validation) and an average area under the curve of 0.65. We applied a combined 5{\texttimes}2 F test to test the model performance of KNN against the baseline classifier that guesses training majority, random forest, support vector machine and logistic regression, and achieved F statistics of 10.7 (P=.009) and 17.6 (P=.003) for training majority and random forest, respectively, rejecting the null of performance being the same. Therefore, we have taken the first steps in prototyping a system that could continuously and accurately assess the risk of suicide via mobile devices. Conclusions: Predicting for suicidality is an underaddressed area of research to which this paper makes a useful contribution. This is part of the first generation of studies to suggest that it is feasible to utilize smartphone-generated user input and passive sensor data to generate a risk algorithm among inpatients at suicide risk. The model reveals fair concordance between phone-derived and research-generated clinical data, and with iterative development, it has the potential for accurate discriminant risk prediction. However, although full automation and independence of clinical judgment or input would be a worthy development for those individuals who are less likely to access specialist mental health services, and for providing a timely response in a crisis situation, the ethical and legal implications of such advances in the field of psychiatry need to be acknowledged. ",
doi="10.2196/15901",
url="https://mhealth.jmir.org/2020/6/e15901",
url="http://www.ncbi.nlm.nih.gov/pubmed/32442152"
}


@Article{info:doi/10.2196/16964,
author="Pastor, N{\'u}ria
and Khalilian, Elizabeth
and Caballeria, Elsa
and Morrison, Danielle
and Sanchez Luque, Unai
and Matrai, Silvia
and Gual, Antoni
and L{\'o}pez-Pelayo, Hugo",
title="Remote Monitoring Telemedicine (REMOTE) Platform for Patients With Anxiety Symptoms and Alcohol Use Disorder: Protocol for a Case-Control Study",
journal="JMIR Res Protoc",
year="2020",
month="Jun",
day="24",
volume="9",
number="6",
pages="e16964",
keywords="digital health",
keywords="digital biomarkers",
keywords="digital phenotype",
keywords="mental health",
abstract="Background: Monitoring mental health outcomes has traditionally been based on heuristic decisions, often based on scarce, subjective evidence, making the clinical decisions made by professionals, as well as the monitoring of these diseases, subject to flaws. However, the digital phenotype, which refers to the analysis of data collected by measuring human behavior with mobile sensors and smart bracelets, is a promising tool for filling this gap in current clinical practice. Objective: The objectives of this study are to develop the digital phenotyping of patients with alcohol use disorder and anxiety symptoms using data collected from a mobile device (ie, smartphone) and a wearable sensor (ie, Fitbit) and to analyze usability and patient satisfaction with the data collection service provided by the app. Methods: We propose to conduct a study among a group of 60 participants split into two subgroups---experimental and control---of 30 participants each. The experimental group will be recruited by physicians from the Hospital Cl{\'i}nic de Barcelona, and the control group will be recruited on a volunteer basis through fliers and social media. All participants will go through pretraining to ensure technological capability and understanding of tasks, then each participant will download the HumanITcare app and will be given a wearable sensor (ie, Fitbit). Throughout the 4-month period, participants will be monitored on a range of factors, including sleep cycle, heart rate, movement patterns, and sociability. All data from the wearable sensors and the mobile devices will be saved and sent to the HumanITcare server. Participants will be asked to complete weekly questionnaires about anxiety, depression, and alcohol use disorder symptoms. Research assistants will ensure timely responses. The data from both sensors will then be compared to the questionnaire responses to determine how accurately the devices can predict the same symptoms. Results: The recruitment phase was completed in November 2019 and all the data were collected by the end of December 2019. Data are being processed; this process is expected to be completed by October 2020. Conclusions: This study was created and conducted as a pilot study with the Hospital Cl{\'i}nic de Barcelona, with the purpose of exploring the feasibility of our approach. The study is focused on patients diagnosed with anxiety and alcohol use disorder, but participants were also monitored for depressive symptoms throughout the trial, although these were not part of the initial inclusion criteria. A limitation to our study was the exclusive use of Android smartphones over iOS devices; this could result in a potential selection bias, due to the accessibility and affordability of Android phones as opposed to iOS-based phones. Another limitation might be that reviews of usability and satisfaction could be confounded by factors such as age and familiarity. An additional function that we might add in future studies is the ability for patients to manage their own data. International Registered Report Identifier (IRRID): DERR1-10.2196/16964 ",
doi="10.2196/16964",
url="https://www.researchprotocols.org/2020/6/e16964",
url="http://www.ncbi.nlm.nih.gov/pubmed/32579124"
}


@Article{info:doi/10.2196/17730,
author="Yang, Qing
and Hatch, Daniel
and Crowley, J. Matthew
and Lewinski, A. Allison
and Vaughn, Jacqueline
and Steinberg, Dori
and Vorderstrasse, Allison
and Jiang, Meilin
and Shaw, J. Ryan",
title="Digital Phenotyping Self-Monitoring Behaviors for Individuals With Type 2 Diabetes Mellitus: Observational Study Using Latent Class Growth Analysis",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jun",
day="11",
volume="8",
number="6",
pages="e17730",
keywords="digital phenotype",
keywords="latent class growth analysis",
keywords="type 2 diabetes",
keywords="self-management",
keywords="self-monitoring",
keywords="Mobile Health",
abstract="Background: Sustained self-monitoring and self-management behaviors are crucial to maintain optimal health for individuals with type 2 diabetes mellitus (T2DM). As smartphones and mobile health (mHealth) devices become widely available, self-monitoring using mHealth devices is an appealing strategy in support of successful self-management of T2DM. However, research indicates that engagement with mHealth devices decreases over time. Thus, it is important to understand engagement trajectories to provide varying levels of support that can improve self-monitoring and self-management behaviors. Objective: The aims of this study were to develop (1) digital phenotypes of the self-monitoring behaviors of patients with T2DM based on their engagement trajectory of using multiple mHealth devices, and (2) assess the association of individual digital phenotypes of self-monitoring behaviors with baseline demographic and clinical characteristics. Methods: This longitudinal observational feasibility study included 60 participants with T2DM who were instructed to monitor their weight, blood glucose, and physical activity using a wireless weight scale, phone-tethered glucometer, and accelerometer, respectively, over 6 months. We used  latent class growth analysis (LCGA) with multitrajectory modeling to associate the digital phenotypes of participants' self-monitoring behaviors based on their engagement trajectories with multiple mHealth devices. Associations between individual characteristics and digital phenotypes on participants' self-monitoring behavior were assessed by analysis of variance or the Chi square test. Results: The engagement with accelerometers to monitor daily physical activities was consistently high for all participants over time. Three distinct digital phenotypes were identified based on participants' engagement with the wireless weight scale and glucometer: (1) low and waning engagement group (24/60, 40\%), (2) medium engagement group (20/60, 33\%), and (3) consistently high engagement group (16/60, 27\%). Participants that were younger, female, nonwhite, had a low income, and with a higher baseline hemoglobin A1c level were more likely to be in the low and waning engagement group. Conclusions: We demonstrated how to digitally phenotype individuals' self-monitoring behavior based on their engagement trajectory with multiple mHealth devices. Distinct self-monitoring behavior groups were identified. Individual demographic and clinical characteristics were associated with different self-monitoring behavior groups. Future research should identify methods to provide tailored support for people with T2DM to help them better monitor and manage their condition. International Registered Report Identifier (IRRID): RR2-10.2196/13517 ",
doi="10.2196/17730",
url="https://mhealth.jmir.org/2020/6/e17730",
url="http://www.ncbi.nlm.nih.gov/pubmed/32525492"
}


@Article{info:doi/10.2196/16875,
author="Jacobson, C. Nicholas
and Summers, Berta
and Wilhelm, Sabine",
title="Digital Biomarkers of Social Anxiety Severity: Digital Phenotyping Using Passive Smartphone Sensors",
journal="J Med Internet Res",
year="2020",
month="May",
day="29",
volume="22",
number="5",
pages="e16875",
keywords="biomarkers",
keywords="machine learning",
keywords="technology assessment, biomedical",
keywords="social anxiety",
keywords="social anxiety disorder",
keywords="mobile phone",
abstract="Background: Social anxiety disorder is a highly prevalent and burdensome condition. Persons with social anxiety frequently avoid seeking physician support and rarely receive treatment. Social anxiety symptoms are frequently underreported and underrecognized, creating a barrier to the accurate assessment of these symptoms. Consequently, more research is needed to identify passive biomarkers of social anxiety symptom severity. Digital phenotyping, the use of passive sensor data to inform health care decisions, offers a possible method of addressing this assessment barrier. Objective: This study aims to determine whether passive sensor data acquired from smartphone data can accurately predict social anxiety symptom severity using a publicly available dataset. Methods: In this study, participants (n=59) completed self-report assessments of their social anxiety symptom severity, depressive symptom severity, positive affect, and negative affect. Next, participants installed an app, which passively collected data about their movement (accelerometers) and social contact (incoming and outgoing calls and texts) over 2 weeks. Afterward, these passive sensor data were used to form digital biomarkers, which were paired with machine learning models to predict participants' social anxiety symptom severity. Results: The results suggested that these passive sensor data could be utilized to accurately predict participants' social anxiety symptom severity (r=0.702 between predicted and observed symptom severity) and demonstrated discriminant validity between depression, negative affect, and positive affect. Conclusions: These results suggest that smartphone sensor data may be utilized to accurately detect social anxiety symptom severity and discriminate social anxiety symptom severity from depressive symptoms, negative affect, and positive affect. ",
doi="10.2196/16875",
url="http://www.jmir.org/2020/5/e16875/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32348284"
}


@Article{info:doi/10.2196/17326,
author="De Canni{\`e}re, H{\'e}l{\`e}ne
and Smeets, P. Christophe J.
and Schoutteten, Melanie
and Varon, Carolina
and Van Hoof, Chris
and Van Huffel, Sabine
and Groenendaal, Willemijn
and Vandervoort, Pieter",
title="Using Biosensors and Digital Biomarkers to Assess Response to Cardiac Rehabilitation: Observational Study",
journal="J Med Internet Res",
year="2020",
month="May",
day="20",
volume="22",
number="5",
pages="e17326",
keywords="wearables",
keywords="sensor",
keywords="6MWT",
keywords="rehabilitation",
keywords="cardiovascular",
abstract="Background: Cardiac rehabilitation (CR) is known for its beneficial effects on functional capacity and is a key component within current cardiovascular disease management strategies. In addition, a larger increase in functional capacity is accompanied by better clinical outcomes. However, not all patients respond in a similar way to CR. Therefore, a patient-tailored approach to CR could open up the possibility to achieve an optimal increase in functional capacity in every patient. Before treatment can be optimized, the differences in response of patients in terms of cardiac adaptation to exercise should first be understood. In addition, digital biomarkers to steer CR need to be identified. Objective: The aim of the study was to investigate the difference in cardiac response between patients characterized by a clear improvement in functional capacity and patients showing only a minor improvement following CR therapy. Methods: A total of 129 patients in CR performed a 6-minute walking test (6MWT) at baseline and during four consecutive short-term follow-up tests while being equipped with a wearable electrocardiogram (ECG) device. The 6MWTs were used to evaluate functional capacity. Patients were divided into high- and low-response groups, based on the improvement in functional capacity during the CR program. Commonly used heart rate parameters and cardiac digital biomarkers representative of the heart rate behavior during the 6MWT and their evolution over time were investigated. Results: All participating patients improved in functional capacity throughout the CR program (P<.001). The heart rate parameters, which are commonly used in practice, evolved differently for both groups throughout CR. The peak heart rate (HRpeak) from patients in the high-response group increased significantly throughout CR, while no change was observed in the low-response group (F4,92=8.321, P<.001). Similar results were obtained for the recovery heart rate (HRrec) values, which increased significantly over time during every minute of recuperation, for the high-response group (HRrec1: P<.001, HRrec2: P<.001, HRrec3: P<.001, HRrec4: P<.001, and HRrec5: P=.02). The other digital biomarkers showed that the evolution of heart rate behavior during a standardized activity test differed throughout CR between both groups. These digital biomarkers, derived from the continuous measurements, contribute to more in-depth insight into the progression of patients' cardiac responses. Conclusions: This study showed that when using wearable sensor technology, the differences in response of patients to CR can be characterized by means of commonly used heart rate parameters and digital biomarkers that are representative of cardiac response to exercise. These digital biomarkers, derived by innovative analysis techniques, allow for more in-depth insights into the cardiac response of cardiac patients during standardized activity. These results open up the possibility to optimized and more patient-tailored treatment strategies and to potentially improve CR outcome. ",
doi="10.2196/17326",
url="http://www.jmir.org/2020/5/e17326/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32432552"
}


@Article{info:doi/10.2196/13810,
author="Nag, Anish
and Haber, Nick
and Voss, Catalin
and Tamura, Serena
and Daniels, Jena
and Ma, Jeffrey
and Chiang, Bryan
and Ramachandran, Shasta
and Schwartz, Jessey
and Winograd, Terry
and Feinstein, Carl
and Wall, P. Dennis",
title="Toward Continuous Social Phenotyping: Analyzing Gaze Patterns in an Emotion Recognition Task for Children With Autism Through Wearable Smart Glasses",
journal="J Med Internet Res",
year="2020",
month="Apr",
day="22",
volume="22",
number="4",
pages="e13810",
keywords="autism spectrum disorder",
keywords="translational medicine",
keywords="eye tracking",
keywords="wearable technologies",
keywords="artificial intelligence",
keywords="machine learning",
keywords="precision health",
keywords="digital therapy",
abstract="Background: Several studies have shown that facial attention differs in children with autism. Measuring eye gaze and emotion recognition in children with autism is challenging, as standard clinical assessments must be delivered in clinical settings by a trained clinician. Wearable technologies may be able to bring eye gaze and emotion recognition into natural social interactions and settings. Objective: This study aimed to test: (1) the feasibility of tracking gaze using wearable smart glasses during a facial expression recognition task and (2) the ability of these gaze-tracking data, together with facial expression recognition responses, to distinguish children with autism from neurotypical controls (NCs). Methods: We compared the eye gaze and emotion recognition patterns of 16 children with autism spectrum disorder (ASD) and 17 children without ASD via wearable smart glasses fitted with a custom eye tracker. Children identified static facial expressions of images presented on a computer screen along with nonsocial distractors while wearing Google Glass and the eye tracker. Faces were presented in three trials, during one of which children received feedback in the form of the correct classification. We employed hybrid human-labeling and computer vision--enabled methods for pupil tracking and world--gaze translation calibration. We analyzed the impact of gaze and emotion recognition features in a prediction task aiming to distinguish children with ASD from NC participants. Results: Gaze and emotion recognition patterns enabled the training of a classifier that distinguished ASD and NC groups. However, it was unable to significantly outperform other classifiers that used only age and gender features, suggesting that further work is necessary to disentangle these effects. Conclusions: Although wearable smart glasses show promise in identifying subtle differences in gaze tracking and emotion recognition patterns in children with and without ASD, the present form factor and data do not allow for these differences to be reliably exploited by machine learning systems. Resolving these challenges will be an important step toward continuous tracking of the ASD phenotype. ",
doi="10.2196/13810",
url="http://www.jmir.org/2020/4/e13810/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32319961"
}


@Article{info:doi/10.2196/15028,
author="Busk, Jonas
and Faurholt-Jepsen, Maria
and Frost, Mads
and Bardram, E. Jakob
and Vedel Kessing, Lars
and Winther, Ole",
title="Forecasting Mood in Bipolar Disorder From Smartphone Self-assessments: Hierarchical Bayesian Approach",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Apr",
day="1",
volume="8",
number="4",
pages="e15028",
keywords="bipolar disorder",
keywords="mood",
keywords="early medical intervention",
keywords="digital phenotyping",
keywords="machine learning",
keywords="forecasting",
keywords="Bayesian analysis",
abstract="Background: Bipolar disorder is a prevalent mental health condition that is imposing significant burden on society. Accurate forecasting of symptom scores can be used to improve disease monitoring, enable early intervention, and eventually help prevent costly hospitalizations. Although several studies have examined the use of smartphone data to detect mood, only few studies deal with forecasting mood for one or more days. Objective: This study aimed to examine the feasibility of forecasting daily subjective mood scores based on daily self-assessments collected from patients with bipolar disorder via a smartphone-based system in a randomized clinical trial. Methods: We applied hierarchical Bayesian regression models, a multi-task learning method, to account for individual differences and forecast mood for up to seven days based on 15,975 smartphone self-assessments from 84 patients with bipolar disorder participating in a randomized clinical trial. We reported the results of two time-series cross-validation 1-day forecast experiments corresponding to two different real-world scenarios and compared the outcomes with commonly used baseline methods. We then applied the best model to evaluate a 7-day forecast. Results: The best performing model used a history of 4 days of self-assessment to predict future mood scores with historical mood being the most important predictor variable. The proposed hierarchical Bayesian regression model outperformed pooled and separate models in a 1-day forecast time-series cross-validation experiment and achieved the predicted metrics, R2=0.51 and root mean squared error of 0.32, for mood scores on a scale of ?3 to 3. When increasing the forecast horizon, forecast errors also increased and the forecast regressed toward the mean of data distribution. Conclusions: Our proposed method can forecast mood for several days with low error compared with common baseline methods. The applicability of a mood forecast in the clinical treatment of bipolar disorder has also been discussed. ",
doi="10.2196/15028",
url="https://mhealth.jmir.org/2020/4/e15028",
url="http://www.ncbi.nlm.nih.gov/pubmed/32234702"
}


@Article{info:doi/10.2196/16770,
author="Fagherazzi, Guy",
title="Deep Digital Phenotyping and Digital Twins for Precision Health: Time to Dig Deeper",
journal="J Med Internet Res",
year="2020",
month="Mar",
day="3",
volume="22",
number="3",
pages="e16770",
keywords="digital health",
keywords="digital epidemiology",
keywords="deep digital phenotyping",
keywords="digital orthodoxy",
keywords="precision medicine",
keywords="precision health",
keywords="personalized medicine",
keywords="digital phenotyping",
keywords="precision prevention",
keywords="big data",
keywords="omics",
keywords="digitosome",
keywords="data lake",
keywords="digital cohort",
doi="10.2196/16770",
url="https://www.jmir.org/2020/3/e16770",
url="http://www.ncbi.nlm.nih.gov/pubmed/32130138"
}


@Article{info:doi/10.2196/12452,
author="Aubourg, Timoth{\'e}e
and Demongeot, Jacques
and Provost, Herv{\'e}
and Vuillerme, Nicolas",
title="Circadian Rhythms in the Telephone Calls of Older Adults: Observational Descriptive Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Feb",
day="25",
volume="8",
number="2",
pages="e12452",
keywords="outgoing telephone call",
keywords="circadian rhythm",
keywords="older adults",
keywords="call-detail records",
keywords="digital phenotyping",
keywords="digital biomarkers",
keywords="digital health",
keywords="mhealth",
abstract="Background: Recent studies have thoughtfully and convincingly demonstrated the possibility of estimating the circadian rhythms of young adults' social activity by analyzing their telephone call-detail records (CDRs). In the field of health monitoring, this development may offer new opportunities for supervising a patient's health status by collecting objective, unobtrusive data about their daily social interactions. However, before considering this future perspective, whether and how similar results could be observed in other populations, including older ones, should be established. Objective: This study was designed specifically to address the circadian rhythms in the telephone calls of older adults. Methods: A longitudinal, 12-month dataset combining CDRs and questionnaire data from 26 volunteers aged 65 years or older was used to examine individual differences in the daily rhythms of telephone call activity. The study used outgoing CDRs only and worked with three specific telecommunication parameters: (1) call recipient (alter), (2) time of day, and (3) call duration. As did the studies involving young adults, we analyzed three issues: (1) the existence of circadian rhythms in the telephone call activity of older adults, (2) their persistence over time, and (3) the alter-specificity of calls by calculating relative entropy. Results: We discovered that older adults had their own specific circadian rhythms of outgoing telephone call activity whose salient features and preferences varied across individuals, from morning until night. We demonstrated that rhythms were consistent, as reflected by their persistence over time. Finally, results suggested that the circadian rhythms of outgoing telephone call activity were partly structured by how older adults allocated their communication time across their social network. Conclusions: Overall, these results are the first to have demonstrated the existence, persistence, and alter-specificity of the circadian rhythms of the outgoing telephone call activity of older adults. These findings suggest an opportunity to consider modern telephone technologies as potential sensors of daily activity. From a health care perspective, these sensors could be harnessed for unobtrusive monitoring purposes. ",
doi="10.2196/12452",
url="http://mhealth.jmir.org/2020/2/e12452/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32130156"
}


@Article{info:doi/10.2196/16409,
author="Rykov, Yuri
and Thach, Thuan-Quoc
and Dunleavy, Gerard
and Roberts, Charles Adam
and Christopoulos, George
and Soh, Chee-Kiong
and Car, Josip",
title="Activity Tracker--Based Metrics as Digital Markers of Cardiometabolic Health in Working Adults: Cross-Sectional Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jan",
day="31",
volume="8",
number="1",
pages="e16409",
keywords="mobile health",
keywords="metabolic cardiovascular syndrome",
keywords="fitness trackers",
keywords="wearable electronic devices",
keywords="Fitbit",
keywords="steps",
keywords="heart rate",
keywords="physical activity",
keywords="circadian rhythms",
keywords="sedentary behavior",
abstract="Background: Greater adoption of wearable devices with multiple sensors may enhance personalized health monitoring, facilitate early detection of some diseases, and further scale up population health screening. However, few studies have explored the utility of data from wearable fitness trackers in cardiovascular and metabolic disease risk prediction. Objective: This study aimed to investigate the associations between a range of activity metrics derived from a wearable consumer-grade fitness tracker and major modifiable biomarkers of cardiometabolic disease in a working-age population. Methods: This was a cross-sectional study of 83 working adults. Participants wore Fitbit Charge 2 for 21 consecutive days and went through a health assessment, including fasting blood tests. The following clinical biomarkers were collected: BMI, waist circumference, waist-to-hip ratio, blood pressure, triglycerides (TGs), high-density lipoprotein (HDL) and low-density lipoprotein cholesterol, and blood glucose. We used a range of wearable-derived metrics based on steps, heart rate (HR), and energy expenditure, including measures of stability of circadian activity rhythms, sedentary time, and time spent at various intensities of physical activity. Spearman rank correlation was used for preliminary analysis. Multiple linear regression adjusted for potential confounders was used to determine the extent to which each metric of activity was associated with continuous clinical biomarkers. In addition, pairwise multiple regression was used to investigate the significance and mutual dependence of activity metrics when two or more of them had significant association with the same outcome from the previous step of the analysis. Results: The participants were predominantly middle aged (mean age 44.3 years, SD 12), Chinese (62/83, 75\%), and male (64/83, 77\%). Blood biomarkers of cardiometabolic disease (HDL cholesterol and TGs) were significantly associated with steps-based activity metrics independent of age, gender, ethnicity, education, and shift work, whereas body composition biomarkers (BMI, waist circumference, and waist-to-hip ratio) were significantly associated with energy expenditure--based and HR-based metrics when adjusted for the same confounders. Steps-based interdaily stability of circadian activity rhythm was strongly associated with HDL (beta=5.4 per 10\% change; 95\% CI 1.8 to 9.0; P=.005) and TG (beta=?27.7 per 10\% change; 95\% CI ?48.4 to ?7.0; P=.01). Average daily steps were negatively associated with TG (beta=?6.8 per 1000 steps; 95\% CI ?13.0 to ?0.6; P=.04). The difference between average HR and resting HR was significantly associated with BMI (beta=?.5; 95\% CI ?1.0 to ?0.1; P=.01) and waist circumference (beta=?1.3; 95\% CI ?2.4 to ?0.2; P=.03). Conclusions: Wearable consumer-grade fitness trackers can provide acceptably accurate and meaningful information, which might be used in the risk prediction of cardiometabolic disease. Our results showed the beneficial effects of stable daily patterns of locomotor activity for cardiometabolic health. Study findings should be further replicated with larger population studies. ",
doi="10.2196/16409",
url="http://mhealth.jmir.org/2020/1/e16409/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32012098"
}


@Article{info:doi/10.2196/16790,
author="Yamada, Yasunori
and Shinkawa, Kaoru
and Shimmei, Keita",
title="Atypical Repetition in Daily Conversation on Different Days for Detecting Alzheimer Disease: Evaluation of Phone-Call Data From a Regular Monitoring Service",
journal="JMIR Ment Health",
year="2020",
month="Jan",
day="14",
volume="7",
number="1",
pages="e16790",
keywords="dementia",
keywords="Alzheimer disease",
keywords="speech analysis",
keywords="screening",
keywords="monitoring",
keywords="behavioral marker",
keywords="daily conversation",
abstract="Background: Identifying signs of Alzheimer disease (AD) through longitudinal and passive monitoring techniques has become increasingly important. Previous studies have succeeded in quantifying language dysfunctions and identifying AD from speech data collected during neuropsychological tests. However, whether and how we can quantify language dysfunction in daily conversation remains unexplored. Objective: The objective of this study was to explore the linguistic features that can be used for differentiating AD patients from daily conversations. Methods: We analyzed daily conversational data of seniors with and without AD obtained from longitudinal follow-up in a regular monitoring service (from n=15 individuals including 2 AD patients at an average follow-up period of 16.1 months; 1032 conversational data items obtained during phone calls and approximately 221 person-hours). In addition to the standard linguistic features used in previous studies on connected speech data during neuropsychological tests, we extracted novel features related to atypical repetition of words and topics reported by previous observational and descriptive studies as one of the prominent characteristics in everyday conversations of AD patients. Results: When we compared the discriminative power of AD, we found that atypical repetition in two conversations on different days outperformed other linguistic features used in previous studies on speech data during neuropsychological tests. It was also a better indicator than atypical repetition in single conversations as well as that in two conversations separated by a specific number of conversations. Conclusions: Our results show how linguistic features related to atypical repetition across days could be used for detecting AD from daily conversations in a passive manner by taking advantage of longitudinal data. ",
doi="10.2196/16790",
url="http://mental.jmir.org/2020/1/e16790/"
}


@Article{info:doi/10.2196/13433,
author="Garcia-Gancedo, Luis
and Kelly, L. Madeline
and Lavrov, Arseniy
and Parr, Jim
and Hart, Rob
and Marsden, Rachael
and Turner, R. Martin
and Talbot, Kevin
and Chiwera, Theresa
and Shaw, E. Christopher
and Al-Chalabi, Ammar",
title="Objectively Monitoring Amyotrophic Lateral Sclerosis Patient Symptoms During Clinical Trials With Sensors: Observational Study",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Dec",
day="20",
volume="7",
number="12",
pages="e13433",
keywords="amyotrophic lateral sclerosis",
keywords="objective symptom monitoring",
keywords="clinical trial",
keywords="physical activity",
keywords="digital phenotyping",
keywords="digital biomarker",
keywords="heart rate",
keywords="speech",
keywords="accelerometer",
keywords="wearable",
abstract="Background: Objective symptom monitoring of patients with Amyotrophic Lateral Sclerosis (ALS) has the potential to provide an important source of information to evaluate the impact of the disease on aspects of real-world functional capacity and activities of daily living in the home setting, providing useful objective outcome measures for clinical trials. Objective: This study aimed to investigate the feasibility of a novel digital platform for remote data collection of multiple symptoms---physical activity, heart rate variability (HRV), and digital speech characteristics---in 25 patients with ALS in an observational clinical trial setting to explore the impact of the devices on patients' everyday life and to record tolerability related to the devices and study procedures over 48 weeks. Methods: In this exploratory, noncontrolled, nondrug study, patients attended a clinical site visit every 3 months to perform activity reference tasks while wearing a sensor, to conduct digital speech tests and for conventional ALS monitoring. In addition, patients wore the sensor in their daily life for approximately 3 days every month for the duration of the study. Results: The amount and quality of digital speech data captured at the clinical sites were as intended, and there were no significant issues. All the home monitoring sensor data available were propagated through the system and were received as expected. However, the amount and quality of physical activity home monitoring data were lower than anticipated. A total of 3 or more days (or partial days) of data were recorded for 65\% of protocol time points, with no data collected for 24\% of time points. At baseline, 24 of 25 patients provided data, reduced to 13 of 18 patients at Week 48. Lower-than-expected quality HRV data were obtained, likely because of poor contact between the sensor and the skin. In total, 6 of 25 patients had mild or moderate adverse events (AEs) in the skin and subcutaneous tissue disorders category because of skin irritation caused by the electrode patch. There were no reports of serious AEs or deaths. Most patients found the sensor comfortable, with no or minimal impact on daily activities. Conclusions: The platform can measure physical activity in patients with ALS in their home environment; patients used the equipment successfully, and it was generally well tolerated. The quantity of home monitoring physical activity data was lower than expected, although it was sufficient to allow investigation of novel physical activity end points. Good-quality in-clinic speech data were successfully captured for analysis. Future studies using objective patient monitoring approaches, combined with the most current technological advances, may be useful to elucidate novel digital biomarkers of disease progression. ",
doi="10.2196/13433",
url="https://mhealth.jmir.org/2019/12/e13433",
url="http://www.ncbi.nlm.nih.gov/pubmed/31859676"
}


@Article{info:doi/10.2196/11643,
author="Ferreri, Florian
and Bourla, Alexis
and Peretti, Charles-Siegfried
and Segawa, Tomoyuki
and Jaafari, Nemat
and Mouchabac, St{\'e}phane",
title="How New Technologies Can Improve Prediction, Assessment, and Intervention in Obsessive-Compulsive Disorder (e-OCD): Review",
journal="JMIR Ment Health",
year="2019",
month="Dec",
day="10",
volume="6",
number="12",
pages="e11643",
keywords="obsessive-compulsive disorder",
keywords="ecological momentary assessment",
keywords="biofeedback",
keywords="digital biomarkers",
keywords="digital phenotyping",
keywords="mobile health",
keywords="virtual reality",
keywords="machine learning",
abstract="Background: New technologies are set to profoundly change the way we understand and manage psychiatric disorders, including obsessive-compulsive disorder (OCD). Developments in imaging and biomarkers, along with medical informatics, may well allow for better assessments and interventions in the future. Recent advances in the concept of digital phenotype, which involves using computerized measurement tools to capture the characteristics of a given psychiatric disorder, is one paradigmatic example. Objective: The impact of new technologies on health professionals' practice in OCD care remains to be determined. Recent developments could disrupt not just their clinical practices, but also their beliefs, ethics, and representations, even going so far as to question their professional culture. This study aimed to conduct an extensive review of new technologies in OCD. Methods: We conducted the review by looking for titles in the PubMed database up to December 2017 that contained the following terms: [Obsessive] AND [Smartphone] OR [phone] OR [Internet] OR [Device] OR [Wearable] OR [Mobile] OR [Machine learning] OR [Artificial] OR [Biofeedback] OR [Neurofeedback] OR [Momentary] OR [Computerized] OR [Heart rate variability] OR [actigraphy] OR [actimetry] OR [digital] OR [virtual reality] OR [Tele] OR [video]. Results: We analyzed 364 articles, of which 62 were included. Our review was divided into 3 parts: prediction, assessment (including diagnosis, screening, and monitoring), and intervention. Conclusions: The review showed that the place of connected objects, machine learning, and remote monitoring has yet to be defined in OCD. Smartphone assessment apps and the Web Screening Questionnaire demonstrated good sensitivity and adequate specificity for detecting OCD symptoms when compared with a full-length structured clinical interview. The ecological momentary assessment procedure may also represent a worthy addition to the current suite of assessment tools. In the field of intervention, CBT supported by smartphone, internet, or computer may not be more effective than that delivered by a qualified practitioner, but it is easy to use, well accepted by patients, reproducible, and cost-effective. Finally, new technologies are enabling the development of new therapies, including biofeedback and virtual reality, which focus on the learning of coping skills. For them to be used, these tools must be properly explained and tailored to individual physician and patient profiles. ",
doi="10.2196/11643",
url="https://mental.jmir.org/2019/12/e11643",
url="http://www.ncbi.nlm.nih.gov/pubmed/31821153"
}


@Article{info:doi/10.2196/12814,
author="Cormack, Francesca
and McCue, Maggie
and Taptiklis, Nick
and Skirrow, Caroline
and Glazer, Emilie
and Panagopoulos, Elli
and van Schaik, A. Tempest
and Fehnert, Ben
and King, James
and Barnett, H. Jennifer",
title="Wearable Technology for High-Frequency Cognitive and Mood Assessment in Major Depressive Disorder: Longitudinal Observational Study",
journal="JMIR Ment Health",
year="2019",
month="Nov",
day="18",
volume="6",
number="11",
pages="e12814",
keywords="depression",
keywords="cognition",
keywords="mood",
keywords="mobile health",
keywords="mHealth",
keywords="mobile apps",
keywords="ecological momentary assessment",
keywords="digital phenotyping",
keywords="digital biomarkers",
abstract="Background: Cognitive symptoms are common in major depressive disorder and may help to identify patients who need treatment or who are not experiencing adequate treatment response. Digital tools providing real-time data assessing cognitive function could help support patient treatment and remediation of cognitive and mood symptoms. Objective: The aim of this study was to examine feasibility and validity of a wearable high-frequency cognitive and mood assessment app over 6 weeks, corresponding to when antidepressant pharmacotherapy begins to show efficacy. Methods: A total of 30 patients (aged 19-63 years; 19 women) with mild-to-moderate depression participated in the study. The new Cognition Kit app was delivered via the Apple Watch, providing a high-resolution touch screen display for task presentation and logging responses. Cognition was assessed by the n-back task up to 3 times daily and depressed mood by 3 short questions once daily. Adherence was defined as participants completing at least 1 assessment daily. Selected tests sensitive to depression from the Cambridge Neuropsychological Test Automated Battery and validated questionnaires of depression symptom severity were administered on 3 occasions (weeks 1, 3, and 6). Exploratory analyses examined the relationship between mood and cognitive measures acquired in low- and high-frequency assessment. Results: Adherence was excellent for mood and cognitive assessments (95\% and 96\%, respectively), did not deteriorate over time, and was not influenced by depression symptom severity or cognitive function at study onset. Analyses examining the relationship between high-frequency cognitive and mood assessment and validated measures showed good correspondence. Daily mood assessments correlated moderately with validated depression questionnaires (r=0.45-0.69 for total daily mood score), and daily cognitive assessments correlated moderately with validated cognitive tests sensitive to depression (r=0.37-0.50 for mean n-back). Conclusions: This study supports the feasibility and validity of high-frequency assessment of cognition and mood using wearable devices over an extended period in patients with major depressive disorder. ",
doi="10.2196/12814",
url="https://mental.jmir.org/2019/11/e12814",
url="http://www.ncbi.nlm.nih.gov/pubmed/31738172"
}


@Article{info:doi/10.2196/12942,
author="Ford, Elizabeth
and Curlewis, Keegan
and Wongkoblap, Akkapon
and Curcin, Vasa",
title="Public Opinions on Using Social Media Content to Identify Users With Depression and Target Mental Health Care Advertising: Mixed Methods Survey",
journal="JMIR Ment Health",
year="2019",
month="Nov",
day="13",
volume="6",
number="11",
pages="e12942",
keywords="social media",
keywords="depression",
keywords="mental health",
keywords="machine learning",
keywords="public opinion",
keywords="social license",
keywords="survey",
abstract="Background: Depression is a common disorder that still remains underdiagnosed and undertreated in the UK National Health Service. Charities and voluntary organizations offer mental health services, but they are still struggling to promote these services to the individuals who need them. By analyzing social media (SM) content using machine learning techniques, it may be possible to identify which SM users are currently experiencing low mood, thus enabling the targeted advertising of mental health services to the individuals who would benefit from them. Objective: This study aimed to understand SM users' opinions of analysis of SM content for depression and targeted advertising on SM for mental health services. Methods: A Web-based, mixed methods, cross-sectional survey was administered to SM users aged 16 years or older within the United Kingdom. It asked participants about their demographics, their usage of SM, and their history of depression and presented structured and open-ended questions on views of SM content being analyzed for depression and views on receiving targeted advertising for mental health services. Results: A total of 183 participants completed the survey, and 114 (62.3\%) of them had previously experienced depression. Participants indicated that they posted less during low moods, and they believed that their SM content would not reflect their depression. They could see the possible benefits of identifying depression from SM content but did not believe that the risks to privacy outweighed these benefits. A majority of the participants would not provide consent for such analysis to be conducted on their data and considered it to be intrusive and exposing. Conclusions: In a climate of distrust of SM platforms' usage of personal data, participants in this survey did not perceive that the benefits of targeting advertisements for mental health services to individuals analyzed as having depression would outweigh the risks to privacy. Future work in this area should proceed with caution and should engage stakeholders at all stages to maximize the transparency and trustworthiness of such research endeavors. ",
doi="10.2196/12942",
url="http://mental.jmir.org/2019/11/e12942/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31719022"
}


@Article{info:doi/10.2196/14149,
author="Kim, Heejung
and Lee, SungHee
and Lee, SangEun
and Hong, Soyun
and Kang, HeeJae
and Kim, Namhee",
title="Depression Prediction by Using Ecological Momentary Assessment, Actiwatch Data, and Machine Learning: Observational Study on Older Adults Living Alone",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Oct",
day="16",
volume="7",
number="10",
pages="e14149",
keywords="elderly",
keywords="one-person household",
keywords="depression",
keywords="ecological momentary assessment",
keywords="actigraphy",
keywords="machine learning",
abstract="Background: Although geriatric depression is prevalent, diagnosis using self-reporting instruments has limitations when measuring the depressed mood of older adults in a community setting. Ecological momentary assessment (EMA) by using wearable devices could be used to collect data to classify older adults into depression groups. Objective: The objective of this study was to develop a machine learning algorithm to predict the classification of depression groups among older adults living alone. We focused on utilizing diverse data collected through a survey, an Actiwatch, and an EMA report related to depression. Methods: The prediction model using machine learning was developed in 4 steps: (1) data collection, (2) data processing and representation, (3) data modeling (feature engineering and selection), and (4) training and validation to test the prediction model. Older adults (N=47), living alone in community settings, completed an EMA to report depressed moods 4 times a day for 2 weeks between May 2017 and January 2018. Participants wore an Actiwatch that measured their activity and ambient light exposure every 30 seconds for 2 weeks. At baseline and the end of the 2-week observation, depressive symptoms were assessed using the Korean versions of the Short Geriatric Depression Scale (SGDS-K) and the Hamilton Depression Rating Scale (K-HDRS). Conventional classification based on binary logistic regression was built and compared with 4 machine learning models (the logit, decision tree, boosted trees, and random forest models). Results: On the basis of the SGDS-K and K-HDRS, 38\% (18/47) of the participants were classified into the probable depression group. They reported significantly lower scores of normal mood and physical activity and higher levels of white and red, green, and blue (RGB) light exposures at different degrees of various 4-hour time frames (all P<.05). Sleep efficiency was chosen for modeling through feature selection. Comparing diverse combinations of the selected variables, daily mean EMA score, daily mean activity level, white and RGB light at 4:00 pm to 8:00 pm exposure, and daily sleep efficiency were selected for modeling. Conventional classification based on binary logistic regression had a good model fit (accuracy: 0.705; precision: 0.770; specificity: 0.859; and area under receiver operating characteristic curve or AUC: 0.754). Among the 4 machine learning models, the logit model had the best fit compared with the others (accuracy: 0.910; precision: 0.929; specificity: 0.940; and AUC: 0.960). Conclusions: This study provides preliminary evidence for developing a machine learning program to predict the classification of depression groups in older adults living alone. Clinicians should consider using this method to identify underdiagnosed subgroups and monitor daily progression regarding treatment or therapeutic intervention in the community setting. Furthermore, more efforts are needed for researchers and clinicians to diversify data collection methods by using a survey, EMA, and a sensor. ",
doi="10.2196/14149",
url="http://mhealth.jmir.org/2019/10/e14149/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31621642"
}


@Article{info:doi/10.2196/12051,
author="Ramos, Munoz Roann
and Cheng, Ferrer Paula Glenda
and Jonas, Michael Stephan",
title="Validation of an mHealth App for Depression Screening and Monitoring (Psychologist in a Pocket): Correlational Study and Concurrence Analysis",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Sep",
day="16",
volume="7",
number="9",
pages="e12051",
keywords="mobile health",
keywords="depression",
keywords="validation",
keywords="Psychologist in a Pocket",
keywords="PiaP",
abstract="Background: Mobile health (mHealth) is a fast-growing professional sector. As of 2016, there were more than 259,000 mHealth apps available internationally. Although mHealth apps are growing in acceptance, relatively little attention and limited efforts have been invested to establish their scientific integrity through statistical validation. This paper presents the external validation of Psychologist in a Pocket (PiaP), an Android-based mental mHealth app which supports traditional approaches in depression screening and monitoring through the analysis of electronic text inputs in communication apps. Objective: The main objectives of the study were (1) to externally validate the construct of the depression lexicon of PiaP with standardized psychological paper-and-pencil tools and (2) to determine the comparability of PiaP, a new depression measure, with a psychological gold standard in identifying depression. Methods: College participants downloaded PiaP for a 2-week administration. Afterward, they were asked to complete 4 psychological depression instruments. Furthermore, 1-week and 2-week PiaP total scores (PTS) were correlated with (1) Beck Depression Index (BDI)-II and Center for Epidemiological Studies--Depression (CES-D) Scale for congruent construct validation, (2) Affect Balance Scale (ABS)--Negative Affect for convergent construct validation, and (3) Satisfaction With Life Scale (SWLS) and ABS--Positive Affect for divergent construct validation. In addition, concordance analysis between PiaP and BDI-II was performed. Results: On the basis of the Pearson product-moment correlation, significant positive correlations exist between (1) 1-week PTS and CES-D Scale, (2) 2-week PTS and BDI-II, and (3) PiaP 2-week PTS and SWLS. Concordance analysis (Bland-Altman plot and analysis) suggested that PiaP's approach to depression screening is comparable with the gold standard (BDI-II). Conclusions: The evaluation of mental health has historically relied on subjective measurements. With the integration of novel approaches using mobile technology (and, by extension, mHealth apps) in mental health care, the validation process becomes more compelling to ensure their accuracy and credibility. This study suggests that PiaP's approach to depression screening by analyzing electronic data is comparable with traditional and well-established depression instruments and can be used to augment the process of measuring depression symptoms. ",
doi="10.2196/12051",
url="https://mhealth.jmir.org/2019/9/e12051/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31538946"
}


@Article{info:doi/10.2196/14329,
author="Rieger, Agnes
and Gaines, Averi
and Barnett, Ian
and Baldassano, Frances Claudia
and Connolly Gibbons, Beth Mary
and Crits-Christoph, Paul",
title="Psychiatry Outpatients' Willingness to Share Social Media Posts and Smartphone Data for Research and Clinical Purposes: Survey Study",
journal="JMIR Form Res",
year="2019",
month="Aug",
day="29",
volume="3",
number="3",
pages="e14329",
keywords="social media",
keywords="smartphone",
keywords="outpatients",
keywords="psychiatry",
keywords="psychotherapy",
keywords="digital health",
keywords="mhealth",
keywords="digital phenotyping",
keywords="privacy",
keywords="user preferences",
abstract="Background: Psychiatry research has begun to leverage data collected from patients' social media and smartphone use. However, information regarding the feasibility of utilizing such data in an outpatient setting and the acceptability of such data in research and practice is limited. Objective: This study aimed at understanding the outpatients' willingness to have information from their social media posts and their smartphones used for clinical or research purposes. Methods: In this survey study, we surveyed patients (N=238) in an outpatient clinic waiting room. Willingness to share social media and passive smartphone data was summarized for the sample as a whole and broken down by sex, age, and race. Results: Most patients who had a social media account and who were receiving talk therapy treatment (74.4\%, 99/133) indicated that they would be willing to share their social media posts with their therapists. The percentage of patients willing to share passive smartphone data with researchers varied from 40.8\% (82/201) to 60.7\% (122/201) depending on the parameter, with sleep duration being the parameter with the highest percentage of patients willing to share. A total of 30.4\% of patients indicated that media stories of social media privacy breaches made them more hesitant about sharing passive smartphone data with researchers. Sex and race were associated with willingness to share smartphone data, with men and whites being the most willing to share. Conclusions: Our results indicate that most patients in a psychiatric outpatient setting would share social media and passive smartphone data and that further research elucidating patterns of willingness to share passive data is needed. ",
doi="10.2196/14329",
url="http://formative.jmir.org/2019/3/e14329/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31493326"
}


@Article{info:doi/10.2196/12785,
author="Piau, Antoine
and Wild, Katherine
and Mattek, Nora
and Kaye, Jeffrey",
title="Current State of Digital Biomarker Technologies for Real-Life, Home-Based Monitoring of Cognitive Function for Mild Cognitive Impairment to Mild Alzheimer Disease and Implications for Clinical Care: Systematic Review",
journal="J Med Internet Res",
year="2019",
month="Aug",
day="30",
volume="21",
number="8",
pages="e12785",
keywords="technology",
keywords="Alzheimer disease",
keywords="cognition disorders",
keywords="dementia",
keywords="older adults",
keywords="digital biomarkers",
keywords="digital phenotyping",
keywords="digital health",
abstract="Background: Among areas that have challenged the progress of dementia care has been the assessment of change in symptoms over time. Digital biomarkers are defined as objective, quantifiable, physiological, and behavioral data that are collected and measured by means of digital devices, such as embedded environmental sensors or wearables. Digital biomarkers provide an alternative assessment approach, as they allow objective, ecologically valid, and long-term follow-up with continuous assessment. Despite the promise of a multitude of sensors and devices that can be applied, there are no agreed-upon standards for digital biomarkers, nor are there comprehensive evidence-based results for which digital biomarkers may be demonstrated to be most effective. Objective: In this review, we seek to answer the following questions: (1) What is the evidence for real-life, home-based use of technologies for early detection and follow-up of mild cognitive impairment (MCI) or dementia? And (2) What transformation might clinicians expect in their everyday practices? Methods: A systematic search was conducted in PubMed, Cochrane, and Scopus databases for papers published from inception to July 2018. We searched for studies examining the implementation of digital biomarker technologies for mild cognitive impairment or mild Alzheimer disease follow-up and detection in nonclinic, home-based settings. All studies that included the following were examined: community-dwelling older adults (aged 65 years or older); cognitively healthy participants or those presenting with cognitive decline, from subjective cognitive complaints to early Alzheimer disease; a focus on home-based evaluation for noninterventional follow-up; and remote diagnosis of cognitive deterioration. Results: An initial sample of 4811 English-language papers were retrieved. After screening and review, 26 studies were eligible for inclusion in the review. These studies ranged from 12 to 279 participants and lasted between 3 days to 3.6 years. Most common reasons for exclusion were as follows: inappropriate setting (eg, hospital setting), intervention (eg, drugs and rehabilitation), or population (eg, psychiatry and Parkinson disease). We summarized these studies into four groups, accounting for overlap and based on the proposed technological solutions, to extract relevant data: (1) data from dedicated embedded or passive sensors, (2) data from dedicated wearable sensors, (3) data from dedicated or purposive technological solutions (eg, games or surveys), and (4) data derived from use of nondedicated technological solutions (eg, computer mouse movements). Conclusions: Few publications dealt with home-based, real-life evaluations. Most technologies were far removed from everyday life experiences and were not mature enough for use under nonoptimal or uncontrolled conditions. Evidence available from embedded passive sensors represents the most relatively mature research area, suggesting that some of these solutions could be proposed to larger populations in the coming decade. The clinical and research communities would benefit from increasing attention to these technologies going forward. ",
doi="10.2196/12785",
url="http://www.jmir.org/2019/8/e12785/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31471958"
}


@Article{info:doi/10.2196/12649,
author="Trifan, Alina
and Oliveira, Maryse
and Oliveira, Lu{\'i}s Jos{\'e}",
title="Passive Sensing of Health Outcomes Through Smartphones: Systematic Review of Current Solutions and Possible Limitations",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Aug",
day="23",
volume="7",
number="8",
pages="e12649",
keywords="smartphone",
keywords="mobile phone",
keywords="mhealth",
keywords="digital health",
keywords="digital medicine",
keywords="digital phenotyping",
keywords="health care",
keywords="self-management",
keywords="systematic review",
abstract="Background: Technological advancements, together with the decrease in both price and size of a large variety of sensors, has expanded the role and capabilities of regular mobile phones, turning them into powerful yet ubiquitous monitoring systems. At present, smartphones have the potential to continuously collect information about the users, monitor their activities and behaviors in real time, and provide them with feedback and recommendations. Objective: This systematic review aimed to identify recent scientific studies that explored the passive use of smartphones for generating health- and well-being--related outcomes. In addition, it explores users' engagement and possible challenges in using such self-monitoring systems. Methods: A systematic review was conducted, following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, to identify recent publications that explore the use of smartphones as ubiquitous health monitoring systems. We ran reproducible search queries on PubMed, IEEE Xplore, ACM Digital Library, and Scopus online databases and aimed to find answers to the following questions: (1) What is the study focus of the selected papers? (2) What smartphone sensing technologies and data are used to gather health-related input? (3) How are the developed systems validated? and (4) What are the limitations and challenges when using such sensing systems? Results: Our bibliographic research returned 7404 unique publications. Of these, 118 met the predefined inclusion criteria, which considered publication dates from 2014 onward, English language, and relevance for the topic of this review. The selected papers highlight that smartphones are already being used in multiple health-related scenarios. Of those, physical activity (29.6\%; 35/118) and mental health (27.9; 33/118) are 2 of the most studied applications. Accelerometers (57.7\%; 67/118) and global positioning systems (GPS; 40.6\%; 48/118) are 2 of the most used sensors in smartphones for collecting data from which the health status or well-being of its users can be inferred. Conclusions: One relevant outcome of this systematic review is that although smartphones present many advantages for the passive monitoring of users' health and well-being, there is a lack of correlation between smartphone-generated outcomes and clinical knowledge. Moreover, user engagement and motivation are not always modeled as prerequisites, which directly affects user adherence and full validation of such systems. ",
doi="10.2196/12649",
url="http://mhealth.jmir.org/2019/8/e12649/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31444874"
}


@Article{info:doi/10.2196/13209,
author="Doryab, Afsaneh
and Villalba, K. Daniella
and Chikersal, Prerna
and Dutcher, M. Janine
and Tumminia, Michael
and Liu, Xinwen
and Cohen, Sheldon
and Creswell, Kasey
and Mankoff, Jennifer
and Creswell, D. John
and Dey, K. Anind",
title="Identifying Behavioral Phenotypes of Loneliness and Social Isolation with Passive Sensing: Statistical Analysis, Data Mining and Machine Learning of Smartphone and Fitbit Data",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Jul",
day="24",
volume="7",
number="7",
pages="e13209",
keywords="mobile health",
keywords="loneliness",
keywords="machine learning",
keywords="statistical data analysis",
keywords="data mining",
keywords="digital phenotyping",
abstract="Background: Feelings of loneliness are associated with poor physical and mental health. Detection of loneliness through passive sensing on personal devices can lead to the development of interventions aimed at decreasing rates of loneliness. Objective: The aim of this study was to explore the potential of using passive sensing to infer levels of loneliness and to identify the corresponding behavioral patterns. Methods: Data were collected from smartphones and Fitbits (Flex 2) of 160 college students over a semester. The participants completed the University of California, Los Angeles (UCLA) loneliness questionnaire at the beginning and end of the semester. For a classification purpose, the scores were categorized into high (questionnaire score>40) and low (?40) levels of loneliness. Daily features were extracted from both devices to capture activity and mobility, communication and phone usage, and sleep behaviors. The features were then averaged to generate semester-level features. We used 3 analytic methods: (1) statistical analysis to provide an overview of loneliness in college students, (2) data mining using the Apriori algorithm to extract behavior patterns associated with loneliness, and (3) machine learning classification to infer the level of loneliness and the change in levels of loneliness using an ensemble of gradient boosting and logistic regression algorithms with feature selection in a leave-one-student-out cross-validation manner. Results: The average loneliness score from the presurveys and postsurveys was above 43 (presurvey SD 9.4 and postsurvey SD 10.4), and the majority of participants fell into the high loneliness category (scores above 40) with 63.8\% (102/160) in the presurvey and 58.8\% (94/160) in the postsurvey. Scores greater than 1 standard deviation above the mean were observed in 12.5\% (20/160) of the participants in both pre- and postsurvey scores. The majority of scores, however, fell between 1 standard deviation below and above the mean (pre=66.9\% [107/160] and post=73.1\% [117/160]). Our machine learning pipeline achieved an accuracy of 80.2\% in detecting the binary level of loneliness and an 88.4\% accuracy in detecting change in the loneliness level. The mining of associations between classifier-selected behavioral features and loneliness indicated that compared with students with low loneliness, students with high levels of loneliness were spending less time outside of campus during evening hours on weekends and spending less time in places for social events in the evening on weekdays (support=17\% and confidence=92\%). The analysis also indicated that more activity and less sedentary behavior, especially in the evening, was associated with a decrease in levels of loneliness from the beginning of the semester to the end of it (support=31\% and confidence=92\%). Conclusions: Passive sensing has the potential for detecting loneliness in college students and identifying the associated behavioral patterns. These findings highlight intervention opportunities through mobile technology to reduce the impact of loneliness on individuals' health and well-being. ",
doi="10.2196/13209",
url="http://mhealth.jmir.org/2019/7/e13209/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31342903"
}


@Article{info:doi/10.2196/12870,
author="Hanna-Pladdy, Brenda
and Gullapalli, Rao
and Chen, Hegang",
title="Functional Magnetic Resonance Imaging Biomarkers Predicting Cognitive Progression in Parkinson Disease: Protocol for a Prospective Longitudinal Cohort Study",
journal="JMIR Res Protoc",
year="2019",
month="Apr",
day="29",
volume="8",
number="4",
pages="e12870",
keywords="Parkinson disease",
keywords="cognition",
keywords="disease progression",
keywords="dementia",
keywords="mild cognitive impairment",
keywords="biomarkers",
keywords="functional neuroimaging",
abstract="Background: Cardinal features of Parkinson disease (PD) are motor symptoms, but nonmotor features such as mild cognitive impairment (MCI) are common early in the disease process. MCI can progress and convert to dementia in advanced stages, creating significant disability and reduced quality of life. The primary pathological substrate for cognitive decline in PD is unclear, and there are no reliable biomarkers predicting the risk of conversion to dementia. A subgroup of PD patients with visual hallucinations may display more rapid conversion to dementia, suggesting that regional markers of visuoperceptual dysfunction may be sensitive to pathologic density in posterior cortical regions. Objective: The purpose of this project is to characterize PD-MCI and evaluate the utility of genetic and neuroimaging biomarkers in predicting cognitive outcomes with a prospective longitudinal study. We will evaluate whether accelerated cognitive progression may be reflected in biomarkers of early posterior cortical changes reflective of $\alpha$-synuclein deposition. Methods: We will evaluate a cohort of early-stage PD patients with the following methods to predict cognitive progression: (1) serial neuropsychological evaluations including detailed visuoperceptual functioning across 4 years; (2) genetic analysis of SNCA ($\alpha$-synuclein), MAPT (microtubule-associated tau), and APOE (apolipoprotein E); (3) an event-related functional magnetic resonance imaging paradigm of object recognition memory; and (4) anatomical and regional brain activation changes (resting-state functional magnetic resonance imaging) across 4 years. Results: The project received funding from the National Institutes of Health in August 2017, and data collection began in February 2018. Enrollment is ongoing, and subjects will be evaluated annually for 4 years extended across a 5-year project including data analysis and image processing. Conclusions: Cognitive, genetic, and structural and functional magnetic resonance imaging will characterize neural network changes predictive of cognitive progression in PD across 4 years. Identification of biomarkers with sensitivity for early prediction and estimation of risk for conversion to dementia in PD will pave the way for effective intervention with neuroprotective therapies during the critical stage when treatment can have the greatest impact. International Registered Report Identifier (IRRID): DERR1-10.2196/12870 ",
doi="10.2196/12870",
url="http://www.researchprotocols.org/2019/4/e12870/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31033450"
}


@Article{info:doi/10.2196/13485,
author="Mandryk, Lee Regan
and Birk, Valentin Max",
title="The Potential of Game-Based Digital Biomarkers for Modeling Mental Health",
journal="JMIR Ment Health",
year="2019",
month="Apr",
day="23",
volume="6",
number="4",
pages="e13485",
keywords="digital games",
keywords="digital phenotyping",
keywords="mental health",
keywords="computational modeling",
keywords="big data",
keywords="video games",
keywords="biomarkers",
abstract="Background: Assessment for mental health is performed by experts using interview techniques, questionnaires, and test batteries and following standardized manuals; however, there would be myriad benefits if behavioral correlates could predict mental health and be used for population screening or prevalence estimations. A variety of digital sources of data (eg, online search data and social media posts) have been previously proposed as candidates for digital biomarkers in the context of mental health. Playing games on computers, gaming consoles, or mobile devices (ie, digital gaming) has become a leading leisure activity of choice and yields rich data from a variety of sources. Objective: In this paper, we argue that game-based data from commercial off-the-shelf games have the potential to be used as a digital biomarker to assess and model mental health and health decline. Although there is great potential in games developed specifically for mental health assessment (eg, Sea Hero Quest), we focus on data gathered ``in-the-wild'' from playing commercial off-the-shelf games designed primarily for entertainment. Methods: We argue that the activity traces left behind by natural interactions with digital games can be modeled using computational approaches for big data. To support our argument, we present an investigation of existing data sources, a categorization of observable traits from game data, and examples of potentially useful game-based digital biomarkers derived from activity traces. Results: Our investigation reveals different types of data that are generated from play and the sources from which these data can be accessed. Based on these insights, we describe five categories of digital biomarkers that can be derived from game-based data, including behavior, cognitive performance, motor performance, social behavior, and affect. For each type of biomarker, we describe the data type, the game-based sources from which it can be derived, its importance for mental health modeling, and any existing statistical associations with mental health that have been demonstrated in prior work. We end with a discussion on the limitations and potential of data from commercial off-the-shelf games for use as a digital biomarker of mental health. Conclusions: When people play commercial digital games, they produce significant volumes of high-resolution data that are not only related to play frequency, but also include performance data reflecting low-level cognitive and motor processing; text-based data that are indicative of the affective state; social data that reveal networks of relationships; content choice data that imply preferred genres; and contextual data that divulge where, when, and with whom the players are playing. These data provide a source for digital biomarkers that may indicate mental health. Produced by engaged human behavior, game data have the potential to be leveraged for population screening or prevalence estimations, leading to at-scale, nonintrusive assessment of mental health. ",
doi="10.2196/13485",
url="http://mental.jmir.org/2019/4/e13485/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31012857"
}


@Article{info:doi/10.2196/11029,
author="Cho, Chul-Hyun
and Lee, Taek
and Kim, Min-Gwan
and In, Peter Hoh
and Kim, Leen
and Lee, Heon-Jeong",
title="Mood Prediction of Patients With Mood Disorders by Machine Learning Using Passive Digital Phenotypes Based on the Circadian Rhythm: Prospective Observational Cohort Study",
journal="J Med Internet Res",
year="2019",
month="Apr",
day="17",
volume="21",
number="4",
pages="e11029",
keywords="mood disorder",
keywords="circadian rhythm",
keywords="projections and predictions",
keywords="machine learning",
keywords="digital phenotype",
keywords="wearable device",
abstract="Background: Virtually, all organisms on Earth have their own circadian rhythm, and humans are no exception. Circadian rhythms are associated with various human states, especially mood disorders, and disturbance of the circadian rhythm is known to be very closely related. Attempts have also been made to derive clinical implications associated with mood disorders using the vast amounts of digital log that is acquired by digital technologies develop and using computational analysis techniques. Objective: This study was conducted to evaluate the mood state or episode, activity, sleep, light exposure, and heart rate during a period of about 2 years by acquiring various digital log data through wearable devices and smartphone apps as well as conventional clinical assessments. We investigated a mood prediction algorithm developed with machine learning using passive data phenotypes based on circadian rhythms. Methods: We performed a prospective observational cohort study on 55 patients with mood disorders (major depressive disorder [MDD] and bipolar disorder type 1 [BD I] and 2 [BD II]) for 2 years. A smartphone app for self-recording daily mood scores and detecting light exposure (using the installed sensor) were provided. From daily worn activity trackers, digital log data of activity, sleep, and heart rate were collected. Passive digital phenotypes were processed into 130 features based on circadian rhythms, and a mood prediction algorithm was developed by random forest. Results: The mood state prediction accuracies for the next 3 days in all patients, MDD patients, BD I patients, and BD II patients were 65\%, 65\%, 64\%, and 65\% with 0.7, 0.69, 0.67, and 0.67 area under the curve (AUC) values, respectively. The accuracies of all patients for no episode (NE), depressive episode (DE), manic episode (ME), and hypomanic episode (HME) were 85.3\%, 87\%, 94\%, and 91.2\% with 0.87, 0.87, 0.958, and 0.912 AUC values, respectively. The prediction accuracy in BD II patients was distinctively balanced as high showing 82.6\%, 74.4\%, and 87.5\% of accuracy (with generally good sensitivity and specificity) with 0.919, 0.868, and 0.949 AUC values for NE, DE, and HME, respectively. Conclusions: On the basis of the theoretical basis of chronobiology, this study proposed a good model for future research by developing a mood prediction algorithm using machine learning by processing and reclassifying digital log data. In addition to academic value, it is expected that this study will be of practical help to improve the prognosis of patients with mood disorders by making it possible to apply actual clinical application owing to the rapid expansion of digital technology. ",
doi="10.2196/11029",
url="http://www.jmir.org/2019/4/e11029/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30994461"
}


@Article{info:doi/10.2196/12808,
author="Jauhiainen, Milla
and Puustinen, Juha
and Mehrang, Saeed
and Ruokolainen, Jari
and Holm, Anu
and Vehkaoja, Antti
and Nieminen, Hannu",
title="Identification of Motor Symptoms Related to Parkinson Disease Using Motion-Tracking Sensors at Home (K{\"A}VELI): Protocol for an Observational Case-Control Study",
journal="JMIR Res Protoc",
year="2019",
month="Mar",
day="27",
volume="8",
number="3",
pages="e12808",
keywords="Parkinson disease",
keywords="movement analysis",
keywords="gait",
keywords="wearable sensors",
keywords="smartphone",
keywords="home monitoring",
keywords="mobile phone",
abstract="Background: Clinical characterization of motion in patients with Parkinson disease (PD) is challenging: symptom progression, suitability of medication, and level of independence in the home environment can vary across time and patients. Appointments at the neurological outpatient clinic provide a limited understanding of the overall situation. In order to follow up these variations, longer-term measurements performed outside of the clinic setting could help optimize and personalize therapies. Several wearable sensors have been used to estimate the severity of symptoms in PD; however, longitudinal recordings, even for a short duration of a few days, are rare. Home recordings have the potential benefit of providing a more thorough and objective follow-up of the disease while providing more information about the possible need to change medications or consider invasive treatments. Objective: The primary objective of this study is to collect a dataset for developing methods to detect PD-related symptoms that are visible in walking patterns at home. The movement data are collected continuously and remotely at home during the normal lives of patients with PD as well as controls. The secondary objective is to use the dataset to study whether the registered medication intakes can be identified from the collected movement data by looking for and analyzing short-term changes in walking patterns. Methods: This paper described the protocol for an observational case-control study that measures activity using three different devices: (1) a smartphone with a built-in accelerometer, gyroscope, and phone orientation sensor, (2) a Movesense smart sensor to measure movement data from the wrist, and (3) a Forciot smart insole to measure the forces applied on the feet. The measurements are first collected during the appointment at the clinic conducted by a trained clinical physiotherapist. Subsequently, the subjects wear the smartphone at home for 3 consecutive days. Wrist and insole sensors are not used in the home recordings. Results: Data collection began in March 2018. Subject recruitment and data collection will continue in spring 2019. The intended sample size was 150 subjects. In 2018, we collected a sample of 103 subjects, 66 of whom were diagnosed with PD. Conclusions: This study aims to produce an extensive movement-sensor dataset recorded from patients with PD in various phases of the disease as well as from a group of control subjects for effective and impactful comparison studies. The study also aims to develop data analysis methods to monitor PD symptoms and the effects of medication intake during normal life and outside of the clinic setting. Further applications of these methods may include using them as tools for health care professionals to monitor PD remotely and applying them to other movement disorders. Trial Registration: ClinicalTrials.gov NCT03366558;?https://clinicaltrials.gov/ct2/show/NCT03366558? International Registered Report Identifier (IRRID): DERR1-10.2196/12808 ",
doi="10.2196/12808",
url="http://www.researchprotocols.org/2019/3/e12808/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30916665"
}


@Article{info:doi/10.2196/12171,
author="Pan, Yuan-Chien
and Lin, Hsiao-Han
and Chiu, Yu-Chuan
and Lin, Sheng-Hsuan
and Lin, Yu-Hsuan",
title="Temporal Stability of Smartphone Use Data: Determining Fundamental Time Unit and Independent Cycle",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Mar",
day="26",
volume="7",
number="3",
pages="e12171",
keywords="temporal stability",
keywords="smartphone use",
keywords="smartphone addiction",
keywords="smartphone",
keywords="mobile phone",
abstract="Background: Assessing human behaviors via smartphone for monitoring the pattern of daily behaviors has become a crucial issue in this century. Thus, a more accurate and structured methodology is needed for smartphone use research. Objective: The study aimed to investigate the duration of data collection needed to establish a reliable pattern of use, how long a smartphone use cycle could perpetuate by assessing maximum time intervals between 2 smartphone periods, and to validate smartphone use and use/nonuse reciprocity parameters. Methods: Using the Know Addiction database, we selected 33 participants and passively recorded their smartphone usage patterns for at least 8 weeks. We generated 4 parameters on the basis of smartphone use episodes, including total use frequency, total use duration, proactive use frequency, and proactive use duration. A total of 3 additional parameters (root mean square of successive differences, Control Index, and Similarity Index) were calculated to reflect impaired control and compulsive use. Results: Our findings included (1) proactive use duration correlated with subjective smartphone addiction scores, (2) a 2-week period of data collection is required to infer a 2-month period of smartphone use, and (3) smartphone use cycles with a time gap of 4 weeks between them are highly likely independent cycles. Conclusions: This study validated temporal stability for smartphone use patterns recorded by a mobile app. The results may provide researchers an opportunity to investigate human behaviors with more structured methods. ",
doi="10.2196/12171",
url="http://mhealth.jmir.org/2019/3/e12171/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30912751"
}


@Article{info:doi/10.2196/11190,
author="Hale, M. Timothy
and Guardigni, Viola
and Roitmann, Eva
and Vegreville, Matthieu
and Brawley, Brooke
and Woodbury, Erin
and Storer, W. Thomas
and Sax, E. Paul
and Montano, Monty",
title="Middle-Aged Men With HIV Have Diminished Accelerometry-Based Activity Profiles Despite Similar Lab-Measured Gait Speed: Pilot Study",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Feb",
day="01",
volume="7",
number="2",
pages="e11190",
keywords="aging",
keywords="digital biomarker",
keywords="gait speed",
keywords="HIV",
abstract="Background: People aging with HIV are living with increased risk for functional decline compared with uninfected adults of the same age. Early preclinical changes in biomarkers in middle-aged individuals at risk for mobility and functional decline are needed. Objective: This pilot study aims to compare measures of free-living activity with lab-based measures. In addition, we aim to examine differences in the activity level and patterns by HIV status. Methods: Forty-six men (23 HIV+, 23 HIV?) currently in the MATCH (Muscle and Aging Treated Chronic HIV) cohort study wore a consumer-grade wristband accelerometer continuously for 3 weeks. We used free-living activity to calculate the gait speed and time spent at different activity intensities. Accelerometer data were compared with lab-based gait speed using the 6-minute walk test (6-MWT). Plasma biomarkers were measured and biobehavioral questionnaires were administered. Results: HIV+ men more often lived alone (P=.02), reported more pain (P=.02), and fatigue (P=.048). In addition, HIV+ men had lower blood CD4/CD8 ratios (P<.001) and higher Veterans Aging Cohort Study Index scores (P=.04) and T-cell activation (P<.001) but did not differ in levels of inflammation (P=.30) or testosterone (P=.83). For all participants, accelerometer-based gait speed was significantly lower than the lab-based 6-MWT gait speed (P<.001). Moreover, accelerometer-based gait speed was significantly lower in HIV+ participants (P=.04) despite the absence of differences in the lab-based 6-MWT (P=.39). HIV+ participants spent more time in the lowest quartile of activity compared with uninfected (P=.01), who spent more time in the middle quartiles of activity (P=.02). Conclusions: Accelerometer-based assessment of gait speed and activity patterns are lower for asymptomatic men living with HIV compared with uninfected controls and may be useful as preclinical digital biomarkers that precede differences captured in lab-based measures. ",
doi="10.2196/11190",
url="http://mhealth.jmir.org/2019/2/e11190/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30707104"
}


@Article{info:doi/10.2196/11988,
author="Jaimini, Utkarshani
and Thirunarayan, Krishnaprasad
and Kalra, Maninder
and Venkataraman, Revathy
and Kadariya, Dipesh
and Sheth, Amit",
title="``How Is My Child's Asthma?'' Digital Phenotype and Actionable Insights for Pediatric Asthma",
journal="JMIR Pediatr Parent",
year="2018",
month="Nov",
day="30",
volume="1",
number="2",
pages="e11988",
keywords="digital phenotype",
keywords="actionable insights",
keywords="asthma control level",
keywords="asthma control test",
keywords="digital phenotype score",
keywords="controller compliance score",
keywords="mobile health",
abstract="Background: In the traditional asthma management protocol, a child meets with a clinician infrequently, once in 3 to 6 months, and is assessed using the Asthma Control Test questionnaire. This information is inadequate for timely determination of asthma control, compliance, precise diagnosis of the cause, and assessing the effectiveness of the treatment plan. The continuous monitoring and improved tracking of the child's symptoms, activities, sleep, and treatment adherence can allow precise determination of asthma triggers and a reliable assessment of medication compliance and effectiveness. Digital phenotyping refers to moment-by-moment quantification of the individual-level human phenotype in situ using data from personal digital devices, in particular, mobile phones. The kHealth kit consists of a mobile app, provided on an Android tablet, that asks timely and contextually relevant questions related to asthma symptoms, medication intake, reduced activity because of symptoms, and nighttime awakenings; a Fitbit to monitor activity and sleep; a Microlife Peak Flow Meter to monitor the peak expiratory flow and forced exhaled volume in 1 second; and a Foobot to monitor indoor air quality. The kHealth cloud stores personal health data and environmental data collected using Web services. The kHealth Dashboard interactively visualizes the collected data.   Objective: The objective of this study was to discuss the usability and feasibility of collecting clinically relevant data to help clinicians diagnose or intervene in a child's care plan by using the kHealth system for continuous and comprehensive monitoring of child's symptoms, activity, sleep pattern, environmental triggers, and compliance. The kHealth system helps in deriving actionable insights to help manage asthma at both the personal and cohort levels. The Digital Phenotype Score and Controller Compliance Score introduced in the study are the basis of ongoing work on addressing personalized asthma care and answer questions such as, ``How can I help my child better adhere to care instructions and reduce future exacerbation?'' Methods: The Digital Phenotype Score and Controller Compliance Score summarize the child's condition from the data collected using the kHealth kit to provide actionable insights. The Digital Phenotype Score formalizes the asthma control level using data about symptoms, rescue medication usage, activity level, and sleep pattern. The Compliance Score captures how well the child is complying with the treatment protocol. We monitored and analyzed data for 95 children, each recruited for a 1- or 3-month-long study. The Asthma Control Test scores obtained from the medical records of 57 children were used to validate the asthma control levels calculated using the Digital Phenotype Scores. Results: At the cohort level, we found asthma was very poorly controlled in 37\% (30/82) of the children, not well controlled in 26\% (21/82), and well controlled in 38\% (31/82). Among the very poorly controlled children (n=30), we found 30\% (9/30) were highly compliant toward their controller medication intake---suggesting a re-evaluation for change in medication or dosage---whereas 50\% (15/30) were poorly compliant and candidates for a more timely intervention to improve compliance to mitigate their situation. We observed a negative Kendall Tau correlation between Asthma Control Test scores and Digital Phenotype Score as ?0.509 (P<.01). Conclusions: kHealth kit is suitable for the collection of clinically relevant information from pediatric patients. Furthermore, Digital Phenotype Score and Controller Compliance Score, computed based on the continuous digital monitoring, provide the clinician with timely and detailed evidence of a child's asthma-related condition when compared with the Asthma Control Test scores taken infrequently during clinic visits. ",
doi="10.2196/11988",
url="http://pediatrics.jmir.org/2018/2/e11988/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31008446"
}


@Article{info:doi/10.2196/mhealth.9472,
author="Berrouiguet, Sofian
and Ram{\'i}rez, David
and Barrig{\'o}n, Luisa Mar{\'i}a
and Moreno-Mu{\~n}oz, Pablo
and Carmona Camacho, Rodrigo
and Baca-Garc{\'i}a, Enrique
and Art{\'e}s-Rodr{\'i}guez, Antonio",
title="Combining Continuous Smartphone Native Sensors Data Capture and Unsupervised Data Mining Techniques for Behavioral Changes Detection: A Case Series of the Evidence-Based Behavior (eB2) Study",
journal="JMIR Mhealth Uhealth",
year="2018",
month="Dec",
day="10",
volume="6",
number="12",
pages="e197",
keywords="behavioral changes",
keywords="data mining",
keywords="mental disorders",
keywords="sensors",
keywords="wearables",
abstract="Background: The emergence of smartphones, wearable sensor technologies, and smart homes allows the nonintrusive collection of activity data. Thus, health-related events, such as activities of daily living (ADLs; eg, mobility patterns, feeding, sleeping, ...) can be captured without patients' active participation. We designed a system to detect changes in the mobility patterns based on the smartphone's native sensors and advanced machine learning and signal processing techniques. Objective: The principal objective of this work is to assess the feasibility of detecting mobility pattern changes in a sample of outpatients with depression using the smartphone's sensors. The proposed method processed the data acquired by the smartphone using an unsupervised detection technique. Methods: In this study, 38 outpatients from the Hospital Fundaci{\'o}n Jim{\'e}nez D{\'i}az Psychiatry Department (Madrid, Spain) participated. The Evidence-Based Behavior (eB2) app was downloaded by patients on the day of recruitment and configured with the assistance of a physician. The app captured the following data: inertial sensors, physical activity, phone calls and message logs, app usage, nearby Bluetooth and Wi-Fi connections, and location. We applied a change-point detection technique to location data on a sample of 9 outpatients recruited between April 6, 2017 and December 14, 2017. The change-point detection was based only on location information, but the eB2 platform allowed for an easy integration of additional data. The app remained running in the background on patients' smartphone during the study participation. Results: The principal outcome measure was the identification of mobility pattern changes based on an unsupervised detection technique applied to the smartphone's native sensors data. Here, results from 5 patients' records are presented as a case series. The eB2 system detected specific mobility pattern changes according to the patients' activity, which may be used as indicators of behavioral and clinical state changes. Conclusions: The proposed technique could automatically detect changes in the mobility patterns of outpatients who took part in this study. Assuming these mobility pattern changes correlated with behavioral changes, we have developed a technique that may identify possible relapses or clinical changes. Nevertheless, it is important to point out that the detected changes are not always related to relapses and that some clinical changes cannot be detected by the proposed method. ",
doi="10.2196/mhealth.9472",
url="https://mhealth.jmir.org/2018/12/e197/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30530465"
}


@Article{info:doi/10.2196/10215,
author="Wilbur, Elizabeth Rachel
and Griffin, Spencer Jacob
and Sorensen, Mark
and Furberg, Daniel Robert",
title="Establishing Digital Biomarkers for Occupational Health Assessment in Commercial Salmon Fishermen: Protocol for a Mixed-Methods Study",
journal="JMIR Res Protoc",
year="2018",
month="Dec",
day="10",
volume="7",
number="12",
pages="e10215",
keywords="digital health",
keywords="digital biomarkers",
keywords="occupational health",
keywords="health and safety",
keywords="fishermen",
keywords="physiological health",
keywords="stress",
abstract="Background: Commercial salmon fishing in Alaska is one of the most dangerous occupations in the United States. Between 1992 and 2008, the average annual industry mortality rate was 128 deaths per 100,000 workers, and despite an increase in industry regulations, there has not been a significant decrease in mortality rate since 2000. Unpredictable fishing openings and fierce competition for limited resources result in periods of intense sleep deprivation and physical strain during the short commercial salmon season in Alaska. Objective: We hypothesize that the combined effect of sleep deprivation, intense physical workload, and significant short-term chronic stress may be deleterious to health in both the short- and long-term among commercial salmon drift gillnet fishermen in Alaska. The objective of this protocol is to determine the feasibility of the study design to test this hypothesis. Methods: The study design uses mixed methods and includes biometric monitoring consisting of heart rate variability, respiration, and movement data collected via a personal, wearable biometric device. Additional methods include observational data on activity, including duration and quality of sleep, weather, catch, and financial gain, as well as the collection of salivary cortisol. As such, the study will provide a holistic assessment of individual stress on multiple simultaneous timescales: immediately and continuously through the personal wearable biometric device, on the minute-hour level through the multiple daily collections of salivary cortisol, and by the hour-day through the use of participant and environment observational data. Results: Data collection was initiated in July 2017 and will extend through August 2019. Initial data collection has indicated that the methods outlined in this protocol are feasible and allow for effective collection of qualitative and quantitative data related to the psychological and physiological impact of Alaska commercial salmon fishing. Conclusions: We anticipate that the use of a biometric device will be crucial in establishing measures of stress and physical activity within a population and environment uniquely challenged by physical isolation, strong weather patterns, and the potential for significant financial gain by fishermen. The potential exists for individuals engaged long-term in the fishing industry, through repeated and extended exposure to periods of intense sleep deprivation and chronic stress, to be at increased risk of cardiovascular disease. International Registered Report Identifier (IRRID): DERR1-10.2196/10215 ",
doi="10.2196/10215",
url="http://www.researchprotocols.org/2018/12/e10215/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30530453"
}


@Article{info:doi/10.2196/jmir.9775,
author="Zulueta, John
and Piscitello, Andrea
and Rasic, Mladen
and Easter, Rebecca
and Babu, Pallavi
and Langenecker, A. Scott
and McInnis, Melvin
and Ajilore, Olusola
and Nelson, C. Peter
and Ryan, Kelly
and Leow, Alex",
title="Predicting Mood Disturbance Severity with Mobile Phone Keystroke Metadata: A BiAffect Digital Phenotyping Study",
journal="J Med Internet Res",
year="2018",
month="Jul",
day="20",
volume="20",
number="7",
pages="e241",
keywords="digital phenotype",
keywords="mHealth",
keywords="ecological momentary assessment",
keywords="keystroke dynamics",
keywords="bipolar disorder",
keywords="depression",
keywords="mania",
keywords="mobile phone",
abstract="Background: Mood disorders are common and associated with significant morbidity and mortality. Better tools are needed for their diagnosis and treatment. Deeper phenotypic understanding of these disorders is integral to the development of such tools. This study is the first effort to use passively collected mobile phone keyboard activity to build deep digital phenotypes of depression and mania. Objective: The objective of our study was to investigate the relationship between mobile phone keyboard activity and mood disturbance in subjects with bipolar disorders and to demonstrate the feasibility of using passively collected mobile phone keyboard metadata features to predict manic and depressive signs and symptoms as measured via clinician-administered rating scales. Methods: Using a within-subject design of 8 weeks, subjects were provided a mobile phone loaded with a customized keyboard that passively collected keystroke metadata. Subjects were administered the Hamilton Depression Rating Scale (HDRS) and Young Mania Rating Scale (YMRS) weekly. Linear mixed-effects models were created to predict HDRS and YMRS scores. The total number of keystrokes was 626,641, with a weekly average of 9791 (7861), and that of accelerometer readings was 6,660,890, with a weekly average 104,076 (68,912). Results: A statistically significant mixed-effects regression model for the prediction of HDRS-17 item scores was created: conditional R2=.63, P=.01. A mixed-effects regression model for YMRS scores showed the variance accounted for by random effect was zero, and so an ordinary least squares linear regression model was created: R2=.34, P=.001. Multiple significant variables were demonstrated for each measure. Conclusions: Mood states in bipolar disorder appear to correlate with specific changes in mobile phone usage. The creation of these models provides evidence for the feasibility of using passively collected keyboard metadata to detect and monitor mood disturbances. ",
doi="10.2196/jmir.9775",
url="http://www.jmir.org/2018/7/e241/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30030209"
}


@Article{info:doi/10.2196/jmir.9410,
author="Sano, Akane
and Taylor, Sara
and McHill, W. Andrew
and Phillips, JK Andrew
and Barger, K. Laura
and Klerman, Elizabeth
and Picard, Rosalind",
title="Identifying Objective Physiological Markers and Modifiable Behaviors for Self-Reported Stress and Mental Health Status Using Wearable Sensors and Mobile Phones: Observational Study",
journal="J Med Internet Res",
year="2018",
month="Jun",
day="08",
volume="20",
number="6",
pages="e210",
keywords="mobile health",
keywords="mood",
keywords="machine learning",
keywords="wearable electronic devices",
keywords="smartphone",
keywords="mobile phone",
keywords="mental health",
keywords="psychological stress",
abstract="Background: Wearable and mobile devices that capture multimodal data have the potential to identify risk factors for high stress and poor mental health and to provide information to improve health and well-being. Objective: We developed new tools that provide objective physiological and behavioral measures using wearable sensors and mobile phones, together with methods that improve their data integrity. The aim of this study was to examine, using machine learning, how accurately these measures could identify conditions of self-reported high stress and poor mental health and which of the underlying modalities and measures were most accurate in identifying those conditions. Methods: We designed and conducted the 1-month SNAPSHOT study that investigated how daily behaviors and social networks influence self-reported stress, mood, and other health or well-being-related factors. We collected over 145,000 hours of data from 201 college students (age: 18-25 years, male:female=1.8:1) at one university, all recruited within self-identified social groups. Each student filled out standardized pre- and postquestionnaires on stress and mental health; during the month, each student completed twice-daily electronic diaries (e-diaries), wore two wrist-based sensors that recorded continuous physical activity and autonomic physiology, and installed an app on their mobile phone that recorded phone usage and geolocation patterns. We developed tools to make data collection more efficient, including data-check systems for sensor and mobile phone data and an e-diary administrative module for study investigators to locate possible errors in the e-diaries and communicate with participants to correct their entries promptly, which reduced the time taken to clean e-diary data by 69\%. We constructed features and applied machine learning to the multimodal data to identify factors associated with self-reported poststudy stress and mental health, including behaviors that can be possibly modified by the individual to improve these measures. Results: We identified the physiological sensor, phone, mobility, and modifiable behavior features that were best predictors for stress and mental health classification. In general, wearable sensor features showed better classification performance than mobile phone or modifiable behavior features. Wearable sensor features, including skin conductance and temperature, reached 78.3\% (148/189) accuracy for classifying students into high or low stress groups and 87\% (41/47) accuracy for classifying high or low mental health groups. Modifiable behavior features, including number of naps, studying duration, calls, mobility patterns, and phone-screen-on time, reached 73.5\% (139/189) accuracy for stress classification and 79\% (37/47) accuracy for mental health classification. Conclusions: New semiautomated tools improved the efficiency of long-term ambulatory data collection from wearable and mobile devices. Applying machine learning to the resulting data revealed a set of both objective features and modifiable behavioral features that could classify self-reported high or low stress and mental health groups in a college student population better than previous studies and showed new insights into digital phenotyping. ",
doi="10.2196/jmir.9410",
url="http://www.jmir.org/2018/6/e210/",
url="http://www.ncbi.nlm.nih.gov/pubmed/29884610"
}


@Article{info:doi/10.2196/resprot.6919,
author="Aledavood, Talayeh
and Triana Hoyos, Maria Ana
and Alak{\"o}rkk{\"o}, Tuomas
and Kaski, Kimmo
and Saram{\"a}ki, Jari
and Isomets{\"a}, Erkki
and Darst, K. Richard",
title="Data Collection for Mental Health Studies Through Digital Platforms: Requirements and Design of a Prototype",
journal="JMIR Res Protoc",
year="2017",
month="Jun",
day="09",
volume="6",
number="6",
pages="e110",
keywords="data collection framework",
keywords="mental health",
keywords="digital phenotyping",
keywords="big data",
abstract="Background: Mental and behavioral disorders are the main cause of disability worldwide. However, their diagnosis is challenging due to a lack of reliable biomarkers; current detection is based on structured clinical interviews which can be biased by the patient's recall ability, affective state, changing in temporal frames, etc. While digital platforms have been introduced as a possible solution to this complex problem, there is little evidence on the extent of usability and usefulness of these platforms. Therefore, more studies where digital data is collected in larger scales are needed to collect scientific evidence on the capacities of these platforms. Most of the existing platforms for digital psychiatry studies are designed as monolithic systems for a certain type of study; publications from these studies focus on their results, rather than the design features of the data collection platform. Inevitably, more tools and platforms will emerge in the near future to fulfill the need for digital data collection for psychiatry. Currently little knowledge is available from existing digital platforms for future data collection platforms to build upon. Objective: The objective of this work was to identify the most important features for designing a digital platform for data collection for mental health studies, and to demonstrate a prototype platform that we built based on these design features. Methods: We worked closely in a multidisciplinary collaboration with psychiatrists, software developers, and data scientists and identified the key features which could guarantee short-term and long-term stability and usefulness of the platform from the designing stage to data collection and analysis of collected data. Results: The key design features that we identified were flexibility of access control, flexibility of data sources, and first-order privacy protection. We also designed the prototype platform Non-Intrusive Individual Monitoring Architecture (Niima), where we implemented these key design features. We described why each of these features are important for digital data collection for psychiatry, gave examples of projects where Niima was used or is going to be used in the future, and demonstrated how incorporating these design principles opens new possibilities for studies. Conclusions: The new methods of digital psychiatry are still immature and need further research. The design features we suggested are a first step to design platforms which can adapt to the upcoming requirements of digital psychiatry. ",
doi="10.2196/resprot.6919",
url="http://www.researchprotocols.org/2017/6/e110/",
url="http://www.ncbi.nlm.nih.gov/pubmed/28600276"
}


@Article{info:doi/10.2196/mental.5165,
author="Torous, John
and Kiang, V. Mathew
and Lorme, Jeanette
and Onnela, Jukka-Pekka",
title="New Tools for New Research in Psychiatry: A Scalable and Customizable Platform to Empower Data Driven Smartphone Research",
journal="JMIR Mental Health",
year="2016",
month="May",
day="05",
volume="3",
number="2",
pages="e16",
keywords="mental health",
keywords="schizophrenia",
keywords="evaluation",
keywords="smartphone",
keywords="informatics",
abstract="Background: A longstanding barrier to progress in psychiatry, both in clinical settings and research trials, has been the persistent difficulty of accurately and reliably quantifying disease phenotypes. Mobile phone technology combined with data science has the potential to offer medicine a wealth of additional information on disease phenotypes, but the large majority of existing smartphone apps are not intended for use as biomedical research platforms and, as such, do not generate research-quality data. Objective: Our aim is not the creation of yet another app per se but rather the establishment of a platform to collect research-quality smartphone raw sensor and usage pattern data. Our ultimate goal is to develop statistical, mathematical, and computational methodology to enable us and others to extract biomedical and clinical insights from smartphone data. Methods: We report on the development and early testing of Beiwe, a research platform featuring a study portal, smartphone app, database, and data modeling and analysis tools designed and developed specifically for transparent, customizable, and reproducible biomedical research use, in particular for the study of psychiatric and neurological disorders. We also outline a proposed study using the platform for patients with schizophrenia. Results: We demonstrate the passive data capabilities of the Beiwe platform and early results of its analytical capabilities. Conclusions: Smartphone sensors and phone usage patterns, when coupled with appropriate statistical learning tools, are able to capture various social and behavioral manifestations of illnesses, in naturalistic settings, as lived and experienced by patients. The ubiquity of smartphones makes this type of moment-by-moment quantification of disease phenotypes highly scalable and, when integrated within a transparent research platform, presents tremendous opportunities for research, discovery, and patient health. ",
doi="10.2196/mental.5165",
url="http://mental.jmir.org/2016/2/e16/",
url="http://www.ncbi.nlm.nih.gov/pubmed/27150677"
}