@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/10.2196/59209,
author="Wickramasekera, Nyantara
and Shackley, Phil
and Rowen, Donna",
title="Embedding a Choice Experiment in an Online Decision Aid or Tool: Scoping Review",
journal="J Med Internet Res",
year="2025",
month="Mar",
day="21",
volume="27",
pages="e59209",
keywords="decision aid",
keywords="decision tool",
keywords="discrete choice experiment",
keywords="conjoint analysis",
keywords="value clarification",
keywords="scoping review",
keywords="choice experiment",
keywords="database",
keywords="study",
keywords="article",
keywords="data charting",
keywords="narrative synthesis",
abstract="Background: Decision aids empower patients to understand how treatment options match their preferences. Choice experiments, a method to clarify values used within decision aids, present patients with hypothetical scenarios to reveal their preferences for treatment characteristics. Given the rise in research embedding choice experiments in decision tools and the emergence of novel developments in embedding methodology, a scoping review is warranted. Objective: This scoping review examines how choice experiments are embedded into decision tools and how these tools are evaluated, to identify best practices. Methods: This scoping review followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. Searches were conducted on MEDLINE, PsycInfo, and Web of Science. The methodology, development and evaluation details of decision aids were extracted and summarized using narrative synthesis. Results: Overall, 33 papers reporting 22 tools were included in the scoping review. These tools were developed for various health conditions, including musculoskeletal (7/22, 32\%), oncological (8/22, 36\%), and chronic conditions (7/22, 32\%). Most decision tools (17/22, 77\%) were developed in the United States, with the remaining tools originating in the Netherlands, United Kingdom, Canada, and Australia. The number of publications increased, with 73\% (16/22) published since 2015, peaking at 4 publications in 2019. The primary purpose of these tools (20/22, 91\%) was to help patients compare or choose treatments. Adaptive conjoint analysis was the most frequently used design type (10/22, 45\%), followed by conjoint analysis and discrete choice experiments (DCEs; both 4/22, 18\%), modified adaptive conjoint analysis (3/22, 14\%), and adaptive best-worst conjoint analysis (1/22, 5\%). The number of tasks varied depending on the design (6-12 for DCEs and adaptive conjoint vs 16-20 for conjoint analysis designs). Sawtooth software was commonly used (14/22, 64\%) to embed choice tasks. Four proof-of-concept embedding methods were identified: scenario analysis, known preference phenotypes, Bayesian collaborative filtering, and penalized multinomial logit model. After completing the choice tasks patients received tailored information, 73\% (16/22) of tools provided attribute importance scores, and 23\% (5/22) presented a ``best match'' treatment ranking. To convey probabilistic attributes, most tools (13/22, 59\%) used a combination of approaches, including percentages, natural frequencies, icon arrays, narratives, and videos. The tools were evaluated across diverse study designs (randomized controlled trials, mixed methods, and cohort studies), with sample sizes ranging from 23 to 743 participants. Over 40 different outcomes were included in the evaluations, with the decisional conflict scale being the most frequently used in 6 tools. Conclusions: This scoping review provides an overview of how choice experiments are embedded into decision tools. It highlights the lack of established best practices for embedding methods, with only 4 proof-of-concept methods identified. Furthermore, the review reveals a lack of consensus on outcome measures, emphasizing the need for standardized outcome selection for future evaluations. ",
doi="10.2196/59209",
url="https://www.jmir.org/2025/1/e59209"
}


@Article{info:doi/10.2196/46149,
author="Baroudi, Loubna
and Zernicke, Fredrick Ronald
and Tewari, Muneesh
and Carlozzi, E. Noelle
and Choi, Won Sung
and Cain, M. Stephen",
title="Using Wear Time for the Analysis of Consumer-Grade Wearables' Data: Case Study Using Fitbit Data",
journal="JMIR Mhealth Uhealth",
year="2025",
month="Mar",
day="21",
volume="13",
pages="e46149",
keywords="wear time",
keywords="wearables",
keywords="smartwatch",
keywords="mobile health",
keywords="physical activity",
keywords="engagement",
keywords="walking",
keywords="dataset",
keywords="wearable devices",
keywords="reliability",
keywords="behavior",
keywords="caregiver",
keywords="students",
keywords="Fitbit",
keywords="users",
abstract="Background: Consumer-grade wearables allow researchers to capture a representative picture of human behavior in the real world over extended periods. However, maintaining users' engagement remains a challenge and can lead to a decrease in compliance (eg, wear time in the context of wearable sensors) over time (eg, ``wearables' abandonment''). Objective: In this work, we analyzed datasets from diverse populations (eg, caregivers for various health issues, college students, and pediatric oncology patients) to quantify the impact that wear time requirements can have on study results. We found evidence that emphasizes the need to account for participants' wear time in the analysis of consumer-grade wearables data. In Aim 1, we demonstrate the sensitivity of parameter estimates to different data processing methods with respect to wear time. In Aim 2, we demonstrate that not all research questions necessitate the same wear time requirements; some parameter estimates are not sensitive to wear time. Methods: We analyzed 3 Fitbit datasets comprising 6 different clinical and healthy population samples. For Aim 1, we analyzed the sensitivity of average daily step count and average daily heart rate at the population sample and individual levels to different methods of defining ``valid'' days using wear time. For Aim 2, we evaluated whether some research questions can be answered with data from lower compliance population samples. We explored (1) the estimation of the average daily step count and (2) the estimation of the average heart rate while walking. Results: For Aim 1, we found that the changes in the population sample average daily step count could reach 2000 steps for different methods of analysis and were dependent on the wear time compliance of the sample. As expected, population samples with a low daily wear time (less than 15 hours of wear time per day) showed the most sensitivity to changes in methods of analysis. On the individual level, we observed that around 15\% of individuals had a difference in step count higher than 1000 steps for 4 of the 6 population samples analyzed when using different data processing methods. Those individual differences were higher than 3000 steps for close to 5\% of individuals across all population samples. Average daily heart rate appeared to be robust to changes in wear time. For Aim 2, we found that, for 5 population samples out of 6, around 11\% of individuals had enough data for the estimation of average heart rate while walking but not for the estimation of their average daily step count. Conclusions: We leveraged datasets from diverse populations to demonstrate the direct relationship between parameter estimates from consumer-grade wearable devices and participants' wear time. Our findings highlighted the importance of a thorough analysis of wear time when processing data from consumer-grade wearables to ensure the relevance and reliability of the associated findings. ",
doi="10.2196/46149",
url="https://mhealth.jmir.org/2025/1/e46149"
}


@Article{info:doi/10.2196/59792,
author="He, Rosemary
and Sarwal, Varuni
and Qiu, Xinru
and Zhuang, Yongwen
and Zhang, Le
and Liu, Yue
and Chiang, Jeffrey",
title="Generative AI Models in Time-Varying Biomedical Data: Scoping Review",
journal="J Med Internet Res",
year="2025",
month="Mar",
day="10",
volume="27",
pages="e59792",
keywords="generative artificial intelligence",
keywords="artificial intelligence",
keywords="time series",
keywords="electronic health records",
keywords="electronic medical records",
keywords="systematic reviews",
keywords="disease trajectory",
keywords="machine learning",
keywords="algorithms",
keywords="forecasting",
abstract="Background: Trajectory modeling is a long-standing challenge in the application of computational methods to health care. In the age of big data, traditional statistical and machine learning methods do not achieve satisfactory results as they often fail to capture the complex underlying distributions of multimodal health data and long-term dependencies throughout medical histories. Recent advances in generative artificial intelligence (AI) have provided powerful tools to represent complex distributions and patterns with minimal underlying assumptions, with major impact in fields such as finance and environmental sciences, prompting researchers to apply these methods for disease modeling in health care. Objective: While AI methods have proven powerful, their application in clinical practice remains limited due to their highly complex nature. The proliferation of AI algorithms also poses a significant challenge for nondevelopers to track and incorporate these advances into clinical research and application. In this paper, we introduce basic concepts in generative AI and discuss current algorithms and how they can be applied to health care for practitioners with little background in computer science. Methods: We surveyed peer-reviewed papers on generative AI models with specific applications to time-series health data. Our search included single- and multimodal generative AI models that operated over structured and unstructured data, physiological waveforms, medical imaging, and multi-omics data. We introduce current generative AI methods, review their applications, and discuss their limitations and future directions in each data modality. Results: We followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines and reviewed 155 articles on generative AI applications to time-series health care data across modalities. Furthermore, we offer a systematic framework for clinicians to easily identify suitable AI methods for their data and task at hand. Conclusions: We reviewed and critiqued existing applications of generative AI to time-series health data with the aim of bridging the gap between computational methods and clinical application. We also identified the shortcomings of existing approaches and highlighted recent advances in generative AI that represent promising directions for health care modeling. ",
doi="10.2196/59792",
url="https://www.jmir.org/2025/1/e59792"
}


@Article{info:doi/10.2196/49507,
author="van der Smissen, Doris
and Schreijer, A. Maud
and van Gemert-Pijnen, C. Lisette J. E. W.
and Verdaasdonk, M. Rudolf
and van der Heide, Agnes
and Korfage, J. Ida
and Rietjens, C. Judith A.",
title="Implementation of a Web-Based Program for Advance Care Planning and Evaluation of its Complexity With the Nonadoption, Abandonment, Scale-Up, Spread, And Sustainability (NASSS) Framework: Qualitative Evaluation Study",
journal="JMIR Aging",
year="2025",
month="Mar",
day="4",
volume="8",
pages="e49507",
keywords="eHealth",
keywords="web-based intervention",
keywords="implementation",
keywords="sustainability",
keywords="advance care planning",
keywords="NASSS framework",
keywords="nonadoption, abandonment, scale-up, spread, and sustainability framework",
keywords="health communication",
keywords="patient education",
keywords="patient-centered care",
abstract="Background: The implementation of eHealth applications often fails. The NASSS (nonadoption, abandonment, scale-up, spread, and sustainability) framework aims to identify complexities in eHealth applications; the more complex, the more risk of implementation failure. Objective: This study aimed to analyze the implementation of the web-based advance care planning (ACP) program ``Explore Your Preferences for Treatment and Care'' using the NASSS framework. Methods: The NASSS framework enables a systematic approach to improve the implementation of eHealth tools. It is aimed at generating a rich and situated analysis of complexities in multiple domains, based on thematic analysis of existing and newly collected data. It also aims at supporting individuals and organizations to handle these complexities. We used 6 of 7 domains of the NASSS framework (ie, condition, technology, value proposition, adopters, external context, and embedding and adaptation over time) leaving out ``organization,'' and analyzed the multimodal dataset of a web-based ACP program, its development and evaluation, including peer-reviewed publications, notes of stakeholder group meetings, and interviews with stakeholders. Results: This study showed that the web-based ACP program uses straightforward technology, is embedded in a well-established web-based health platform, and in general appears to generate a positive value for stakeholders. A complexity is the rather broad target population of the program. A potential complexity considers the limited insight into the extent to which health care professionals adopt the program. Awareness of the relevance of the web-based ACP program may still be improved among target populations of ACP and among health care professionals. Furthermore, the program may especially appeal to those who value individual autonomy, self-management, and an explicit and direct communicative approach. Conclusions: Relatively few complexities were identified considering the implementation of the web-based ACP program ``Explore Your Preferences for Treatment and Care.'' The program is evidence-based, freestanding, and well-maintained, with straightforward, well-understood technology. The program is expected to generate a positive value for different stakeholders. Complexities include the broad target population of the program and sociocultural factors. People with limited digital literacy may need support to use the program. Its uptake might be improved by increasing awareness of ACP and the program among a wider population of potential users and among health care professionals. Addressing these issues may guide future use and sustainability of the program. ",
doi="10.2196/49507",
url="https://aging.jmir.org/2025/1/e49507",
url="http://www.ncbi.nlm.nih.gov/pubmed/40053753"
}


@Article{info:doi/10.2196/63497,
author="Bernstein, E. Emily
and Daniel, E. Katharine
and Miyares, E. Peyton
and Hoeppner, S. Susanne
and Bentley, H. Kate
and Snorrason, Ivar
and Fisher, B. Lauren
and Greenberg, L. Jennifer
and Weingarden, Hilary
and Harrison, Oliver
and Wilhelm, Sabine",
title="Patterns of Skills Review in Smartphone Cognitive Behavioral Therapy for Depression: Observational Study of Intervention Content Use",
journal="JMIR Ment Health",
year="2025",
month="Feb",
day="24",
volume="12",
pages="e63497",
keywords="smartphone",
keywords="cognitive behavioral therapy",
keywords="engagement",
keywords="depression",
keywords="mental health",
keywords="Mindset",
keywords="mHealth",
keywords="mobile health",
keywords="app",
keywords="digital health",
keywords="mobile phone",
abstract="Background: Smartphones could enhance access to effective cognitive behavioral therapy (CBT). Users may frequently and flexibly access bite-size CBT content on personal devices, review and practice skills, and thereby achieve better outcomes. Objective: We explored the distribution of actual interactions participants had with therapeutic content in a trial of smartphone CBT for depression and whether interactions were within assigned treatment modules or revisits to prior module content (ie, between-module interactions). Methods: We examined the association between the number of within- and between-module interactions and baseline and end-of-treatment symptom severity during an 8-week, single-arm open trial of a therapist-guided CBT for depression mobile health app. Results: Interactions were more frequent early in treatment and modestly declined in later stages. Within modules, most participants consistently made more interactions than required to progress to the next module and tended to return to all types of content rather than focus on 1 skill. By contrast, only 15 of 26 participants ever revisited prior module content (median number of revisits=1, mode=0, IQR 0-4). More revisits were associated with more severe end-of-treatment symptom severity after controlling for pretreatment symptom severity (P<.05). Conclusions: The results suggest that the frequency of use is an insufficient metric of engagement, lacking the nuance of what users are engaging with and when during treatment. This lens is essential for developing personalized recommendations and yielding better treatment outcomes. Trial Registration: ClinicalTrials.gov NCT05386329; https://clinicaltrials.gov/study/NCT05386329?term=NCT05386329 ",
doi="10.2196/63497",
url="https://mental.jmir.org/2025/1/e63497"
}


@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/10.2196/60521,
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/10.2196/65099,
author="Terceiro, Luciana
and Mustafa, Imran Mudassir
and H{\"a}gglund, Maria
and Kharko, Anna",
title="Research Participants' Engagement and Retention in Digital Health Interventions Research: Protocol for Mixed Methods Systematic Review",
journal="JMIR Res Protoc",
year="2025",
month="Jan",
day="3",
volume="14",
pages="e65099",
keywords="clinical research informatics",
keywords="participant engagement",
keywords="participant retention",
keywords="clinical research",
keywords="mobile application",
keywords="digital platforms",
keywords="mobile phone",
abstract="Background: Digital health interventions have become increasingly popular in recent years, expanding the possibilities for treatment for various patient groups. In clinical research, while the design of the intervention receives close attention, challenges with research participant engagement and retention persist. This may be partially due to the use of digital health platforms, which may lack adequacy for participants. Objective: This systematic literature review aims to investigate the relationship between digital health platforms and participant engagement and retention in clinical research. It will map and analyze key definitions of engagement and retention, as well as identify design characteristics that influence them. Methods: We will carry out a mixed methods systematic literature review, analyzing qualitative and quantitative studies. The search strategy includes the electronic databases PubMed, IEEE Xplore, CINAHL, Scopus, Web of Science, APA PsycINFO, and the ACM Digital Library. The review will encompass studies published between January 2018 and June 2024. Criteria for inclusion will be the presence of digital health care interventions conducted through digital health platforms like websites, web and mobile apps used by patients, and informal caregivers as research participants. The main outcome will be a narrative analysis with key findings on the definitions of participant engagement and retention and critical factors that affect them. Quality assessment and appraisal will be done through the Mixed-Methods Assessment Tool. Data analysis and synthesis will follow the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 flow diagram. Quantitative data will be qualified and integrated into qualitative data, which will be analyzed using thematic analysis and synthesis. Results: The study expects to map and summarize critical definitions of participant engagement and retention, and the characteristics of digital health platforms that influence them. The systematic review is expected to be completed in June 2025. Conclusions: This systematic review will contribute to the growing discussion on how the design of digital health intervention platforms can promote participant engagement and retention in clinical research. Trial Registration: PROSPERO CRD42024561650; https://www.crd.york.ac.uk/prospero/display\_record.php?RecordID=561650 International Registered Report Identifier (IRRID): PRR1-10.2196/65099 ",
doi="10.2196/65099",
url="https://www.researchprotocols.org/2025/1/e65099"
}


@Article{info:doi/10.2196/53187,
author="Lopez-Alcalde, Jesus
and Wieland, Susan L.
and Yan, Yuqian
and Barth, J{\"u}rgen
and Khami, Reza Mohammad
and Shivalli, Siddharudha
and Lokker, Cynthia
and Rai, Kaur Harleen
and Macharia, Paul
and Yun, Sergi
and Lang, Elvira
and Bwanika Naggirinya, Agnes
and Campos-Asensio, Concepci{\'o}n
and Ahmadian, Leila
and Witt, M. Claudia",
title="Methodological Challenges in Randomized Controlled Trials of mHealth Interventions: Cross-Sectional Survey Study and Consensus-Based Recommendations",
journal="J Med Internet Res",
year="2024",
month="Dec",
day="19",
volume="26",
pages="e53187",
keywords="digital health",
keywords="eHealth",
keywords="mobile health",
keywords="mHealth",
keywords="randomized controlled trial",
keywords="survey",
keywords="recommendations",
keywords="intervention integrity",
keywords="adherence",
keywords="consensus",
keywords="mobile phone",
abstract="Background: Mobile health (mHealth) refers to using mobile communication devices such as smartphones to support health, health care, and public health. mHealth interventions have their own nature and characteristics that distinguish them from traditional health care interventions, including drug interventions. Thus, randomized controlled trials (RCTs) of mHealth interventions present specific methodological challenges. Identifying and overcoming those challenges is essential to determine whether mHealth interventions improve health outcomes. Objective: We aimed to identify specific methodological challenges in RCTs testing mHealth interventions' effects and develop consensus-based recommendations to address selected challenges. Methods: A 2-phase participatory research project was conducted. First, we sent a web-based survey to authors of mHealth RCTs. Survey respondents rated on a 5-point scale how challenging they found 21 methodological aspects in mHealth RCTs compared to non-mHealth RCTs. Nonsystematic searches until June 2022 informed the selection of the methodological challenges listed in the survey. Second, a subset of survey respondents participated in an online workshop to discuss recommendations to address selected methodological aspects identified in the survey. Finally, consensus-based recommendations were developed based on the workshop discussion and email interaction. Results: We contacted 1535 authors of mHealth intervention RCTs, of whom 80 (5.21\%) completed the survey. Most respondents (74/80, 92\%) identified at least one methodological aspect as more or much more challenging in mHealth RCTs. The aspects most frequently reported as more or much more challenging were those related to mHealth intervention integrity, that is, the degree to which the study intervention was implemented as intended, in particular managing low adherence to the mHealth intervention (43/77, 56\%), defining adherence (39/79, 49\%), measuring adherence (33/78, 42\%), and determining which mHealth intervention components are used or received by the participant (31/75, 41\%). Other challenges were also frequent, such as analyzing passive data (eg, data collected from smartphone sensors; 24/58, 41\%) and verifying the participants' identity during recruitment (28/68, 41\%). In total, 11 survey respondents participated in the subsequent workshop (n=8, 73\% had been involved in at least 2 mHealth RCTs). We developed 17 consensus-based recommendations related to the following four categories: (1) how to measure adherence to the mHealth intervention (7 recommendations), (2) defining adequate adherence (2 recommendations), (3) dealing with low adherence rates (3 recommendations), and (4) addressing mHealth intervention components (5 recommendations). Conclusions: RCTs of mHealth interventions have specific methodological challenges compared to those of non-mHealth interventions, particularly those related to intervention integrity. Following our recommendations for addressing these challenges can lead to more reliable assessments of the effects of mHealth interventions on health outcomes. ",
doi="10.2196/53187",
url="https://www.jmir.org/2024/1/e53187"
}


@Article{info:doi/10.2196/55712,
author="Portillo-Van Diest, Ana
and Mortier, Philippe
and Ballester, Laura
and Amigo, Franco
and Carrasco, Paula
and Falc{\'o}, Raquel
and Gili, Margalida
and Kiekens, Glenn
and H Machancoses, Francisco
and Piqueras, A. Jose
and Rebagliato, Marisa
and Roca, Miquel
and Rodr{\'i}guez-Jim{\'e}nez, T{\'i}scar
and Alonso, Jordi
and Vilagut, Gemma",
title="Ecological Momentary Assessment of Mental Health Problems Among University Students: Data Quality Evaluation Study",
journal="J Med Internet Res",
year="2024",
month="Dec",
day="10",
volume="26",
pages="e55712",
keywords="experience sampling method",
keywords="ecological momentary assessment",
keywords="mental health",
keywords="university students",
keywords="participation",
keywords="compliance",
keywords="reliability",
keywords="sensitivity analysis",
keywords="mobile phone",
abstract="Background: The use of ecological momentary assessment (EMA) designs has been on the rise in mental health epidemiology. However, there is a lack of knowledge of the determinants of participation in and compliance with EMA studies, reliability of measures, and underreporting of methodological details and data quality indicators. Objective: This study aims to evaluate the quality of EMA data in a large sample of university students by estimating participation rate and mean compliance, identifying predictors of individual-level participation and compliance, evaluating between- and within-person reliability of measures of negative and positive affect, and identifying potential careless responding. Methods: A total of 1259 university students were invited to participate in a 15-day EMA study on mental health problems. Logistic and Poisson regressions were used to investigate the associations between sociodemographic factors, lifetime adverse experiences, stressful events in the previous 12 months, and mental disorder screens and EMA participation and compliance. Multilevel reliability and intraclass correlation coefficients were obtained for positive and negative affect measures. Careless responders were identified based on low compliance or individual reliability coefficients. Results: Of those invited, 62.1\% (782/1259) participated in the EMA study, with a mean compliance of 76.9\% (SD 27.7\%). Participation was higher among female individuals (odds ratio [OR] 1.41, 95\% CI 1.06-1.87) and lower among those aged ?30 years (OR 0.20, 95\% CI 0.08-0.43 vs those aged 18-21 years) and those who had experienced the death of a friend or family member in the previous 12 months (OR 0.73, 95\% CI 0.57-0.94) or had a suicide attempt in the previous 12 months (OR 0.26, 95\% CI 0.10-0.64). Compliance was particularly low among those exposed to sexual abuse before the age of 18 years (exponential of $\beta$=0.87) or to sexual assault or rape in the previous year (exponential of $\beta$=0.80) and among those with 12-month positive alcohol use disorder screens (exponential of $\beta$=0.89). Between-person reliability of negative and positive affect was strong (RkRn>0.97), whereas within-person reliability was fair to moderate (Rcn>0.43). Of all answered assessments, 0.86\% (291/33,626) were flagged as careless responses because the response time per item was <1 second or the participants gave the same response to all items. Of the participants, 17.5\% (137/782) could be considered careless responders due to low compliance (<25/56, 45\%) or very low to null individual reliability (raw Cronbach $\alpha$<0.11) for either negative or positive affect. Conclusions: Data quality assessments should be carried out in EMA studies in a standardized manner to provide robust conclusions to advance the field. Future EMA research should implement strategies to mitigate nonresponse bias as well as conduct sensitivity analyses to assess possible exclusion of careless responders. ",
doi="10.2196/55712",
url="https://www.jmir.org/2024/1/e55712",
url="http://www.ncbi.nlm.nih.gov/pubmed/39657180"
}


@Article{info:doi/10.2196/52110,
author="Bermejo-Mart{\'i}nez, Gemma
and Juli{\'a}n, Antonio Jos{\'e}
and Villanueva-Blasco, Jos{\'e} V{\'i}ctor
and Aibar, Alberto
and Corral-Ab{\'o}s, Ana
and Abarca-Sos, Alberto
and Generelo, Eduardo
and Mur, Melania
and Bueno, Manuel
and Ferrer, Elisa
and Artero, Isabel
and Garc{\'i}a-Gonz{\'a}lez, Luis
and Murillo-Pardo, Berta
and Ferriz, Roberto
and Menal-Puey, Susana
and Marques-Lopes, Iva
and Faj{\'o}-Pascual, Marta
and Ibor-Bernalte, Eduardo
and Zaragoza Casterad, Javier",
title="Development of a Web Platform to Facilitate the Implementation and Evaluation of Health Promoting Schools: Protocol for a Double Diamond Design Approach",
journal="JMIR Res Protoc",
year="2024",
month="Nov",
day="20",
volume="13",
pages="e52110",
keywords="web platform",
keywords="health promoting schools",
keywords="co-design process",
keywords="Double Diamond Design Model",
keywords="implementation processes.",
abstract="Background: Health Promoting Schools (HPS) have emerged as a powerful framework to promote healthy behaviors in many countries. However, HPS still present several challenges, highlighting the excessive workload involved in the accreditation, design, implementation, and evaluation processes. In this sense, a resource to facilitate the implementation processes may have a positive impact on the support of HPS. Objective: The aim of this study was to describe the co-design processes undertaken and resulting learnings to develop the Red Escuelas Promotoras de Salud (network of health promoting schools; REDEPS)-Gestion platform to facilitate the accreditation, design, implementation procedures, and evaluation processes of the Aragon's Health-Promoting School Network. Methods: The Double Diamond Design Approach was used to co-design this web-platform. The different stakeholders that participated in this co-design, progressed through a 4-stage reflective phase, to discover, define, develop, and deliver the REDEPS-Gestion platform. Results: Participants agreed that the functions of the REDEPS-Gestion platform should permit the management of both the educational centers and the administration such as accreditation processes, definition and review intervention projects, and preparation and review of the different progress reports to evaluate the HPS. Despite co-design being a well-established approach to creative practice, especially within the public sector, some challenges emerged during the co-design process, such as engaging and facilitating stakeholders' participation or the complexity of combining the interests of all stakeholders. This approach allowed us to identify the main barriers for future users and implement platform improvements. Conclusions: We hope that the REDEPS-Gestion platform will therefore be able to contribute to facilitating the implementation of HPS. The Double Diamond Design Approach used to co-design this web platform was an efficient and feasible methodological design approach. The REDEPS-Gestion platform will facilitate HPS implementation in Aragon as well as all the processes involving HPS. Future work will determine its effectiveness in improving HPS implementation. International Registered Report Identifier (IRRID): DERR1-10.2196/52110 ",
doi="10.2196/52110",
url="https://www.researchprotocols.org/2024/1/e52110",
url="http://www.ncbi.nlm.nih.gov/pubmed/39566054"
}


@Article{info:doi/10.2196/59155,
author="Kissler, Katherine
and Phillippi, C. Julia
and Erickson, Elise
and Holmes, Leah
and Tilden, Ellen",
title="Collecting Real-Time Patient-Reported Outcome Data During Latent Labor: Feasibility Study of the MyCap Mobile App in Prospective Person-Centered Research",
journal="JMIR Form Res",
year="2024",
month="Nov",
day="8",
volume="8",
pages="e59155",
keywords="patient-reported outcomes",
keywords="survey methods",
keywords="smartphone",
keywords="labor onset",
keywords="prodromal symptoms",
keywords="prospective studies",
abstract="Background: The growing emphasis on patient experience in medical research has increased the focus on patient-reported outcomes and symptom measures. However, patient-reported outcomes data are subject to recall bias, limiting reliability. Patient-reported data are most valid when reported by patients in real time; however, this type of data is difficult to collect from patients experiencing acute health events such as labor. Mobile technologies such as the MyCap app, integrated with the REDCap (Research Electronic Data Capture) platform, have emerged as tools for collecting patient-generated health data in real time offering potential improvements in data quality and relevance. Objective: This study aimed to evaluate the feasibility of using MyCap for real-time, patient-reported data collection during latent labor. The objective was to assess the usability of MyCap in characterizing patient experiences during this acute health event and to identify any challenges in data collection that could inform future research. Methods: In this descriptive cohort study, we quantified and characterized data collected prospectively through MyCap and the extent to which participants engaged with the app as a research tool for collecting patient-reported data in real time. Longitudinal quantitative and qualitative surveys were sent to (N=18) enrolled patients with term pregnancies planning vaginal birth at Oregon Health Sciences University. Participants were trained in app use prenatally. Then participants were invited to initiate the research survey on their personal smartphone via MyCap when they experienced labor symptoms and were asked to return to MyCap every 3 hours to provide additional longitudinal symptom data. Results: Out of 18 enrolled participants, 17 completed the study. During latent labor, 13 (76.5\%) participants (all those who labored at home and two-thirds of those who were induced) recorded at least 1 symptom report during latent labor. A total of 191 quantitative symptom reports (mean of 10 per participant) were recorded. The most commonly reported symptoms were fatigue, contractions, and pain, with nausea and diarrhea being less frequent but more intense. Four participants recorded qualitative data during labor and 14 responded to qualitative prompts in the postpartum period. The study demonstrated that MyCap could effectively capture real-time patient-reported data during latent labor, although qualitative data collection during active symptoms was less robust. Conclusions: MyCap is a feasible tool for collecting prospective data on patient-reported symptoms during latent labor. Participants engaged actively with quantitative symptom reporting, though qualitative data collection was more challenging. The use of MyCap appears to reduce recall bias and facilitate more accurate data collection for patient-reported symptoms during acute health events outside of health care settings. Future research should explore strategies to enhance qualitative data collection and assess the tool's usability across more diverse populations and disease states. ",
doi="10.2196/59155",
url="https://formative.jmir.org/2024/1/e59155"
}


@Article{info:doi/10.2196/63776,
author="Saliasi, Ina
and Lan, Romain
and Rhanoui, Maryem
and Fraticelli, Laurie
and Viennot, St{\'e}phane
and Tardivo, Delphine
and Cl{\'e}ment, C{\'e}line
and du Sartz de Vigneulles, Benjamin
and Bernard, Sandie
and Darlington-Bernard, Adeline
and Dussart, Claude
and Bourgeois, Denis
and Carrouel, Florence",
title="French Version of the User Mobile Application Rating Scale: Adaptation and Validation Study",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Oct",
day="24",
volume="12",
pages="e63776",
keywords="mHealth",
keywords="mobile health",
keywords="mobile health apps",
keywords="eHealth",
keywords="Mobile Application Rating Scale, user version",
keywords="mobile apps",
keywords="quality assessment tool",
keywords="uMARS",
abstract="Background: Managing noncommunicable diseases effectively requires continuous coordination and monitoring, often facilitated by eHealth technologies like mobile health (mHealth) apps. The end-user version of the Mobile Application Rating Scale is a valuable tool for assessing the quality of mHealth apps from the user perspective. However, the absence of a French version restricts its use in French-speaking countries, where the evaluation and regulation of mHealth apps are still lacking, despite the increasing number of apps and their strong relevance in health care. Objective: This study aims to translate and culturally adapt a French version of the user Mobile Application Rating Scale (uMARS-F) and to test its overall and internal reliability. Methods: Cross-cultural adaptation and translation followed the universalist approach. The uMARS-F was evaluated as part through a cohort study using the French mHealth app ``MonSherpa'' (Qare). Participants were French-speaking adults with Apple or Android phones, excluding those with difficulty understanding French, prior app use, or physical limitations. They assessed the app using the uMARS-F twice (T1 and T2) 1 week apart. Scores for each section and overall were assessed for normal distribution using the Shapiro-Wilk test and presented as mean (SD), and potential floor or ceiling effects were calculated accordingly. Overall reliability was evaluated using intraclass correlation coefficients and internal reliability using Cronbach $\alpha$. Concordance between the 3 subscales (objective quality, subjective quality, and perceived impact), 4 sections, and 26 items at T1 and T2 was evaluated using the paired t test (2-tailed) and Pearson correlation. Results: In total, 167 participants assessed the app at both T1 and T2 (100\% compliance). Among them, 49.7\% (n=83) were female, and 50.3\% (n=84) were male, with a mean age of 43 (SD 16) years. The uMARS-F intraclass correlation coefficients were excellent for objective quality (0.959), excellent for subjective quality (0.993), and moderate for perceived impact (0.624). Cronbach $\alpha$ was good for objective quality (0.881), acceptable for subjective quality (0.701), and excellent for perceived impact (0.936). The paired t tests (2-tailed) demonstrated similar scores between the 2 assessments (P>.05), and the Pearson correlation coefficient indicated high consistency in each subscale, section, and item (r>0.76 and P<.001). The reliability and validity of the measures were similar to those found in the original English version as well as in the Spanish, Japanese, Italian, Greek, and Turkish versions that have already been translated and validated. Conclusions: The uMARS-F is a valid tool for end users to assess the quality of mHealth apps in French-speaking countries. The uMARS-F used in combination with the French version of the Mobile Application Rating Scale could enable health care professionals and public health authorities to identify reliable, high-quality, and valid apps for patients and should be part of French health care education programs. ",
doi="10.2196/63776",
url="https://mhealth.jmir.org/2024/1/e63776"
}


@Article{info:doi/10.2196/58144,
author="Sumner, Jennifer
and Tan, Ying Si
and Wang, Yuchen
and Keck, Sze Camille Hui
and Xin Lee, Wei Eunice
and Chew, Hoon Emily Hwee
and Yip, Wenjun Alexander",
title="Co-Designing Remote Patient Monitoring Technologies for Inpatients: Systematic Review",
journal="J Med Internet Res",
year="2024",
month="Oct",
day="15",
volume="26",
pages="e58144",
keywords="remote patient monitoring",
keywords="technology",
keywords="inpatient",
keywords="care transition",
keywords="systematic review",
keywords="health technology",
keywords="patient-centeredness",
keywords="technology use",
keywords="effectiveness",
keywords="study design",
keywords="assessment",
keywords="pilot testing",
keywords="health care",
keywords="technologies",
keywords="terminology",
keywords="quality and consistency",
keywords="telehealth",
keywords="telemonitoring",
abstract="Background: The co-design of health technology enables patient-centeredness and can help reduce barriers to technology use. Objective: The study objectives were to identify what remote patient monitoring (RPM) technology has been co-designed for inpatients and how effective it is, to identify and describe the co-design approaches used to develop RPM technologies and in which contexts they emerge, and to identify and describe barriers and facilitators of the co-design process. Methods: We conducted a systematic review of co-designed RPM technologies for inpatients or for the immediate postdischarge period and assessed (1) their effectiveness in improving health outcomes, (2) the co-design approaches used, and (3) barriers and facilitators to the co-design process. Eligible records included those involving stakeholders co-designing RPM technology for use in the inpatient setting or during the immediate postdischarge period. Searches were limited to the English language within the last 10 years. We searched MEDLINE, Embase, CINAHL, PsycInfo, and Science Citation Index (Web of Science) in April 2023. We used the Joanna Briggs Institute critical appraisal checklist for quasi-experimental studies and qualitative research. Findings are presented narratively. Results: We screened 3334 reports, and 17 projects met the eligibility criteria. Interventions were designed for pre- and postsurgical monitoring (n=6), intensive care monitoring (n=2), posttransplant monitoring (n=3), rehabilitation (n=4), acute inpatients (n=1), and postpartum care (n=1). No projects evaluated the efficacy of their co-designed RPM technology. Three pilot studies reported clinical outcomes; their risk of bias was low to moderate. Pilot evaluations (11/17) also focused on nonclinical outcomes such as usability, usefulness, feasibility, and satisfaction. Common co-design approaches included needs assessment or ideation (16/17), prototyping (15/17), and pilot testing (11/17). The most commonly reported challenge to the co-design process was the generalizability of findings, closely followed by time and resource constraints and participant bias. Stakeholders' perceived value was the most frequently reported enabler of co-design. Other enablers included continued stakeholder engagement and methodological factors (ie, the use of flexible mixed method approaches and prototyping). Conclusions: Co-design methods can help enhance interventions' relevance, usability, and adoption. While included studies measured usability, satisfaction, and acceptability---critical factors for successful implementation and uptake---we could not determine the clinical effectiveness of co-designed RPM technologies. A stronger commitment to clinical evaluation is needed. Studies' use of diverse co-design approaches can foster stakeholder inclusivity, but greater standardization in co-design terminology is needed to improve the quality and consistency of co-design research. ",
doi="10.2196/58144",
url="https://www.jmir.org/2024/1/e58144",
url="http://www.ncbi.nlm.nih.gov/pubmed/39405106"
}


@Article{info:doi/10.2196/49449,
author="Hach, Sylvia
and Alder, Gemma
and Stavric, Verna
and Taylor, Denise
and Signal, Nada",
title="Usability Assessment Methods for Mobile Apps for Physical Rehabilitation: Umbrella Review",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Oct",
day="4",
volume="12",
pages="e49449",
keywords="usability",
keywords="quality evaluation",
keywords="mobile health",
keywords="physical exercise",
keywords="rehabilitation",
keywords="overview",
keywords="umbrella review",
keywords="psychometrics",
abstract="Background: Usability has been touted as one determiner of success of mobile health (mHealth) interventions. Multiple systematic reviews of usability assessment approaches for different mHealth solutions for physical rehabilitation are available. However, there is a lack of synthesis in this portion of the literature, which results in clinicians and developers devoting a significant amount of time and effort in analyzing and summarizing a large body of systematic reviews. Objective: This study aims to summarize systematic reviews examining usability assessment instruments, or measurements tools, in mHealth interventions including physical rehabilitation. Methods: An umbrella review was conducted according to a published registered protocol. A topic-based search of PubMed, Cochrane, IEEE Xplore, Epistemonikos, Web of Science, and CINAHL Complete was conducted from January 2015 to April 2023 for systematic reviews investigating usability assessment instruments in mHealth interventions including physical exercise rehabilitation. Eligibility screening included date, language, participant, and article type. Data extraction and assessment of the methodological quality (AMSTAR 2 [A Measurement Tool to Assess Systematic Reviews 2]) was completed and tabulated for synthesis. Results: A total of 12 systematic reviews were included, of which 3 (25\%) did not refer to any theoretical usability framework and the remaining (n=9, 75\%) most commonly referenced the ISO framework. The sample referenced a total of 32 usability assessment instruments and 66 custom-made, as well as hybrid, instruments. Information on psychometric properties was included for 9 (28\%) instruments with satisfactory internal consistency and structural validity. A lack of reliability, responsiveness, and cross-cultural validity data was found. The methodological quality of the systematic reviews was limited, with 8 (67\%) studies displaying 2 or more critical weaknesses. Conclusions: There is significant diversity in the usability assessment of mHealth for rehabilitation, and a link to theoretical models is often lacking. There is widespread use of custom-made instruments, and preexisting instruments often do not display sufficient psychometric strength. As a result, existing mHealth usability evaluations are difficult to compare. It is proposed that multimethod usability assessment is used and that, in the selection of usability assessment instruments, there is a focus on explicit reference to their theoretical underpinning and acceptable psychometric properties. This could be facilitated by a closer collaboration between researchers, developers, and clinicians throughout the phases of mHealth tool development. Trial Registration: PROSPERO CRD42022338785; https://www.crd.york.ac.uk/prospero/\#recordDetails ",
doi="10.2196/49449",
url="https://mhealth.jmir.org/2024/1/e49449"
}


@Article{info:doi/10.2196/58079,
author="Podda, Jessica
and Grange, Erica
and Susini, Alessia
and Tacchino, Andrea
and Di Antonio, Federica
and Pedull{\`a}, Ludovico
and Brichetto, Giampaolo
and Ponzio, Michela",
title="Italian Version of the mHealth App Usability Questionnaire (Ita-MAUQ): Translation and Validation Study in People With Multiple Sclerosis",
journal="JMIR Hum Factors",
year="2024",
month="Sep",
day="30",
volume="11",
pages="e58079",
keywords="mHealth",
keywords="multiple sclerosis",
keywords="cognitive assessment",
keywords="questionnaire validation",
keywords="usability",
keywords="mHealth app",
keywords="mHealth application",
keywords="validation study",
keywords="MAUQ",
keywords="app usability",
keywords="telemedicine",
keywords="disability",
keywords="usability questionnaire",
keywords="mobile health",
abstract="Background: Telemedicine and mobile health (mHealth) apps have emerged as powerful tools in health care, offering convenient access to services and empowering participants in managing their health. Among populations with chronic and progressive disease such as multiple sclerosis (MS), mHealth apps hold promise for enhancing self-management and care. To be used in clinical practice, the validity and usability of mHealth tools should be tested. The most commonly used method for assessing the usability of electronic technologies are questionnaires. Objective: This study aimed to translate and validate the English version of the mHealth App Usability Questionnaire into Italian (ita-MAUQ) in a sample of people with MS. Methods: The 18-item mHealth App Usability Questionnaire was forward- and back-translated from English into Italian by an expert panel, following scientific guidelines for translation and cross-cultural adaptation. The ita-MAUQ (patient version for stand-alone apps) comprises 3 subscales, which are ease of use, interface and satisfaction, and usefulness. After interacting with DIGICOG-MS (Digital Assessment of Cognitive Impairment in Multiple Sclerosis), a novel mHealth app for cognitive self-assessment in MS, people completed the ita-MAUQ and the System Usability Scale, included to test construct validity of the translated questionnaire. Confirmatory factor analysis, internal consistency, test-retest reliability, and construct validity were assessed. Known-groups validity was examined based on disability levels as indicated by the Expanded Disability Status Scale (EDSS) score and gender. Results: In total, 116 people with MS (female n=74; mean age 47.2, SD 14 years; mean EDSS 3.32, SD 1.72) were enrolled. The ita-MAUQ demonstrated acceptable model fit, good internal consistency (Cronbach $\alpha$=0.92), and moderate test-retest reliability (intraclass coefficient correlation 0.84). Spearman coefficients revealed significant correlations between the ita-MAUQ total score; the ease of use (5 items), interface and satisfaction (7 items), and usefulness subscales; and the System Usability Scale (all P values <.05). Known-group analysis found no difference between people with MS with mild and moderate EDSS (all P values >.05), suggesting that ambulation ability, mainly detected by the EDSS, did not affect the ita-MAUQ scores. Interestingly, a statistical difference between female and male participants concerning the ease of use ita-MAUQ subscale was found (P=.02). Conclusions: The ita-MAUQ demonstrated high reliability and validity and it might be used to evaluate the usability, utility, and acceptability of mHealth apps in people with MS. ",
doi="10.2196/58079",
url="https://humanfactors.jmir.org/2024/1/e58079"
}


@Article{info:doi/10.2196/56370,
author="Attamimi, Sultan
and Marshman, Zoe
and Deery, Christopher
and Radley, Stephen
and Gilchrist, Fiona",
title="A Behavior-Based Model to Validate Electronic Systems Designed to Collect Patient-Reported Outcomes: Model Development and Application",
journal="JMIR Form Res",
year="2024",
month="Sep",
day="17",
volume="8",
pages="e56370",
keywords="patient-reported outcome",
keywords="PRO",
keywords="electronic PRO",
keywords="user acceptance testing",
keywords="system validation",
keywords="patient-reported outcomes",
keywords="electronic PROs",
keywords="user acceptance",
keywords="validation model",
keywords="paediatric dentistry",
abstract="Background: The merits of technology have been adopted in capturing patient-reported outcomes (PROs) by incorporating PROs into electronic systems. Following the development of an electronic system, evaluation of system performance is crucial to ensuring the collection of meaningful data. In contemporary PRO literature, electronic system validation is overlooked, and evidence on validation methods is lacking. Objective: This study aims to introduce a generalized concept to guide electronic patient-reported outcome (ePRO) providers in planning for system-specific validation methods. Methods: Since electronic systems are essentially products of software engineering endeavors, electronic systems used to collect PRO should be viewed from a computer science perspective with consideration to the health care environment. On this basis, a testing model was blueprinted and applied to a newly developed ePRO system designed for clinical use in pediatric dentistry (electronic Personal Assessment Questionnaire-Paediatric Dentistry) to investigate its thoroughness. Results: A behavior-based model of ePRO system validation was developed based on the principles of user acceptance testing and patient-centered care. The model allows systematic inspection of system specifications and identification of technical errors through simulated positive and negative usage pathways in open and closed environments. The model was able to detect 15 positive errors with 1 unfavorable response when applied to electronic Personal Assessment Questionnaire-Paediatric Dentistry system testing. Conclusions: The application of the behavior-based model to a newly developed ePRO system showed a high ability for technical error detection in a systematic fashion. The proposed model will increase confidence in the validity of ePRO systems as data collection tools in future research and clinical practice. ",
doi="10.2196/56370",
url="https://formative.jmir.org/2024/1/e56370"
}


@Article{info:doi/10.2196/59497,
author="Liang, Ya-Ting
and Wang, Charlotte
and Hsiao, Kate Chuhsing",
title="Data Analytics in Physical Activity Studies With Accelerometers: Scoping Review",
journal="J Med Internet Res",
year="2024",
month="Sep",
day="11",
volume="26",
pages="e59497",
keywords="accelerometer",
keywords="association",
keywords="behavioral study",
keywords="classification",
keywords="digital biomarkers",
keywords="digital health",
keywords="physical activity",
keywords="prediction",
keywords="statistical method",
keywords="wearable",
abstract="Background: Monitoring free-living physical activity (PA) through wearable devices enables the real-time assessment of activity features associated with health outcomes and provision of treatment recommendations and adjustments. The conclusions of studies on PA and health depend crucially on reliable statistical analyses of digital data. Data analytics, however, are challenging due to the various metrics adopted for measuring PA, different aims of studies, and complex temporal variations within variables. The application, interpretation, and appropriateness of these analytical tools have yet to be summarized. Objective: This research aimed to review studies that used analytical methods for analyzing PA monitored by accelerometers. Specifically, this review addressed three questions: (1) What metrics are used to describe an individual's free-living daily PA? (2) What are the current analytical tools for analyzing PA data, particularly under the aims of classification, association with health outcomes, and prediction of health events? and (3) What challenges exist in the analyses, and what recommendations for future research are suggested regarding the use of statistical methods in various research tasks? Methods: This scoping review was conducted following an existing framework to map research studies by exploring the information about PA. Three databases, PubMed, IEEE Xplore, and the ACM Digital Library, were searched in February 2024 to identify related publications. Eligible articles were classification, association, or prediction studies involving human PA monitored through wearable accelerometers. Results: After screening 1312 articles, 428 (32.62\%) eligible studies were identified and categorized into at least 1 of the following 3 thematic categories: classification (75/428, 17.5\%), association (342/428, 79.9\%), and prediction (32/428, 7.5\%). Most articles (414/428, 96.7\%) derived PA variables from 3D acceleration, rather than 1D acceleration. All eligible articles (428/428, 100\%) considered PA metrics represented in the time domain, while a small fraction (16/428, 3.7\%) also considered PA metrics in the frequency domain. The number of studies evaluating the influence of PA on health conditions has increased greatly. Among the studies in our review, regression-type models were the most prevalent (373/428, 87.1\%). The machine learning approach for classification research is also gaining popularity (32/75, 43\%). In addition to summary statistics of PA, several recent studies used tools to incorporate PA trajectories and account for temporal patterns, including longitudinal data analysis with repeated PA measurements and functional data analysis with PA as a continuum for time-varying association (68/428, 15.9\%). Conclusions: Summary metrics can quickly provide descriptions of the strength, frequency, and duration of individuals' overall PA. When the distribution and profile of PA need to be evaluated or detected, considering PA metrics as longitudinal or functional data can provide detailed information and improve the understanding of the role PA plays in health. Depending on the research goal, appropriate analytical tools can ensure the reliability of the scientific findings. ",
doi="10.2196/59497",
url="https://www.jmir.org/2024/1/e59497"
}


@Article{info:doi/10.2196/59444,
author="Tak, Won Yae
and Lee, Won Jong
and Kim, Junetae
and Lee, Yura",
title="Predicting Long-Term Engagement in mHealth Apps: Comparative Study of Engagement Indices",
journal="J Med Internet Res",
year="2024",
month="Sep",
day="9",
volume="26",
pages="e59444",
keywords="treatment adherence and compliance",
keywords="patient compliance",
keywords="medication adherence",
keywords="digital therapeutics",
keywords="engagement index",
keywords="mobile phone",
abstract="Background: Digital health care apps, including digital therapeutics, have the potential to increase accessibility and improve patient engagement by overcoming the limitations of traditional facility-based medical treatments. However, there are no established tools capable of quantitatively measuring long-term engagement at present. Objective: This study aimed to evaluate an existing engagement index (EI) in a commercial health management app for long-term use and compare it with a newly developed EI. Methods: Participants were recruited from cancer survivors enrolled in a randomized controlled trial that evaluated the impact of mobile health apps on recovery. Of these patients, 240 were included in the study and randomly assigned to the Noom app (Noom Inc). The newly developed EI was compared with the existing EI, and a long-term use analysis was conducted. Furthermore, the new EI was evaluated based on adapted measurements from the Web Matrix Visitor Index, focusing on click depth, recency, and loyalty indices. Results: The newly developed EI model outperformed the existing EI model in terms of predicting EI of a 6- to 9-month period based on the EI of a 3- to 6-month period. The existing model had a mean squared error of 0.096, a root mean squared error of 0.310, and an R2 of 0.053. Meanwhile, the newly developed EI models showed improved performance, with the best one achieving a mean squared error of 0.025, root mean squared error of 0.157, and R2 of 0.610. The existing EI exhibited significant associations: the click depth index (hazard ratio [HR] 0.49, 95\% CI 0.29-0.84; P<.001) and loyalty index (HR 0.17, 95\% CI 0.09-0.31; P<.001) were significantly associated with improved survival, whereas the recency index exhibited no significant association (HR 1.30, 95\% CI 1.70-2.42; P=.41). Among the new EI models, the EI with a menu combination of menus available in the app's free version yielded the most promising result. Furthermore, it exhibited significant associations with the loyalty index (HR 0.32, 95\% CI 0.16-0.62; P<.001) and the recency index (HR 0.47, 95\% CI 0.30-0.75; P<.001). Conclusions: The newly developed EI model outperformed the existing model in terms of the prediction of long-term user engagement and compliance in a mobile health app context. We emphasized the importance of log data and suggested avenues for future research to address the subjectivity of the EI and incorporate a broader range of indices for comprehensive evaluation. ",
doi="10.2196/59444",
url="https://www.jmir.org/2024/1/e59444",
url="http://www.ncbi.nlm.nih.gov/pubmed/39250192"
}


@Article{info:doi/10.2196/53119,
author="Cescon, Corrado
and Landolfi, Giuseppe
and Bonomi, Niko
and Derboni, Marco
and Giuffrida, Vincenzo
and Rizzoli, Emilio Andrea
and Maino, Paolo
and Koetsier, Eva
and Barbero, Marco",
title="Automated Pain Spots Recognition Algorithm Provided by a Web Service--Based Platform: Instrument Validation Study",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Aug",
day="27",
volume="12",
pages="e53119",
keywords="pain drawing",
keywords="image processing",
keywords="body charts",
keywords="scan",
keywords="pain",
keywords="draw",
keywords="drawing",
keywords="scanner",
keywords="scanners",
keywords="app",
keywords="apps",
keywords="applications",
keywords="device",
keywords="devices",
keywords="image",
keywords="images",
keywords="smartphone",
keywords="smartphones",
keywords="scale",
keywords="musculoskeletal",
keywords="body chart",
keywords="accuracy",
keywords="reliability",
keywords="accurate",
keywords="reliable",
keywords="picture",
keywords="pictures",
keywords="mobile phone",
abstract="Background: Understanding the causes and mechanisms underlying musculoskeletal pain is crucial for developing effective treatments and improving patient outcomes. Self-report measures, such as the Pain Drawing Scale, involve individuals rating their level of pain on a scale. In this technique, individuals color the area where they experience pain, and the resulting picture is rated based on the depicted pain intensity. Analyzing pain drawings (PDs) typically involves measuring the size of the pain region. There are several studies focusing on assessing the clinical use of PDs, and now, with the introduction of digital PDs, the usability and reliability of these platforms need validation. Comparative studies between traditional and digital PDs have shown good agreement and reliability. The evolution of PD acquisition over the last 2 decades mirrors the commercialization of digital technologies. However, the pen-on-paper approach seems to be more accepted by patients, but there is currently no standardized method for scanning PDs. Objective: The objective of this study was to evaluate the accuracy of PD analysis performed by a web platform using various digital scanners. The primary goal was to demonstrate that simple and affordable mobile devices can be used to acquire PDs without losing important information. Methods: Two sets of PDs were generated: one with the addition of 216 colored circles and another composed of various red shapes distributed randomly on a frontal view body chart of an adult male. These drawings were then printed in color on A4 sheets, including QR codes at the corners in order to allow automatic alignment, and subsequently scanned using different devices and apps. The scanners used were flatbed scanners of different sizes and prices (professional, portable flatbed, and home printer or scanner), smartphones with varying price ranges, and 6 virtual scanner apps. The acquisitions were made under normal light conditions by the same operator. Results: High-saturation colors, such as red, cyan, magenta, and yellow, were accurately identified by all devices. The percentage error for small, medium, and large pain spots was consistently below 20\% for all devices, with smaller values associated with larger areas. In addition, a significant negative correlation was observed between the percentage of error and spot size (R=?0.237; P=.04). The proposed platform proved to be robust and reliable for acquiring paper PDs via a wide range of scanning devices. Conclusions: This study demonstrates that a web platform can accurately analyze PDs acquired through various digital scanners. The findings support the use of simple and cost-effective mobile devices for PD acquisition without compromising the quality of data. Standardizing the scanning process using the proposed platform can contribute to more efficient and consistent PD analysis in clinical and research settings. ",
doi="10.2196/53119",
url="https://mhealth.jmir.org/2024/1/e53119"
}


@Article{info:doi/10.2196/52196,
author="Castillo-Valdez, Fernando Pedro
and Rodriguez-Salvador, Marisela
and Ho, Yuh-Shan",
title="Scientific Production Dynamics in mHealth for Diabetes: Scientometric Analysis",
journal="JMIR Diabetes",
year="2024",
month="Aug",
day="22",
volume="9",
pages="e52196",
keywords="competitive technology intelligence",
keywords="diabetes",
keywords="digital health care",
keywords="mobile health",
keywords="mHealth",
keywords="scientometrics",
keywords="mobile phone",
abstract="Background: The widespread use of mobile technologies in health care (mobile health; mHealth) has facilitated disease management, especially for chronic illnesses such as diabetes. mHealth for diabetes is an attractive alternative to reduce costs and overcome geographical and temporal barriers to improve patients' conditions. Objective: This study aims to reveal the dynamics of scientific publications on mHealth for diabetes to gain insights into who are the most prominent authors, countries, institutions, and journals and what are the most cited documents and current hot spots. Methods: A scientometric analysis based on a competitive technology intelligence methodology was conducted. An innovative 8-step methodology supported by experts was executed considering scientific documents published between 1998 and 2021 in the Science Citation Index Expanded database. Publication language, publication output characteristics, journals, countries and institutions, authors, and most cited and most impactful articles were identified. Results: The insights obtained show that a total of 1574 scientific articles were published by 7922 authors from 90 countries, with an average of 15 (SD 38) citations and 6.5 (SD 4.4) authors per article. These documents were published in 491 journals and 92 Web of Science categories. The most productive country was the United States, followed by the United Kingdom, China, Australia, and South Korea, and the top 3 most productive institutions came from the United States, whereas the top 3 most cited articles were published in 2016, 2009, and 2017 and the top 3 most impactful articles were published in 2016 and 2017. Conclusions: This approach provides a comprehensive knowledge panorama of research productivity in mHealth for diabetes, identifying new insights and opportunities for research and development and innovation, including collaboration with other entities, new areas of specialization, and human resource development. The findings obtained are useful for decision-making in policy planning, resource allocation, and identification of research opportunities, benefiting researchers, health professionals, and decision makers in their efforts to make significant contributions to the advancement of diabetes science. ",
doi="10.2196/52196",
url="https://diabetes.jmir.org/2024/1/e52196",
url="http://www.ncbi.nlm.nih.gov/pubmed/39172508"
}


@Article{info:doi/10.2196/49576,
author="Pauly, Theresa
and L{\"u}scher, Janina
and Wilhelm, Olivia Lea
and Amrein, Alexandra Melanie
and Boateng, George
and Kowatsch, Tobias
and Fleisch, Elgar
and Bodenmann, Guy
and Scholz, Urte",
title="Using Wearables to Study Biopsychosocial Dynamics in Couples Who Cope With a Chronic Health Condition: Ambulatory Assessment Study",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Aug",
day="5",
volume="12",
pages="e49576",
keywords="couples",
keywords="wearables",
keywords="type II diabetes",
keywords="heart rate",
keywords="biopsychosocial dynamics",
keywords="physiological linkage",
keywords="mobile health",
keywords="technology",
keywords="social support",
keywords="chronic disease",
keywords="usability",
keywords="utility",
keywords="mHealth",
abstract="Background: Technology has become an integral part of our everyday life, and its use to manage and study health is no exception. Romantic partners play a critical role in managing chronic health conditions as they tend to be a primary source of support. Objective: This study tests the feasibility of using commercial wearables to monitor couples' unique way of communicating and supporting each other and documents the physiological correlates of interpersonal dynamics (ie, heart rate linkage). Methods: We analyzed 617 audio recordings of 5-minute duration (384 with concurrent heart rate data) and 527 brief self-reports collected from 11 couples in which 1 partner had type II diabetes during the course of their typical daily lives. Audio data were coded by trained raters for social support. The extent to which heart rate fluctuations were linked among couples was quantified using cross-correlations. Random-intercept multilevel models explored whether cross-correlations might differ by social contexts and exchanges. Results: Sixty percent of audio recordings captured speech between partners and partners reported personal contact with each other in 75\% of self-reports. Based on the coding, social support was found in 6\% of recordings, whereas at least 1 partner self-reported social support about half the time (53\%). Couples, on average, showed small to moderate interconnections in their heart rate fluctuations (r=0.04-0.22). Couples also varied in the extent to which there was lagged linkage, that is, meaning that changes in one partner's heart rate tended to precede changes in the other partner's heart rate. Exploratory analyses showed that heart rate linkage was stronger (1) in rater-coded partner conversations (vs moments of no rater-coded partner conversations: rdiff=0.13; P=.03), (2) when partners self-reported interpersonal contact (vs moments of no self-reported interpersonal contact: rdiff=0.20; P<.001), and (3) when partners self-reported social support exchanges (vs moments of no self-reported social support exchange: rdiff=0.15; P=.004). Conclusions: Our study provides initial evidence for the utility of using wearables to collect biopsychosocial data in couples managing a chronic health condition in daily life. Specifically, heart rate linkage might play a role in fostering chronic disease management as a couple. Insights from collecting such data could inform future technology interventions to promote healthy lifestyle engagement and adaptive chronic disease management. International Registered Report Identifier (IRRID): RR2-10.2196/13685 ",
doi="10.2196/49576",
url="https://mhealth.jmir.org/2024/1/e49576"
}


@Article{info:doi/10.2196/48516,
author="Bowers, M. Jennifer
and Huelsnitz, O. Chloe
and Dwyer, A. Laura
and Gibson, P. Laurel
and Agurs-Collins, Tanya
and Ferrer, A. Rebecca
and Acevedo, M. Amanda",
title="Measuring Relationship Influences on Romantic Couples' Cancer-Related Behaviors During the COVID-19 Pandemic: Protocol for a Longitudinal Online Study of Dyads and Cancer Survivors",
journal="JMIR Res Protoc",
year="2024",
month="Jul",
day="31",
volume="13",
pages="e48516",
keywords="cancer prevention",
keywords="COVID-19",
keywords="risk perceptions",
keywords="dyads",
keywords="romantic relationships",
keywords="cancer",
keywords="oncology",
keywords="survivor",
keywords="survivors",
keywords="dyad",
keywords="spouse",
keywords="spousal",
keywords="partner",
keywords="health behavior",
keywords="health behaviors",
keywords="cohabiting",
keywords="cohabit",
keywords="study design",
keywords="recruit",
keywords="recruitment",
keywords="methodology",
keywords="methods",
keywords="enrol",
keywords="enrolment",
keywords="enroll",
keywords="enrollment",
abstract="Background: Research has established the effects of romantic relationships on individuals' morbidity and mortality. However, the interplay between relationship functioning, affective processes, and health behaviors has been relatively understudied. During the COVID-19 pandemic, relational processes may influence novel health behaviors such as social distancing and masking. Objective: We describe the design, recruitment, and methods of the relationships, risk perceptions, and cancer-related behaviors during the COVID-19 pandemic study. This study was developed to understand how relational and affective processes influence romantic partners' engagement in cancer prevention behaviors as well as health behaviors introduced or exacerbated by the COVID-19 pandemic. Methods: The relationships, risk perceptions, and cancer-related behaviors during the COVID-19 pandemic study used online survey methods to recruit and enroll 2 cohorts of individuals involved in cohabiting romantic relationships, including 1 cohort of dyads (n=223) and 1 cohort of cancer survivors (n=443). Survey assessments were completed over 2 time points that were 5.57 (SD 3.14) weeks apart on average. Health behaviors assessed included COVID-19 vaccination and social distancing, physical activity, diet, sleep, alcohol use, and smoking behavior. We also examined relationship factors, psychological distress, and household chaos. Results: Data collection occurred between October 2021 and August 2022. During that time, a total of 926 participants were enrolled, of which about two-thirds were from the United Kingdom (n=622, 67.8\%) and one-third were from the United States (n=296, 32.2\%); about two-thirds were married (n=608, 66.2\%) and one-third were members of unmarried couples (n=294, 32\%). In cohorts 1 and 2, the mean age was about 34 and 50, respectively. Out of 478 participants in cohort 1, 19 (4\%) identified as Hispanic or Latino/a, 79 (17\%) as non-Hispanic Asian, 40 (9\%) as non-Hispanic Black or African American, and 306 (64\%) as non-Hispanic White; 62 (13\%) participants identified their sexual orientation as bisexual or pansexual, 359 (75.1\%) as heterosexual or straight, and 53 (11\%) as gay or lesbian. In cohort 2, out of 440 participants, 13 (3\%) identified as Hispanic or Latino/a, 8 (2\%) as non-Hispanic Asian, 5 (1\%) as non-Hispanic Black or African American, and 398 (90.5\%) as non-Hispanic White; 41 (9\%) participants identified their sexual orientation as bisexual or pansexual, 384 (87.3\%) as heterosexual or straight, and 13 (3\%) as gay or lesbian. The overall enrollment rate for individuals was 66.14\% and the overall completion rate was 80.08\%. Conclusions: We discuss best practices for collecting online survey data for studies examining relationships and health, challenges related to the COVID-19 pandemic, recruitment of underrepresented populations, and enrollment of dyads. Recommendations include conducting pilot studies, allowing for extra time in the data collection timeline for marginalized or underserved populations, surplus screening to account for expected attrition within dyads, as well as planning dyad-specific data quality checks. International Registered Report Identifier (IRRID): DERR1-10.2196/48516 ",
doi="10.2196/48516",
url="https://www.researchprotocols.org/2024/1/e48516"
}


@Article{info:doi/10.2196/48582,
author="Little, L. Claire
and Schultz, M. David
and House, Thomas
and Dixon, G. William
and McBeth, John",
title="Identifying Weekly Trajectories of Pain Severity Using Daily Data From an mHealth Study: Cluster Analysis",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Jul",
day="19",
volume="12",
pages="e48582",
keywords="mobile health",
keywords="mHealth",
keywords="pain",
keywords="cluster",
keywords="trajectory",
keywords="k-medoids",
keywords="transition",
keywords="forecast",
keywords="mobile phone",
abstract="Background: People with chronic pain experience variability in their trajectories of pain severity. Previous studies have explored pain trajectories by clustering sparse data; however, to understand daily pain variability, there is a need to identify clusters of weekly trajectories using daily pain data. Between-week variability can be explored by quantifying the week-to-week movement between these clusters. We propose that future work can use clusters of pain severity in a forecasting model for short-term (eg, daily fluctuations) and longer-term (eg, weekly patterns) variability. Specifically, future work can use clusters of weekly trajectories to predict between-cluster movement and within-cluster variability in pain severity. Objective: This study aims to understand clusters of common weekly patterns as a first stage in developing a pain-forecasting model. Methods: Data from a population-based mobile health study were used to compile weekly pain trajectories (n=21,919) that were then clustered using a k-medoids algorithm. Sensitivity analyses tested the impact of assumptions related to the ordinal and longitudinal structure of the data. The characteristics of people within clusters were examined, and a transition analysis was conducted to understand the movement of people between consecutive weekly clusters. Results: Four clusters were identified representing trajectories of no or low pain (1714/21,919, 7.82\%), mild pain (8246/21,919, 37.62\%), moderate pain (8376/21,919, 38.21\%), and severe pain (3583/21,919, 16.35\%). Sensitivity analyses confirmed the 4-cluster solution, and the resulting clusters were similar to those in the main analysis, with at least 85\% of the trajectories belonging to the same cluster as in the main analysis. Male participants spent longer (participant mean 7.9, 95\% bootstrap CI 6\%-9.9\%) in the no or low pain cluster than female participants (participant mean 6.5, 95\% bootstrap CI 5.7\%-7.3\%). Younger people (aged 17-24 y) spent longer (participant mean 28.3, 95\% bootstrap CI 19.3\%-38.5\%) in the severe pain cluster than older people (aged 65-86 y; participant mean 9.8, 95\% bootstrap CI 7.7\%-12.3\%). People with fibromyalgia (participant mean 31.5, 95\% bootstrap CI 28.5\%-34.4\%) and neuropathic pain (participant mean 31.1, 95\% bootstrap CI 27.3\%-34.9\%) spent longer in the severe pain cluster than those with other conditions, and people with rheumatoid arthritis spent longer (participant mean 7.8, 95\% bootstrap CI 6.1\%-9.6\%) in the no or low pain cluster than those with other conditions. There were 12,267 pairs of consecutive weeks that contributed to the transition analysis. The empirical percentage remaining in the same cluster across consecutive weeks was 65.96\% (8091/12,267). When movement between clusters occurred, the highest percentage of movement was to an adjacent cluster. Conclusions: The clusters of pain severity identified in this study provide a parsimonious description of the weekly experiences of people with chronic pain. These clusters could be used for future study of between-cluster movement and within-cluster variability to develop accurate and stakeholder-informed pain-forecasting tools. ",
doi="10.2196/48582",
url="https://mhealth.jmir.org/2024/1/e48582",
url="http://www.ncbi.nlm.nih.gov/pubmed/39028557"
}


@Article{info:doi/10.2196/52998,
author="Squire, M. Claudia
and Giombi, C. Kristen
and Rupert, J. Douglas
and Amoozegar, Jacqueline
and Williams, Peyton",
title="Determining an Appropriate Sample Size for Qualitative Interviews to Achieve True and Near Code Saturation: Secondary Analysis of Data",
journal="J Med Internet Res",
year="2024",
month="Jul",
day="9",
volume="26",
pages="e52998",
keywords="saturation",
keywords="sample size",
keywords="web-based data collection",
keywords="semistructured interviews",
keywords="qualitative",
keywords="research methods",
keywords="research methodology",
keywords="data collection",
keywords="coding",
keywords="interviews",
keywords="interviewing",
keywords="in-depth",
abstract="Background: In-depth interviews are a common method of qualitative data collection, providing rich data on individuals' perceptions and behaviors that would be challenging to collect with quantitative methods. Researchers typically need to decide on sample size a priori. Although studies have assessed when saturation has been achieved, there is no agreement on the minimum number of interviews needed to achieve saturation. To date, most research on saturation has been based on in-person data collection. During the COVID-19 pandemic, web-based data collection became increasingly common, as traditional in-person data collection was possible. Researchers continue to use web-based data collection methods post the COVID-19 emergency, making it important to assess whether findings around saturation differ for in-person versus web-based interviews. Objective: We aimed to identify the number of web-based interviews needed to achieve true code saturation or near code saturation. Methods: The analyses for this study were based on data from 5 Food and Drug Administration--funded studies conducted through web-based platforms with patients with underlying medical conditions or with health care providers who provide primary or specialty care to patients. We extracted code- and interview-specific data and examined the data summaries to determine when true saturation or near saturation was reached. Results: The sample size used in the 5 studies ranged from 30 to 70 interviews. True saturation was reached after 91\% to 100\% (n=30-67) of planned interviews, whereas near saturation was reached after 33\% to 60\% (n=15-23) of planned interviews. Studies that relied heavily on deductive coding and studies that had a more structured interview guide reached both true saturation and near saturation sooner. We also examined the types of codes applied after near saturation had been reached. In 4 of the 5 studies, most of these codes represented previously established core concepts or themes. Codes representing newly identified concepts, other or miscellaneous responses (eg, ``in general''), uncertainty or confusion (eg, ``don't know''), or categorization for analysis (eg, correct as compared with incorrect) were less commonly applied after near saturation had been reached. Conclusions: This study provides support that near saturation may be a sufficient measure to target and that conducting additional interviews after that point may result in diminishing returns. Factors to consider in determining how many interviews to conduct include the structure and type of questions included in the interview guide, the coding structure, and the population under study. Studies with less structured interview guides, studies that rely heavily on inductive coding and analytic techniques, and studies that include populations that may be less knowledgeable about the topics discussed may require a larger sample size to reach an acceptable level of saturation. Our findings also build on previous studies looking at saturation for in-person data collection conducted at a small number of sites. ",
doi="10.2196/52998",
url="https://www.jmir.org/2024/1/e52998",
url="http://www.ncbi.nlm.nih.gov/pubmed/38980711"
}


@Article{info:doi/10.2196/55302,
author="Zhang, Yuezhou
and Folarin, A. Amos
and Sun, Shaoxiong
and Cummins, Nicholas
and Ranjan, Yatharth
and Rashid, Zulqarnain
and Stewart, Callum
and Conde, Pauline
and Sankesara, Heet
and Laiou, Petroula
and Matcham, Faith
and White, M. Katie
and Oetzmann, Carolin
and Lamers, Femke
and Siddi, Sara
and Simblett, Sara
and Vairavan, Srinivasan
and Myin-Germeys, Inez
and Mohr, C. David
and Wykes, Til
and Haro, Maria Josep
and Annas, Peter
and Penninx, WJH Brenda
and Narayan, A. Vaibhav
and Hotopf, Matthew
and Dobson, JB Richard
and ",
title="Longitudinal Assessment of Seasonal Impacts and Depression Associations on Circadian Rhythm Using Multimodal Wearable Sensing: Retrospective Analysis",
journal="J Med Internet Res",
year="2024",
month="Jun",
day="28",
volume="26",
pages="e55302",
keywords="circadian rhythm",
keywords="biological rhythms",
keywords="mental health",
keywords="major depressive disorder",
keywords="MDD",
keywords="wearable",
keywords="mHealth",
keywords="mobile health",
keywords="digital health",
keywords="monitoring",
abstract="Background: Previous mobile health (mHealth) studies have revealed significant links between depression and circadian rhythm features measured via wearables. However, the comprehensive impact of seasonal variations was not fully considered in these studies, potentially biasing interpretations in real-world settings. Objective: This study aims to explore the associations between depression severity and wearable-measured circadian rhythms while accounting for seasonal impacts. Methods: Data were sourced from a large longitudinal mHealth study, wherein participants' depression severity was assessed biweekly using the 8-item Patient Health Questionnaire (PHQ-8), and participants' behaviors, including sleep, step count, and heart rate (HR), were tracked via Fitbit devices for up to 2 years. We extracted 12 circadian rhythm features from the 14-day Fitbit data preceding each PHQ-8 assessment, including cosinor variables, such as HR peak timing (HR acrophase), and nonparametric features, such as the onset of the most active continuous 10-hour period (M10 onset). To investigate the association between depression severity and circadian rhythms while also assessing the seasonal impacts, we used three nested linear mixed-effects models for each circadian rhythm feature: (1) incorporating the PHQ-8 score as an independent variable, (2) adding seasonality, and (3) adding an interaction term between season and the PHQ-8 score. Results: Analyzing 10,018 PHQ-8 records alongside Fitbit data from 543 participants (n=414, 76.2\% female; median age 48, IQR 32-58 years), we found that after adjusting for seasonal effects, higher PHQ-8 scores were associated with reduced daily steps ($\beta$=--93.61, P<.001), increased sleep variability ($\beta$=0.96, P<.001), and delayed circadian rhythms (ie, sleep onset: $\beta$=0.55, P=.001; sleep offset: $\beta$=1.12, P<.001; M10 onset: $\beta$=0.73, P=.003; HR acrophase: $\beta$=0.71, P=.001). Notably, the negative association with daily steps was more pronounced in spring ($\beta$ of PHQ-8 {\texttimes} spring = --31.51, P=.002) and summer ($\beta$ of PHQ-8 {\texttimes} summer = --42.61, P<.001) compared with winter. Additionally, the significant correlation with delayed M10 onset was observed solely in summer ($\beta$ of PHQ-8 {\texttimes} summer = 1.06, P=.008). Moreover, compared with winter, participants experienced a shorter sleep duration by 16.6 minutes, an increase in daily steps by 394.5, a delay in M10 onset by 20.5 minutes, and a delay in HR peak time by 67.9 minutes during summer. Conclusions: Our findings highlight significant seasonal influences on human circadian rhythms and their associations with depression, underscoring the importance of considering seasonal variations in mHealth research for real-world applications. This study also indicates the potential of wearable-measured circadian rhythms as digital biomarkers for depression. ",
doi="10.2196/55302",
url="https://www.jmir.org/2024/1/e55302"
}


@Article{info:doi/10.2196/55548,
author="Straand, J. Ingjerd
and Baxter, A. Kimberley
and F{\o}lstad, Asbj{\o}rn",
title="Remote Inclusion of Vulnerable Users in mHealth Intervention Design: Retrospective Case Analysis",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Jun",
day="14",
volume="12",
pages="e55548",
keywords="user testing",
keywords="user participation in research",
keywords="COVID-19",
keywords="remote testing",
keywords="intervention design",
keywords="mobile phone",
abstract="Background: Mobile health (mHealth) interventions that promote healthy behaviors or mindsets are a promising avenue to reach vulnerable or at-risk groups. In designing such mHealth interventions, authentic representation of intended participants is essential. The COVID-19 pandemic served as a catalyst for innovation in remote user-centered research methods. The capability of such research methods to effectively engage with vulnerable participants requires inquiry into practice to determine the suitability and appropriateness of these methods. Objective: In this study, we aimed to explore opportunities and considerations that emerged from involving vulnerable user groups remotely when designing mHealth interventions. Implications and recommendations are presented for researchers and practitioners conducting remote user-centered research with vulnerable populations. Methods: Remote user-centered research practices from 2 projects involving vulnerable populations in Norway and Australia were examined retrospectively using visual mapping and a reflection-on-action approach. The projects engaged low-income and unemployed groups during the COVID-19 pandemic in user-based evaluation and testing of interactive, web-based mHealth interventions. Results: Opportunities and considerations were identified as (1) reduced barriers to research inclusion; (2) digital literacy transition; (3) contextualized insights: a window into people's lives; (4) seamless enactment of roles; and (5) increased flexibility for researchers and participants. Conclusions: Our findings support the capability and suitability of remote user methods to engage with users from vulnerable groups. Remote methods facilitate recruitment, ease the burden of research participation, level out power imbalances, and provide a rich and relevant environment for user-centered evaluation of mHealth interventions. There is a potential for a much more agile research practice. Future research should consider the privacy impacts of increased access to participants' environment via webcams and screen share and how technology mediates participants' action in terms of privacy. The development of support procedures and tools for remote testing of mHealth apps with user participants will be crucial to capitalize on efficiency gains and better protect participants' privacy. ",
doi="10.2196/55548",
url="https://mhealth.jmir.org/2024/1/e55548",
url="http://www.ncbi.nlm.nih.gov/pubmed/38875700"
}


@Article{info:doi/10.2196/56218,
author="Tran, D. Amanda
and White, E. Alice
and Torok, R. Michelle
and Jervis, H. Rachel
and Albanese, A. Bernadette
and Scallan Walter, J. Elaine",
title="Lessons Learned From a Sequential Mixed-Mode Survey Design to Recruit and Collect Data From Case-Control Study Participants: Formative Evaluation",
journal="JMIR Form Res",
year="2024",
month="May",
day="27",
volume="8",
pages="e56218",
keywords="case-control studies",
keywords="mixed-mode design",
keywords="epidemiologic study methods",
keywords="web-based survey",
keywords="telephone interview",
keywords="public health",
keywords="outbreak preparedness",
keywords="COVID-19",
keywords="survey",
keywords="recruitment",
keywords="epidemiology",
keywords="methods",
abstract="Background: Sequential mixed-mode surveys using both web-based surveys and telephone interviews are increasingly being used in observational studies and have been shown to have many benefits; however, the application of this survey design has not been evaluated in the context of epidemiological case-control studies. Objective: In this paper, we discuss the challenges, benefits, and limitations of using a sequential mixed-mode survey design for a case-control study assessing risk factors during the COVID-19 pandemic. Methods: Colorado adults testing positive for SARS-CoV-2 were randomly selected and matched to those with a negative SARS-CoV-2 test result from March to April 2021. Participants were first contacted by SMS text message to complete a self-administered web-based survey asking about community exposures and behaviors. Those who did not respond were contacted for a telephone interview. We evaluated the representativeness of survey participants to sample populations and compared sociodemographic characteristics, participant responses, and time and resource requirements by survey mode using descriptive statistics and logistic regression models. Results: Of enrolled case and control participants, most were interviewed by telephone (308/537, 57.4\% and 342/648, 52.8\%, respectively), with overall enrollment more than doubling after interviewers called nonresponders. Participants identifying as female or White non-Hispanic, residing in urban areas, and not working outside the home were more likely to complete the web-based survey. Telephone participants were more likely than web-based participants to be aged 18-39 years or 60 years and older and reside in areas with lower levels of education, more linguistic isolation, lower income, and more people of color. While there were statistically significant sociodemographic differences noted between web-based and telephone case and control participants and their respective sample pools, participants were more similar to sample pools when web-based and telephone responses were combined. Web-based participants were less likely to report close contact with an individual with COVID-19 (odds ratio [OR] 0.70, 95\% CI 0.53-0.94) but more likely to report community exposures, including visiting a grocery store or retail shop (OR 1.55, 95\% CI 1.13-2.12), restaurant or cafe or coffee shop (OR 1.52, 95\% CI 1.20-1.92), attending a gathering (OR 1.69, 95\% CI 1.34-2.15), or sport or sporting event (OR 1.05, 95\% CI 1.05-1.88). The web-based survey required an average of 0.03 (SD 0) person-hours per enrolled participant and US \$920 in resources, whereas the telephone interview required an average of 5.11 person-hours per enrolled participant and US \$70,000 in interviewer wages. Conclusions: While we still encountered control recruitment challenges noted in other observational studies, the sequential mixed-mode design was an efficient method for recruiting a more representative group of participants for a case-control study with limited impact on data quality and should be considered during public health emergencies when timely and accurate exposure information is needed to inform control measures. ",
doi="10.2196/56218",
url="https://formative.jmir.org/2024/1/e56218",
url="http://www.ncbi.nlm.nih.gov/pubmed/38801768"
}


@Article{info:doi/10.2196/54705,
author="Kuziemsky, E. Craig
and Chrimes, Dillon
and Minshall, Simon
and Mannerow, Michael
and Lau, Francis",
title="AI Quality Standards in Health Care: Rapid Umbrella Review",
journal="J Med Internet Res",
year="2024",
month="May",
day="22",
volume="26",
pages="e54705",
keywords="artificial intelligence",
keywords="health care artificial intelligence",
keywords="health care AI",
keywords="rapid review",
keywords="umbrella review",
keywords="quality standard",
abstract="Background: In recent years, there has been an upwelling of artificial intelligence (AI) studies in the health care literature. During this period, there has been an increasing number of proposed standards to evaluate the quality of health care AI studies. Objective: This rapid umbrella review examines the use of AI quality standards in a sample of health care AI systematic review articles published over a 36-month period. Methods: We used a modified version of the Joanna Briggs Institute umbrella review method. Our rapid approach was informed by the practical guide by Tricco and colleagues for conducting rapid reviews. Our search was focused on the MEDLINE database supplemented with Google Scholar. The inclusion criteria were English-language systematic reviews regardless of review type, with mention of AI and health in the abstract, published during a 36-month period. For the synthesis, we summarized the AI quality standards used and issues noted in these reviews drawing on a set of published health care AI standards, harmonized the terms used, and offered guidance to improve the quality of future health care AI studies. Results: We selected 33 review articles published between 2020 and 2022 in our synthesis. The reviews covered a wide range of objectives, topics, settings, designs, and results. Over 60 AI approaches across different domains were identified with varying levels of detail spanning different AI life cycle stages, making comparisons difficult. Health care AI quality standards were applied in only 39\% (13/33) of the reviews and in 14\% (25/178) of the original studies from the reviews examined, mostly to appraise their methodological or reporting quality. Only a handful mentioned the transparency, explainability, trustworthiness, ethics, and privacy aspects. A total of 23 AI quality standard--related issues were identified in the reviews. There was a recognized need to standardize the planning, conduct, and reporting of health care AI studies and address their broader societal, ethical, and regulatory implications. Conclusions: Despite the growing number of AI standards to assess the quality of health care AI studies, they are seldom applied in practice. With increasing desire to adopt AI in different health topics, domains, and settings, practitioners and researchers must stay abreast of and adapt to the evolving landscape of health care AI quality standards and apply these standards to improve the quality of their AI studies. ",
doi="10.2196/54705",
url="https://www.jmir.org/2024/1/e54705",
url="http://www.ncbi.nlm.nih.gov/pubmed/38776538"
}


@Article{info:doi/10.2196/53790,
author="Sanchez, Jasmin
and Trofholz, Amanda
and Berge, M. Jerica",
title="Best Practices and Recommendations for Research Using Virtual Real-Time Data Collection: Protocol for Virtual Data Collection Studies",
journal="JMIR Res Protoc",
year="2024",
month="May",
day="14",
volume="13",
pages="e53790",
keywords="real-time data collection",
keywords="remote research",
keywords="virtual data collection",
keywords="virtual research protocol",
keywords="virtual research visits",
abstract="Background: The COVID-19 pandemic and the subsequent need for social distancing required the immediate pivoting of research modalities. Research that had previously been conducted in person had to pivot to remote data collection. Researchers had to develop data collection protocols that could be conducted remotely with limited or no evidence to guide the process. Therefore, the use of web-based platforms to conduct real-time research visits surged despite the lack of evidence backing these novel approaches. Objective: This paper aims to review the remote or virtual research protocols that have been used in the past 10 years, gather existing best practices, and propose recommendations for continuing to use virtual real-time methods when appropriate. Methods: Articles (n=22) published from 2013 to June 2023 were reviewed and analyzed to understand how researchers conducted virtual research that implemented real-time protocols. ``Real-time'' was defined as data collection with a participant through a live medium where a participant and research staff could talk to each other back and forth in the moment. We excluded studies for the following reasons: (1) studies that collected participant or patient measures for the sole purpose of engaging in a clinical encounter; (2) studies that solely conducted qualitative interview data collection; (3) studies that conducted virtual data collection such as surveys or self-report measures that had no interaction with research staff; (4) studies that described research interventions but did not involve the collection of data through a web-based platform; (5) studies that were reviews or not original research; (6) studies that described research protocols and did not include actual data collection; and (7) studies that did not collect data in real time, focused on telehealth or telemedicine, and were exclusively intended for medical and not research purposes. Results: Findings from studies conducted both before and during the COVID-19 pandemic suggest that many types of data can be collected virtually in real time. Results and best practice recommendations from the current protocol review will be used in the design and implementation of a substudy to provide more evidence for virtual real-time data collection over the next year. Conclusions: Our findings suggest that virtual real-time visits are doable across a range of participant populations and can answer a range of research questions. Recommended best practices for virtual real-time data collection include (1) providing adequate equipment for real-time data collection, (2) creating protocols and materials for research staff to facilitate or guide participants through data collection, (3) piloting data collection, (4) iteratively accepting feedback, and (5) providing instructions in multiple forms. The implementation of these best practices and recommendations for future research are further discussed in the paper. International Registered Report Identifier (IRRID): DERR1-10.2196/53790 ",
doi="10.2196/53790",
url="https://www.researchprotocols.org/2024/1/e53790",
url="http://www.ncbi.nlm.nih.gov/pubmed/38743477"
}


@Article{info:doi/10.2196/57978,
author="Zhu, Lingxuan
and Mou, Weiming
and Hong, Chenglin
and Yang, Tao
and Lai, Yancheng
and Qi, Chang
and Lin, Anqi
and Zhang, Jian
and Luo, Peng",
title="The Evaluation of Generative AI Should Include Repetition to Assess Stability",
journal="JMIR Mhealth Uhealth",
year="2024",
month="May",
day="6",
volume="12",
pages="e57978",
keywords="large language model",
keywords="generative AI",
keywords="ChatGPT",
keywords="artificial intelligence",
keywords="health care",
doi="10.2196/57978",
url="https://mhealth.jmir.org/2024/1/e57978",
url="http://www.ncbi.nlm.nih.gov/pubmed/38688841"
}


@Article{info:doi/10.2196/51526,
author="Ruksakulpiwat, Suebsarn
and Phianhasin, Lalipat
and Benjasirisan, Chitchanok
and Ding, Kedong
and Ajibade, Anuoluwapo
and Kumar, Ayanesh
and Stewart, Cassie",
title="Assessing the Efficacy of ChatGPT Versus Human Researchers in Identifying Relevant Studies on mHealth Interventions for Improving Medication Adherence in Patients With Ischemic Stroke When Conducting Systematic Reviews: Comparative Analysis",
journal="JMIR Mhealth Uhealth",
year="2024",
month="May",
day="6",
volume="12",
pages="e51526",
keywords="ChatGPT",
keywords="systematic reviews",
keywords="medication adherence",
keywords="mobile health",
keywords="mHealth",
keywords="ischemic stroke",
keywords="mobile phone",
abstract="Background: ChatGPT by OpenAI emerged as a potential tool for researchers, aiding in various aspects of research. One such application was the identification of relevant studies in systematic reviews. However, a comprehensive comparison of the efficacy of relevant study identification between human researchers and ChatGPT has not been conducted. Objective: This study aims to compare the efficacy of ChatGPT and human researchers in identifying relevant studies on medication adherence improvement using mobile health interventions in patients with ischemic stroke during systematic reviews. Methods: This study used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Four electronic databases, including CINAHL Plus with Full Text, Web of Science, PubMed, and MEDLINE, were searched to identify articles published from inception until 2023 using search terms based on MeSH (Medical Subject Headings) terms generated by human researchers versus ChatGPT. The authors independently screened the titles, abstracts, and full text of the studies identified through separate searches conducted by human researchers and ChatGPT. The comparison encompassed several aspects, including the ability to retrieve relevant studies, accuracy, efficiency, limitations, and challenges associated with each method. Results: A total of 6 articles identified through search terms generated by human researchers were included in the final analysis, of which 4 (67\%) reported improvements in medication adherence after the intervention. However, 33\% (2/6) of the included studies did not clearly state whether medication adherence improved after the intervention. A total of 10 studies were included based on search terms generated by ChatGPT, of which 6 (60\%) overlapped with studies identified by human researchers. Regarding the impact of mobile health interventions on medication adherence, most included studies (8/10, 80\%) based on search terms generated by ChatGPT reported improvements in medication adherence after the intervention. However, 20\% (2/10) of the studies did not clearly state whether medication adherence improved after the intervention. The precision in accurately identifying relevant studies was higher in human researchers (0.86) than in ChatGPT (0.77). This is consistent with the percentage of relevance, where human researchers (9.8\%) demonstrated a higher percentage of relevance than ChatGPT (3\%). However, when considering the time required for both humans and ChatGPT to identify relevant studies, ChatGPT substantially outperformed human researchers as it took less time to identify relevant studies. Conclusions: Our comparative analysis highlighted the strengths and limitations of both approaches. Ultimately, the choice between human researchers and ChatGPT depends on the specific requirements and objectives of each review, but the collaborative synergy of both approaches holds the potential to advance evidence-based research and decision-making in the health care field. ",
doi="10.2196/51526",
url="https://mhealth.jmir.org/2024/1/e51526",
url="http://www.ncbi.nlm.nih.gov/pubmed/38710069"
}


@Article{info:doi/10.2196/52074,
author="Lee, Lachlan
and Hall, Rosemary
and Stanley, James
and Krebs, Jeremy",
title="Tailored Prompting to Improve Adherence to Image-Based Dietary Assessment: Mixed Methods Study",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Apr",
day="15",
volume="12",
pages="e52074",
keywords="dietary assessment",
keywords="diet",
keywords="dietary",
keywords="nutrition",
keywords="mobile phone apps",
keywords="image-based dietary assessment",
keywords="nutritional epidemiology",
keywords="mHealth",
keywords="mobile health",
keywords="app",
keywords="apps",
keywords="applications",
keywords="image",
keywords="RCT",
keywords="randomized",
keywords="controlled trial",
keywords="controlled trials",
keywords="cross-over",
keywords="images",
keywords="photo",
keywords="photographs",
keywords="photos",
keywords="photograph",
keywords="assessment",
keywords="prompt",
keywords="prompts",
keywords="nudge",
keywords="nudges",
keywords="food",
keywords="meal",
keywords="meals",
keywords="consumption",
keywords="behaviour change",
keywords="behavior change",
abstract="Background: Accurately assessing an individual's diet is vital in the management of personal nutrition and in the study of the effect of diet on health. Despite its importance, the tools available for dietary assessment remain either too imprecise, expensive, or burdensome for clinical or research use. Image-based methods offer a potential new tool to improve the reliability and accessibility of dietary assessment. Though promising, image-based methods are sensitive to adherence, as images cannot be captured from meals that have already been consumed. Adherence to image-based methods may be improved with appropriately timed prompting via text message. Objective: This study aimed to quantitatively examine the effect of prompt timing on adherence to an image-based dietary record and qualitatively explore the participant experience of dietary assessment in order to inform the design of a novel image-based dietary assessment tool. Methods: This study used a randomized crossover design to examine the intraindividual effect of 3 prompt settings on the number of images captured in an image-based dietary record. The prompt settings were control, where no prompts were sent; standard, where prompts were sent at 7:15 AM, 11:15 AM, and 5:15 PM for every participant; and tailored, where prompt timing was tailored to habitual meal times for each participant. Participants completed a text-based dietary record at baseline to determine the timing of tailored prompts. Participants were randomized to 1 of 6 study sequences, each with a unique order of the 3 prompt settings, with each 3-day image-based dietary record separated by a washout period of at least 7 days. The qualitative component comprised semistructured interviews and questionnaires exploring the experience of dietary assessment. Results: A total of 37 people were recruited, and 30 participants (11 male, 19 female; mean age 30, SD 10.8 years), completed all image-based dietary records. The image rate increased by 0.83 images per day in the standard setting compared to control (P=.23) and increased by 1.78 images per day in the tailored setting compared to control (P?.001). We found that 13/21 (62\%) of participants preferred to use the image-based dietary record versus the text-based dietary record but reported method-specific challenges with each method, particularly the inability to record via an image after a meal had been consumed. Conclusions: Tailored prompting improves adherence to image-based dietary assessment. Future image-based dietary assessment tools should use tailored prompting and offer both image-based and written input options to improve record completeness. ",
doi="10.2196/52074",
url="https://mhealth.jmir.org/2024/1/e52074"
}


@Article{info:doi/10.2196/48694,
author="Segur-Ferrer, Joan
and Molt{\'o}-Puigmart{\'i}, Carolina
and Pastells-Peir{\'o}, Roland
and Vivanco-Hidalgo, Maria Rosa",
title="Methodological Frameworks and Dimensions to Be Considered in Digital Health Technology Assessment: Scoping Review and Thematic Analysis",
journal="J Med Internet Res",
year="2024",
month="Apr",
day="10",
volume="26",
pages="e48694",
keywords="digital health",
keywords="eHealth",
keywords="mHealth",
keywords="mobile health",
keywords="AI",
keywords="artificial intelligence",
keywords="framework",
keywords="health technology assessment",
keywords="scoping review",
keywords="technology",
keywords="health care system",
keywords="methodological framework",
keywords="thematic analysis",
abstract="Background: Digital health technologies (dHTs) offer a unique opportunity to address some of the major challenges facing health care systems worldwide. However, the implementation of dHTs raises some concerns, such as the limited understanding of their real impact on health systems and people's well-being or the potential risks derived from their use. In this context, health technology assessment (HTA) is 1 of the main tools that health systems can use to appraise evidence and determine the value of a given dHT. Nevertheless, due to the nature of dHTs, experts highlight the need to reconsider the frameworks used in traditional HTA. Objective: This scoping review (ScR) aimed to identify the methodological frameworks used worldwide for digital health technology assessment (dHTA); determine what domains are being considered; and generate, through a thematic analysis, a proposal for a methodological framework based on the most frequently described domains in the literature. Methods: The ScR was performed in accordance with the guidelines established in the PRISMA-ScR guidelines. We searched 7 databases for peer reviews and gray literature published between January 2011 and December 2021. The retrieved studies were screened using Rayyan in a single-blind manner by 2 independent authors, and data were extracted using ATLAS.ti software. The same software was used for thematic analysis. Results: The systematic search retrieved 3061 studies (n=2238, 73.1\%, unique), of which 26 (0.8\%) studies were included. From these, we identified 102 methodological frameworks designed for dHTA. These frameworks revealed great heterogeneity between them due to their different structures, approaches, and items to be considered in dHTA. In addition, we identified different wording used to refer to similar concepts. Through thematic analysis, we reduced this heterogeneity. In the first phase of the analysis, 176 provisional codes related to different assessment items emerged. In the second phase, these codes were clustered into 86 descriptive themes, which, in turn, were grouped in the third phase into 61 analytical themes and organized through a vertical hierarchy of 3 levels: level 1 formed by 13 domains, level 2 formed by 38 dimensions, and level 3 formed by 11 subdimensions. From these 61 analytical themes, we developed a proposal for a methodological framework for dHTA. Conclusions: There is a need to adapt the existing frameworks used for dHTA or create new ones to more comprehensively assess different kinds of dHTs. Through this ScR, we identified 26 studies including 102 methodological frameworks and tools for dHTA. The thematic analysis of those 26 studies led to the definition of 12 domains, 38 dimensions, and 11 subdimensions that should be considered in dHTA. ",
doi="10.2196/48694",
url="https://www.jmir.org/2024/1/e48694",
url="http://www.ncbi.nlm.nih.gov/pubmed/38598288"
}


@Article{info:doi/10.2196/52179,
author="Moorthy, Preetha
and Weinert, Lina
and Sch{\"u}ttler, Christina
and Svensson, Laura
and Sedlmayr, Brita
and M{\"u}ller, Julia
and Nagel, Till",
title="Attributes, Methods, and Frameworks Used to Evaluate Wearables and Their Companion mHealth Apps: Scoping Review",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Apr",
day="5",
volume="12",
pages="e52179",
keywords="wearables",
keywords="mobile health",
keywords="mHealth",
keywords="mobile phone",
keywords="usability methods",
keywords="usability attributes",
keywords="evaluation frameworks",
keywords="health care",
abstract="Background: Wearable devices, mobile technologies, and their combination have been accepted into clinical use to better assess the physical fitness and quality of life of patients and as preventive measures. Usability is pivotal for overcoming constraints and gaining users' acceptance of technology such as wearables and their companion mobile health (mHealth) apps. However, owing to limitations in design and evaluation, interactive wearables and mHealth apps have often been restricted from their full potential. Objective: This study aims to identify studies that have incorporated wearable devices and determine their frequency of use in conjunction with mHealth apps or their combination. Specifically, this study aims to understand the attributes and evaluation techniques used to evaluate usability in the health care domain for these technologies and their combinations. Methods: We conducted an extensive search across 4 electronic databases, spanning the last 30 years up to December 2021. Studies including the keywords ``wearable devices,'' ``mobile apps,'' ``mHealth apps,'' ``physiological data,'' ``usability,'' ``user experience,'' and ``user evaluation'' were considered for inclusion. A team of 5 reviewers screened the collected publications and charted the features based on the research questions. Subsequently, we categorized these characteristics following existing usability and wearable taxonomies. We applied a methodological framework for scoping reviews and the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) checklist. Results: A total of 382 reports were identified from the search strategy, and 68 articles were included. Most of the studies (57/68, 84\%) involved the simultaneous use of wearables and connected mobile apps. Wrist-worn commercial consumer devices such as wristbands were the most prevalent, accounting for 66\% (45/68) of the wearables identified in our review. Approximately half of the data from the medical domain (32/68, 47\%) focused on studies involving participants with chronic illnesses or disorders. Overall, 29 usability attributes were identified, and 5 attributes were frequently used for evaluation: satisfaction (34/68, 50\%), ease of use (27/68, 40\%), user experience (16/68, 24\%), perceived usefulness (18/68, 26\%), and effectiveness (15/68, 22\%). Only 10\% (7/68) of the studies used a user- or human-centered design paradigm for usability evaluation. Conclusions: Our scoping review identified the types and categories of wearable devices and mHealth apps, their frequency of use in studies, and their implementation in the medical context. In addition, we examined the usability evaluation of these technologies: methods, attributes, and frameworks. Within the array of available wearables and mHealth apps, health care providers encounter the challenge of selecting devices and companion apps that are effective, user-friendly, and compatible with user interactions. The current gap in usability and user experience in health care research limits our understanding of the strengths and limitations of wearable technologies and their companion apps. Additional research is necessary to overcome these limitations. ",
doi="10.2196/52179",
url="https://mhealth.jmir.org/2024/1/e52179",
url="http://www.ncbi.nlm.nih.gov/pubmed/38578671"
}


@Article{info:doi/10.2196/52763,
author="Gryglewicz, Kim
and Orr, L. Victoria
and McNeil, J. Marissa
and Taliaferro, A. Lindsay
and Hines, Serenea
and Duffy, L. Taylor
and Wisniewski, J. Pamela",
title="Translating Suicide Safety Planning Components Into the Design of mHealth App Features: Systematic Review",
journal="JMIR Ment Health",
year="2024",
month="Mar",
day="28",
volume="11",
pages="e52763",
keywords="suicide prevention",
keywords="suicide safety planning",
keywords="mobile health",
keywords="mHealth apps",
keywords="eHealth",
keywords="digital health",
keywords="systematic review",
keywords="Preferred Reporting Items for Systematic Reviews and Meta-Analyses",
keywords="PRISMA",
abstract="Background: Suicide safety planning is an evidence-based approach used to help individuals identify strategies to keep themselves safe during a mental health crisis. This study systematically reviewed the literature focused on mobile health (mHealth) suicide safety planning apps. Objective: This study aims to evaluate the extent to which apps integrated components of the safety planning intervention (SPI), and if so, how these safety planning components were integrated into the design-based features of the apps. Methods: Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we systematically analyzed 14 peer-reviewed studies specific to mHealth apps for suicide safety planning. We conducted an analysis of the literature to evaluate how the apps incorporated SPI components and examined similarities and differences among the apps by conducting a comparative analysis of app features. An independent review of SPI components and app features was conducted by downloading the available apps. Results: Most of the mHealth apps (5/7, 71\%) integrated SPI components and provided customizable features that expanded upon traditional paper-based safety planning processes. App design features were categorized into 5 themes, including interactive features, individualized user experiences, interface design, guidance and training, and privacy and sharing. All apps included access to community supports and revisable safety plans. Fewer mHealth apps (3/7, 43\%) included interactive features, such as associating coping strategies with specific stressors. Most studies (10/14, 71\%) examined the usability, feasibility, and acceptability of the safety planning mHealth apps. Usability findings were generally positive, as users often found these apps easy to use and visually appealing. In terms of feasibility, users preferred using mHealth apps during times of crisis, but the continuous use of the apps outside of crisis situations received less support. Few studies (4/14, 29\%) examined the effectiveness of mHealth apps for suicide-related outcomes. Positive shifts in attitudes and desire to live, improved coping strategies, enhanced emotional stability, and a decrease in suicidal thoughts or self-harm behaviors were examined in these studies. Conclusions: Our study highlights the need for researchers, clinicians, and app designers to continue to work together to align evidence-based research on mHealth suicide safety planning apps with lessons learned for how to best deliver these technologies to end users. Our review brings to light mHealth suicide safety planning strategies needing further development and testing, such as lethal means guidance, collaborative safety planning, and the opportunity to embed more interactive features that leverage the advanced capabilities of technology to improve client outcomes as well as foster sustained user engagement beyond a crisis. Although preliminary evidence shows that these apps may help to mitigate suicide risk, clinical trials with larger sample sizes and more robust research designs are needed to validate their efficacy before the widespread adoption and use. ",
doi="10.2196/52763",
url="https://mental.jmir.org/2024/1/e52763",
url="http://www.ncbi.nlm.nih.gov/pubmed/38546711"
}


@Article{info:doi/10.2196/55209,
author="Zhang, Yunxi
and Lin, Yueh-Yun
and Lal, S. Lincy
and Reneker, C. Jennifer
and Hinton, G. Elizabeth
and Chandra, Saurabh
and Swint, Michael J.",
title="Telehealth Evaluation in the United States: Protocol for a Scoping Review",
journal="JMIR Res Protoc",
year="2024",
month="Mar",
day="28",
volume="13",
pages="e55209",
keywords="cost",
keywords="effectiveness",
keywords="evaluation",
keywords="framework",
keywords="healthcare delivery",
keywords="measurement",
keywords="quality",
keywords="scoping review",
keywords="telehealth",
keywords="United States",
abstract="Background: The rapid expansion of telehealth services, driven by the COVID-19 pandemic, necessitates systematic evaluation to guarantee the quality, effectiveness, and cost-effectiveness of telehealth services and programs in the United States. While numerous evaluation frameworks have emerged, crafted by various stakeholders, their comprehensiveness is limited, and the overall state of telehealth evaluation remains unclear. Objective: The overarching goal of this scoping review is to create a comprehensive overview of telehealth evaluation, incorporating perspectives from multiple stakeholder categories. Specifically, we aim to (1) map the existing landscape of telehealth evaluation, (2) identify key concepts for evaluation, (3) synthesize existing evaluation frameworks, and (4) identify measurements and assessments considered in the United States. Methods: We will conduct this scoping review in accordance with the Joanna Briggs Institute (JBI) methodology for scoping reviews and in line with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews). This scoping review will consider documents, including reviews, reports, and white papers, published since January 1, 2019. It will focus on evaluation frameworks and associated measurements of telehealth services and programs in the US health care system, developed by telehealth stakeholders, professional organizations, and authoritative sources, excluding those developed by individual researchers, to collect data that reflect the collective expertise and consensus of experts within the respective professional group. Results: The data extracted from selected documents will be synthesized using tools such as tables and figures. Visual aids like Venn diagrams will be used to illustrate the relationships between the evaluation frameworks from various sources. A narrative summary will be crafted to further describe how the results align with the review objectives, facilitating a comprehensive overview of the findings. This scoping review is expected to conclude by August 2024. Conclusions: By addressing critical gaps in telehealth evaluation, this scoping review protocol lays the foundation for a comprehensive and multistakeholder assessment of telehealth services and programs. Its findings will inform policy makers, health care providers, researchers, and other stakeholders in advancing the quality, effectiveness, and cost-effectiveness of telehealth in the US health care system. Trial Registration: OSF Registries osf.io/aytus; https://osf.io/aytus International Registered Report Identifier (IRRID): DERR1-10.2196/55209 ",
doi="10.2196/55209",
url="https://www.researchprotocols.org/2024/1/e55209",
url="http://www.ncbi.nlm.nih.gov/pubmed/38546709"
}


@Article{info:doi/10.2196/52482,
author="Nguyen, Duy-Anh
and Li, Minyi
and Lambert, Gavin
and Kowalczyk, Ryszard
and McDonald, Rachael
and Vo, Bao Quoc",
title="Efficient Machine Reading Comprehension for Health Care Applications: Algorithm Development and Validation of a Context Extraction Approach",
journal="JMIR Form Res",
year="2024",
month="Mar",
day="25",
volume="8",
pages="e52482",
keywords="question answering",
keywords="machine reading comprehension",
keywords="context extraction",
keywords="covid19",
keywords="health care",
abstract="Background: Extractive methods for machine reading comprehension (MRC) tasks have achieved comparable or better accuracy than human performance on benchmark data sets. However, such models are not as successful when adapted to complex domains such as health care. One of the main reasons is that the context that the MRC model needs to process when operating in a complex domain can be much larger compared with an average open-domain context. This causes the MRC model to make less accurate and slower predictions. A potential solution to this problem is to reduce the input context of the MRC model by extracting only the necessary parts from the original context. Objective: This study aims to develop a method for extracting useful contexts from long articles as an additional component to the question answering task, enabling the MRC model to work more efficiently and accurately. Methods: Existing approaches to context extraction in MRC are based on sentence selection strategies, in which the models are trained to find the sentences containing the answer. We found that using only the sentences containing the answer was insufficient for the MRC model to predict correctly. We conducted a series of empirical studies and observed a strong relationship between the usefulness of the context and the confidence score output of the MRC model. Our investigation showed that a precise input context can boost the prediction correctness of the MRC and greatly reduce inference time. We proposed a method to estimate the utility of each sentence in a context in answering the question and then extract a new, shorter context according to these estimations. We generated a data set to train 2 models for estimating sentence utility, based on which we selected more precise contexts that improved the MRC model's performance. Results: We demonstrated our approach on the Question Answering Data Set for COVID-19 and Biomedical Semantic Indexing and Question Answering data sets and showed that the approach benefits the downstream MRC model. First, the method substantially reduced the inference time of the entire question answering system by 6 to 7 times. Second, our approach helped the MRC model predict the answer more correctly compared with using the original context (F1-score increased from 0.724 to 0.744 for the Question Answering Data Set for COVID-19 and from 0.651 to 0.704 for the Biomedical Semantic Indexing and Question Answering). We also found a potential problem where extractive transformer MRC models predict poorly despite being given a more precise context in some cases. Conclusions: The proposed context extraction method allows the MRC model to achieve improved prediction correctness and a significantly reduced MRC inference time. This approach works technically with any MRC model and has potential in tasks involving processing long texts. ",
doi="10.2196/52482",
url="https://formative.jmir.org/2024/1/e52482",
url="http://www.ncbi.nlm.nih.gov/pubmed/38526545"
}


@Article{info:doi/10.2196/50839,
author="Gagnon, Julie
and Probst, Sebastian
and Chartrand, Julie
and Lalonde, Michelle",
title="mHealth App Usability Questionnaire for Stand-Alone mHealth Apps Used by Health Care Providers: Canadian French Translation, Cross-Cultural Adaptation, and Validation (Part 1)",
journal="JMIR Form Res",
year="2024",
month="Feb",
day="13",
volume="8",
pages="e50839",
keywords="cross-cultural adaptation",
keywords="French language",
keywords="mHealth App Usability Questionnaire",
keywords="MAUQ",
keywords="mobile health",
keywords="mHealth",
keywords="mobile app",
keywords="questionnaire translation",
keywords="usability",
keywords="validation",
keywords="health care providers",
keywords="French translation",
abstract="Background: An increasing number of health care professionals are using mobile apps. The mHealth App Usability Questionnaire (MAUQ) was designed to evaluate the usability of mobile health apps by patients and providers. However, this questionnaire is not available in French. Objective: This study aims to translate (from English to Canadian French), cross-culturally adapt, and initiate the validation of the original version of MAUQ for stand-alone mobile health apps used by French-speaking health care providers. Methods: A cross-cultural research study using a well-established method was conducted to translate MAUQ to Canadian French by certified translators and subsequently review it with a translation committee. It was then back translated to English. The back translations were compared with the original by the members of the committee to reach consensus regarding the prefinal version. A pilot test of the prefinal version was conducted with a sample of 49 potential users and 10 experts for content validation. Results: The statements are considered clear, with interrater agreement of 99.14\% among potential users and 90\% among experts. Of 21 statements, 5 (24\%) did not exceed the 80\% interrater agreement of the experts regarding clarity. Following the revisions, interrater agreement exceeded 80\%. The content validity index of the items varied from 0.90 to 1, and the overall content validity index was 0.981. Individual Fleiss multirater $\kappa$ of each item was between 0.89 and 1, showing excellent agreement and increasing confidence in the questionnaire's content validity. Conclusions: This process of translation and cultural adaptation produced a new version of MAUQ that was validated for later use among the Canadian French--speaking population. An upcoming separate study will investigate the psychometric properties of the adapted questionnaire. ",
doi="10.2196/50839",
url="https://formative.jmir.org/2024/1/e50839",
url="http://www.ncbi.nlm.nih.gov/pubmed/38349710"
}


@Article{info:doi/10.2196/51057,
author="Robertson, C. Michael
and Cox-Martin, Emily
and Basen-Engquist, Karen
and Lyons, J. Elizabeth",
title="Reflective Engagement With a Digital Physical Activity Intervention Among People Living With and Beyond Breast Cancer: Mixed Methods Study",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Feb",
day="9",
volume="12",
pages="e51057",
keywords="survivors of cancer",
keywords="exercise",
keywords="acceptance and commitment therapy",
keywords="fatigue",
keywords="mindfulness",
keywords="motivation",
keywords="behavioral sciences",
abstract="Background: People living with and beyond breast cancer can face internal barriers to physical activity (eg, fatigue and pain). Digital interventions that promote psychological acceptance and motivation may help this population navigate these barriers. The degree to which individuals (1) adhere to intervention protocols and (2) reflect on and internalize intervention content may predict intervention efficacy. Objective: The objective of this study was to characterize the nature of reflective processes brought about by an 8-week acceptance- and mindfulness-based physical activity intervention for insufficiently active survivors of breast cancer (n=75). Furthermore, we explored the potential utility of a metric of reflective processes for predicting study outcomes. Methods: Of the intervention's 8 weekly modules, 7 (88\%) included an item that asked participants to reflect on what they found to be most useful. Two coders conducted directed content analysis on participants' written responses. They assessed each comment's depth of reflection using an existing framework (ranging from 0 to 4, with 0=simple description and 4=fundamental change with consideration of social and ethical issues). The coders identified themes within the various levels of reflection. We fit multiple linear regression models to evaluate whether participants' (1) intervention adherence (ie, number of modules completed) and (2) the mean level of the depth of reflection predicted study outcomes. Results: Participants were aged on average 57.2 (SD 11.2) years, mostly non-Hispanic White (58/75, 77\%), and mostly overweight or obese (54/75, 72\%). Of the 407 responses to the item prompting personal reflection, 70 (17.2\%) were rated as reflection level 0 (ie, description), 247 (60.7\%) were level 1 (ie, reflective description), 74 (18.2\%) were level 2 (ie, dialogic reflection), 14 (3.4\%) were level 3 (ie, transformative reflection), and 2 (0.5\%) were level 4 (ie, critical reflection). Lower levels of reflection were characterized by the acquisition of knowledge or expressing intentions. Higher levels were characterized by personal insight, commentary on behavior change processes, and a change of perspective. Intervention adherence was associated with increases in self-reported weekly bouts of muscle-strengthening exercise (B=0.26, SE 0.12, 95\% CI 0.02-0.50) and decreases in sleep disturbance (B=?1.04, SE 0.50, 95\% CI ?0.06 to ?2.02). The mean level of reflection was associated with increases in psychological acceptance (B=3.42, SE 1.70, 95\% CI 0.09-6.75) and motivation for physical activity (ie, integrated regulation: B=0.55, SE 0.25, 95\% CI 0.06-1.04). Conclusions: We identified a useful method for understanding the reflective processes that can occur during digital behavior change interventions serving people living with and beyond breast cancer. Intervention adherence and the depth of reflection each predicted changes in study outcomes. Deeper reflection on intervention content was associated with beneficial changes in the determinants of sustained behavior change. More research is needed to investigate the relations among digital behavior change intervention use, psychological processes, and intervention efficacy. ",
doi="10.2196/51057",
url="https://mhealth.jmir.org/2024/1/e51057",
url="http://www.ncbi.nlm.nih.gov/pubmed/38335025"
}


@Article{info:doi/10.2196/46347,
author="King, D. Zachary
and Yu, Han
and Vaessen, Thomas
and Myin-Germeys, Inez
and Sano, Akane",
title="Investigating Receptivity and Affect Using Machine Learning: Ecological Momentary Assessment and Wearable Sensing Study",
journal="JMIR Mhealth Uhealth",
year="2024",
month="Feb",
day="7",
volume="12",
pages="e46347",
keywords="mobile health",
keywords="mHealth",
keywords="affect inference",
keywords="study design",
keywords="ecological momentary assessment",
keywords="EMA",
keywords="just-in-time adaptive interventions",
keywords="JITAIs",
keywords="receptivity",
keywords="mobile phone",
abstract="Background: As mobile health (mHealth) studies become increasingly productive owing to the advancements in wearable and mobile sensor technology, our ability to monitor and model human behavior will be constrained by participant receptivity. Many health constructs are dependent on subjective responses, and without such responses, researchers are left with little to no ground truth to accompany our ever-growing biobehavioral data. This issue can significantly impact the quality of a study, particularly for populations known to exhibit lower compliance rates. To address this challenge, researchers have proposed innovative approaches that use machine learning (ML) and sensor data to modify the timing and delivery of surveys. However, an overarching concern is the potential introduction of biases or unintended influences on participants' responses when implementing new survey delivery methods. Objective: This study aims to demonstrate the potential impact of an ML-based ecological momentary assessment (EMA) delivery system (using receptivity as the predictor variable) on the participants' reported emotional state. We examine the factors that affect participants' receptivity to EMAs in a 10-day wearable and EMA--based emotional state--sensing mHealth study. We study the physiological relationships indicative of receptivity and affect while also analyzing the interaction between the 2 constructs. Methods: We collected data from 45 healthy participants wearing 2 devices measuring electrodermal activity, accelerometer, electrocardiography, and skin temperature while answering 10 EMAs daily, containing questions about perceived mood. Owing to the nature of our constructs, we can only obtain ground truth measures for both affect and receptivity during responses. Therefore, we used unsupervised and supervised ML methods to infer affect when a participant did not respond. Our unsupervised method used k-means clustering to determine the relationship between physiology and receptivity and then inferred the emotional state during nonresponses. For the supervised learning method, we primarily used random forest and neural networks to predict the affect of unlabeled data points as well as receptivity. Results: Our findings showed that using a receptivity model to trigger EMAs decreased the reported negative affect by >3 points or 0.29 SDs in our self-reported affect measure, scored between 13 and 91. The findings also showed a bimodal distribution of our predicted affect during nonresponses. This indicates that this system initiates EMAs more commonly during states of higher positive emotions. Conclusions: Our results showed a clear relationship between affect and receptivity. This relationship can affect the efficacy of an mHealth study, particularly those that use an ML algorithm to trigger EMAs. Therefore, we propose that future work should focus on a smart trigger that promotes EMA receptivity without influencing affect during sampled time points. ",
doi="10.2196/46347",
url="https://mhealth.jmir.org/2024/1/e46347",
url="http://www.ncbi.nlm.nih.gov/pubmed/38324358"
}


@Article{info:doi/10.2196/51839,
author="Oldham, Melissa
and Dinu, Larisa
and Loebenberg, Gemma
and Field, Matt
and Hickman, Matthew
and Michie, Susan
and Brown, Jamie
and Garnett, Claire",
title="Methodological Insights on Recruitment and Retention From a Remote Randomized Controlled Trial Examining the Effectiveness of an Alcohol Reduction App: Descriptive Analysis Study",
journal="JMIR Form Res",
year="2024",
month="Jan",
day="5",
volume="8",
pages="e51839",
keywords="alcohol reduction",
keywords="alcohol",
keywords="digital care",
keywords="digital intervention",
keywords="ethnic minority",
keywords="methods",
keywords="mHealth",
keywords="randomised controlled trial",
keywords="recruitment",
keywords="retention",
keywords="social media",
abstract="Background: Randomized controlled trials (RCTs) with no in-person contact (ie, remote) between researchers and participants offer savings in terms of cost and time but present unique challenges. Objective: The goal of this study is to examine the differences between different forms of remote recruitment (eg, National Health Service [NHS] website, social media, and radio advertising) in the proportion of participants recruited, demographic diversity, follow-up rates, and cost. We also examine the cost per participant of sequential methods of follow-up (emails, phone calls, postal surveys, and postcards). Finally, our experience with broader issues around study advertising and participant deception is discussed. Methods: We conducted a descriptive analysis of 5602 increasing-and-higher-risk drinkers (Alcohol Use Disorders Identification Test score ?8), taking part in a 2-arm, parallel group, remote RCT with a 1:1 allocation, comparing the intervention (Drink Less app) with usual digital care (NHS alcohol advice web page). Participants were recruited between July 2020 and March 2022 and compensated with gift vouchers of up to {\textsterling}36 (a currency exchange rate of {\textsterling}1=US \$1.26988 is applicable) for completing follow-up surveys, with 4 stages of follow-up: email reminders, phone calls, postal survey, and postcard. Results: The three main recruitment methods were advertisements on (1) social media (2483/5602, 44.32\%), (2) the NHS website (1961/5602, 35.01\%), and (3) radio and newspapers (745/5602, 13.3\%), with the remaining methods of recruitment accounting 7.37\% (413/5602) of the sample. The overall recruitment cost per participant varied from {\textsterling}0 to {\textsterling}11.01. Costs were greater when recruiting participants who were men ({\textsterling}0-{\textsterling}28.85), from an ethnic minority group ({\textsterling}0-{\textsterling}303.81), and more disadvantaged ({\textsterling}0-{\textsterling}49.12). Targeted approaches were useful for recruiting more men but less useful in achieving diversity in ethnicity and socioeconomic status. Follow-up at 6 months was 79.58\% (4458/5602). Of those who responded, 92.4\% (4119/4458) responded by email. Each additional stage of follow-up resulted in an additional 2-3 percentage points of the overall sample being followed up, although phone calls, postal surveys, and postcards were more resource intensive than email reminders. Conclusions: For remote RCTs, researchers could benefit from using a range of recruitment methods and cost-targeted approaches to achieve demographic diversity. Automated emails with substantial financial incentives for prompt completion can achieve good follow-up rates, and sequential, offline follow-up options, such as phone calls and postal surveys, can further increase follow-up rates but are comparatively expensive. We also make broader recommendations focused on striking the right balance when designing remote RCTs. Careful planning, ongoing maintenance, and dynamic decision-making are required throughout a trial to balance the competing demands of participation among those eligible, deceptive participation among those who are not eligible, and ensuring no postrandomization bias is introduced by data-checking protocols. ",
doi="10.2196/51839",
url="https://formative.jmir.org/2024/1/e51839",
url="http://www.ncbi.nlm.nih.gov/pubmed/38180802"
}


@Article{info:doi/10.2196/50663,
author="Kim, Junhyoung
and Choi, Jin-Young
and Kim, Hana
and Lee, Taeksang
and Ha, Jaeyoung
and Lee, Sangyi
and Park, Jungmi
and Jeon, Gyeong-Suk
and Cho, Sung-il",
title="Physical Activity Pattern of Adults With Metabolic Syndrome Risk Factors: Time-Series Cluster Analysis",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Dec",
day="1",
volume="11",
pages="e50663",
keywords="wrist-worn wearable",
keywords="wearable data",
keywords="physical activity pattern",
keywords="TADPole clustering",
keywords="TADPole",
keywords="cluster",
keywords="clustering",
keywords="wearable",
keywords="wearables",
keywords="wrist-worn",
keywords="physical activity",
keywords="pattern",
keywords="patterns",
keywords="data analysis",
keywords="data analytics",
keywords="regression",
keywords="risk",
keywords="risks",
keywords="time series",
keywords="Time-Series Anytime Density Peak",
abstract="Background: Physical activity plays a crucial role in maintaining a healthy lifestyle, and wrist-worn wearables, such as smartwatches and smart bands, have become popular tools for measuring activity levels in daily life. However, studies on physical activity using wearable devices have limitations; for example, these studies often rely on a single device model or use improper clustering methods to analyze the wearable data that are extracted from wearable devices. Objective: This study aimed to identify methods suitable for analyzing wearable data and determining daily physical activity patterns. This study also explored the association between these physical activity patterns and health risk factors. Methods: People aged >30 years who had metabolic syndrome risk factors and were using their own wrist-worn devices were included in this study. We collected personal health data through a web-based survey and measured physical activity levels using wrist-worn wearables over the course of 1 week. The Time-Series Anytime Density Peak (TADPole) clustering method, which is a novel time-series method proposed recently, was used to identify the physical activity patterns of study participants. Additionally, we defined physical activity pattern groups based on the similarity of physical activity patterns between weekdays and weekends. We used the $\chi$2 or Fisher exact test for categorical variables and the 2-tailed t test for numerical variables to find significant differences between physical activity pattern groups. Logistic regression models were used to analyze the relationship between activity patterns and health risk factors. Results: A total of 47 participants were included in the analysis, generating a total of 329 person-days of data. We identified 2 different types of physical activity patterns (early bird pattern and night owl pattern) for weekdays and weekends. The physical activity levels of early birds were less than that of night owls on both weekdays and weekends. Additionally, participants were categorized into stable and shifting groups based on the similarity of physical activity patterns between weekdays and weekends. The physical activity pattern groups showed significant differences depending on age (P=.004) and daily energy expenditure (P<.001 for weekdays; P=.003 for weekends). Logistic regression analysis revealed a significant association between older age (?40 y) and shifting physical activity patterns (odds ratio 8.68, 95\% CI 1.95-48.85; P=.007). Conclusions: This study overcomes the limitations of previous studies by using various models of wrist-worn wearables and a novel time-series clustering method. Our findings suggested that age significantly influenced physical activity patterns. It also suggests a potential role of the TADPole clustering method in the analysis of large and multidimensional data, such as wearable data. ",
doi="10.2196/50663",
url="https://mhealth.jmir.org/2023/1/e50663"
}


@Article{info:doi/10.2196/41551,
author="Khalemsky, Michael
and Khalemsky, Anna
and Lankenau, Stephen
and Ataiants, Janna
and Roth, Alexis
and Marcu, Gabriela
and Schwartz, G. David",
title="Predictive Dispatch of Volunteer First Responders: Algorithm Development and Validation",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Nov",
day="28",
volume="11",
pages="e41551",
keywords="volunteer",
keywords="emergency",
keywords="dispatch",
keywords="responder",
keywords="smartphone",
keywords="emergency response",
keywords="smartphone-based apps",
keywords="mobile phone apps",
keywords="first responders",
keywords="medical emergency",
keywords="dispatch algorithms",
keywords="dispatch decisions",
keywords="dispatch prediction",
keywords="smartphone app",
keywords="decision-making",
keywords="algorithm",
keywords="mobile health",
keywords="mHealth intervention",
keywords="mobile phone",
abstract="Background: Smartphone-based emergency response apps are increasingly being used to identify and dispatch volunteer first responders (VFRs) to medical emergencies to provide faster first aid, which is associated with better prognoses. Volunteers' availability and willingness to respond are uncertain, leading in recent studies to response rates of 17\% to 47\%. Dispatch algorithms that select volunteers based on their estimated time of arrival (ETA) without considering the likelihood of response may be suboptimal due to a large percentage of alerts wasted on VFRs with shorter ETA but a low likelihood of response, resulting in delays until a volunteer who will actually respond can be dispatched. Objective: This study aims to improve the decision-making process of human emergency medical services dispatchers and autonomous dispatch algorithms by presenting a novel approach for predicting whether a VFR will respond to or ignore a given alert. Methods: We developed and compared 4 analytical models to predict VFRs' response behaviors based on emergency event characteristics, volunteers' demographic data and previous experience, and condition-specific parameters. We tested these 4 models using 4 different algorithms applied on actual demographic and response data from a 12-month study of 112 VFRs who received 993 alerts to respond to 188 opioid overdose emergencies. Model 4 used an additional dynamically updated synthetic dichotomous variable, frequent responder, which reflects the responder's previous behavior. Results: The highest accuracy (260/329, 79.1\%) of prediction that a VFR will ignore an alert was achieved by 2 models that used events data, VFRs' demographic data, and their previous response experience, with slightly better overall accuracy (248/329, 75.4\%) for model 4, which used the frequent responder indicator. Another model that used events data and VFRs' previous experience but did not use demographic data provided a high-accuracy prediction (277/329, 84.2\%) of ignored alerts but a low-accuracy prediction (153/329, 46.5\%) of responded alerts. The accuracy of the model that used events data only was unacceptably low. The J48 decision tree algorithm provided the best accuracy. Conclusions: VFR dispatch has evolved in the last decades, thanks to technological advances and a better understanding of VFR management. The dispatch of substitute responders is a common approach in VFR systems. Predicting the response behavior of candidate responders in advance of dispatch can allow any VFR system to choose the best possible response candidates based not only on ETA but also on the probability of actual response. The integration of the probability to respond into the dispatch algorithm constitutes a new generation of individual dispatch, making this one of the first studies to harness the power of predictive analytics for VFR dispatch. Our findings can help VFR network administrators in their continual efforts to improve the response times of their networks and to save lives. ",
doi="10.2196/41551",
url="https://mhealth.jmir.org/2023/1/e41551",
url="http://www.ncbi.nlm.nih.gov/pubmed/38015602"
}


@Article{info:doi/10.2196/47043,
author="Hyzy, Maciej
and Bond, Raymond
and Mulvenna, Maurice
and Bai, Lu
and Dix, Alan
and Daly, Robert
and Frey, Anna-Lena
and Leigh, Simon",
title="Quality of Digital Health Interventions Across Different Health Care Domains: Secondary Data Analysis Study",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Nov",
day="23",
volume="11",
pages="e47043",
keywords="digital health interventions scoring",
keywords="digital health interventions",
keywords="digital health",
keywords="mHealth assessment",
keywords="mobile health",
keywords="ORCHA assessment",
keywords="Organisation for the Review of Care and Health Apps",
keywords="quality assessment",
keywords="quantifying DHIs",
abstract="Background: There are more than 350,000 digital health interventions (DHIs) in the app stores. To ensure that they are effective and safe to use, they should be assessed for compliance with best practice standards. Objective: The objective of this paper was to examine and compare the compliance of DHIs with best practice standards and adherence to user experience (UX), professional and clinical assurance (PCA), and data privacy (DP). Methods: We collected assessment data from 1574 DHIs using the Organisation for the Review of Care and Health Apps Baseline Review (OBR) assessment tool. As part of the assessment, each DHI received a score out of 100 for each of the abovementioned areas (ie, UX, PCA, and DP). These 3 OBR scores are combined to make up the overall ORCHA score (a proxy for quality). Inferential statistics, probability distributions, Kruskal-Wallis, Wilcoxon rank sum test, Cliff delta, and Dunn tests were used to conduct the data analysis. Results: We found that 57.3\% (902/1574) of the DHIs had an Organisation for the Review of Care and Health Apps (ORCHA) score below the threshold of 65. The overall median OBR score (ORCHA score) for all DHIs was 61.5 (IQR 51.0-73.0) out of 100. A total of 46.2\% (12/26) of DHI's health care domains had a median equal to or above the ORCHA threshold score of 65. For the 3 assessment areas (UX, DP, and PCA), DHIs scored the highest for the UX assessment 75.2 (IQR 70.0-79.6), followed by DP 65.1 (IQR 55.0-73.4) and PCA 49.6 (IQR 31.9-76.1). UX scores had the least variance (SD 13.9), while PCA scores had the most (SD 24.8). Respiratory and urology DHIs were consistently highly ranked in the National Institute for Health and Care Excellence Evidence Standards Framework tiers B and C based on their ORCHA score. Conclusions: There is a high level of variability in the ORCHA scores of DHIs across different health care domains. This suggests that there is an urgent need to improve compliance with best practices in some health care areas. Possible explanations for the observed differences might include varied market maturity and commercial interests within the different health care domains. More investment to support the development of higher-quality DHIs in areas such as ophthalmology, allergy, women's health, sexual health, and dental care may be needed. ",
doi="10.2196/47043",
url="https://mhealth.jmir.org/2023/1/e47043",
url="http://www.ncbi.nlm.nih.gov/pubmed/37995121"
}


@Article{info:doi/10.2196/34232,
author="Nurmi, Johanna
and Knittle, Keegan
and Naughton, Felix
and Sutton, Stephen
and Ginchev, Todor
and Khattak, Fida
and Castellano-Tejedor, Carmina
and Lusilla-Palacios, Pilar
and Ravaja, Niklas
and Haukkala, Ari",
title="Biofeedback and Digitalized Motivational Interviewing to Increase Daily Physical Activity: Series of Factorial N-of-1 Randomized Controlled Trials Piloting the Precious App",
journal="JMIR Form Res",
year="2023",
month="Nov",
day="23",
volume="7",
pages="e34232",
keywords="smartphone",
keywords="daily steps",
keywords="activity tracker",
keywords="activity bracelet",
keywords="motivational interviewing",
keywords="self-efficacy",
keywords="self-regulation",
keywords="biofeedback",
keywords="N-of-1",
keywords="automated",
keywords="digitalized",
keywords="behavior change",
keywords="intervention",
keywords="ecological momentary assessment",
keywords="within-person design",
keywords="intensive longitudinal multilevel modeling",
keywords="mobile phone",
abstract="Background: Insufficient physical activity is a public health concern. New technologies may improve physical activity levels and enable the identification of its predictors with high accuracy. The Precious smartphone app was developed to investigate the effect of specific modular intervention elements on physical activity and examine theory-based predictors within individuals. Objective: This study pilot-tested a fully automated factorial N-of-1 randomized controlled trial (RCT) with the Precious app and examined whether digitalized motivational interviewing (dMI) and heart rate variability--based biofeedback features increased objectively recorded steps. The secondary aim was to assess whether daily self-efficacy and motivation predicted within-person variability in daily steps. Methods: In total, 15 adults recruited from newspaper advertisements participated in a 40-day factorial N-of-1 RCT. They installed 2 study apps on their phones: one to receive intervention elements and one to collect ecological momentary assessment (EMA) data on self-efficacy, motivation, perceived barriers, pain, and illness. Steps were tracked using Xiaomi Mi Band activity bracelets. The factorial design included seven 2-day biofeedback interventions with a Firstbeat Bodyguard 2 (Firstbeat Technologies Ltd) heart rate variability sensor, seven 2-day dMI interventions, a wash-out day after each intervention, and 11 control days. EMA questions were sent twice per day. The effects of self-efficacy, motivation, and the interventions on subsequent steps were analyzed using within-person dynamic regression models and aggregated data using longitudinal multilevel modeling (level 1: daily observations; level 2: participants). The analyses were adjusted for covariates (ie, within- and between-person perceived barriers, pain or illness, time trends, and recurring events). Results: All participants completed the study, and adherence to activity bracelets and EMA measurements was high. The implementation of the factorial design was successful, with the dMI features used, on average, 5.1 (SD 1.0) times of the 7 available interventions. Biofeedback interventions were used, on average, 5.7 (SD 1.4) times out of 7, although 3 participants used this feature a day later than suggested and 1 did not use it at all. Neither within- nor between-person analyses revealed significant intervention effects on step counts. Self-efficacy predicted steps in 27\% (4/15) of the participants. Motivation predicted steps in 20\% (3/15) of the participants. Aggregated data showed significant group-level effects of day-level self-efficacy (B=0.462; P<.001), motivation (B=0.390; P<.001), and pain or illness (B=?1524; P<.001) on daily steps. Conclusions: The automated factorial N-of-1 trial with the Precious app was mostly feasible and acceptable, especially the automated delivery of the dMI components, whereas self-conducted biofeedback measurements were more difficult to time correctly. The findings suggest that changes in self-efficacy and motivation may have same-day effects on physical activity, but the effects vary across individuals. This study provides recommendations based on the lessons learned on the implementation of factorial N-of-1 RCTs. ",
doi="10.2196/34232",
url="https://formative.jmir.org/2023/1/e34232",
url="http://www.ncbi.nlm.nih.gov/pubmed/37995122"
}


@Article{info:doi/10.2196/46937,
author="Frey, Anna-Lena
and Baines, Rebecca
and Hunt, Sophie
and Kent, Rachael
and Andrews, Tim
and Leigh, Simon",
title="Association Between the Characteristics of mHealth Apps and User Input During Development and Testing: Secondary Analysis of App Assessment Data",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Nov",
day="22",
volume="11",
pages="e46937",
keywords="patient and public involvement",
keywords="user involvement",
keywords="mobile apps",
keywords="digital health",
keywords="mobile health",
keywords="quality assessment",
abstract="Background: User involvement is increasingly acknowledged as a central part of health care innovation. However, meaningful user involvement during the development and testing of mobile health apps is often not fully realized. Objective: This study aims to examine in which areas user input is most prevalent and whether there is an association between user inclusion and compliance with best practices for mobile health apps. Methods: A secondary analysis was conducted on an assessment data set of 1595 health apps. The data set contained information on whether the apps had been developed or tested with user input and whether they followed best practices across several domains. Background information was also available regarding the apps' country of origin, targeted condition areas, subjective user ratings, download numbers, and risk (as per the National Institute for Health and Care Excellence Evidence Standards Framework [ESF]). Descriptive statistics, Mann-Whitney U tests, and Pearson chi-square analyses were applied to the data. Results: User involvement was reported by 8.71\% (139/1595) of apps for only the development phase, by 33.67\% (537/1595) of apps for only the testing phase, by 21.88\% (349/1595) of apps for both phases, and by 35.74\% (570/1595) of apps for neither phase. The highest percentage of health apps with reported user input during development was observed in Denmark (19/24, 79\%); in the condition areas of diabetes (38/79, 48\%), cardiology (15/32, 47\%), pain management (20/43, 47\%), and oncology (25/54, 46\%); and for high app risk (ESF tier 3a; 105/263, 39.9\%). The highest percentage of health apps with reported user input during testing was observed in Belgium (10/11, 91\%), Sweden (29/34, 85\%), and France (13/16, 81\%); in the condition areas of neurodiversity (42/52, 81\%), respiratory health (58/76, 76\%), cardiology (23/32, 72\%), and diabetes (56/79, 71\%); and for high app risk (ESF tier 3a; 176/263, 66.9\%). Notably, apps that reported seeking user input during testing demonstrated significantly more downloads than those that did not (P=.008), and user inclusion was associated with better compliance with best practices in clinical assurance, data privacy, risk management, and user experience. Conclusions: The countries and condition areas in which the highest percentage of health apps with user involvement were observed tended to be those with higher digital maturity in health care and more funding availability, respectively. This suggests that there may be a trade-off between developers' willingness or ability to involve users and the need to meet challenges arising from infrastructure limitations and financial constraints. Moreover, the finding of a positive association between user inclusion and compliance with best practices indicates that, where no other guidance is available, users may benefit from prioritizing health apps developed with user input as the latter may be a proxy for broader app quality. ",
doi="10.2196/46937",
url="https://mhealth.jmir.org/2023/1/e46937",
url="http://www.ncbi.nlm.nih.gov/pubmed/37991822"
}


@Article{info:doi/10.2196/46237,
author="Grayek, Emily
and Krishnamurti, Tamar
and Hu, Lydia
and Babich, Olivia
and Warren, Katherine
and Fischhoff, Baruch",
title="Collection and Analysis of Adherence Information for Software as a Medical Device Clinical Trials: Systematic Review",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Nov",
day="15",
volume="11",
pages="e46237",
keywords="mobile health",
keywords="mHealth",
keywords="adherence",
keywords="evaluation",
keywords="usability",
keywords="efficacy",
keywords="systematic review",
keywords="application",
keywords="compliance",
keywords="safety",
keywords="effectiveness",
keywords="engagement",
keywords="risk",
keywords="medical device",
keywords="clinical trials",
abstract="Background: The rapid growth of digital health apps has necessitated new regulatory approaches to ensure compliance with safety and effectiveness standards. Nonadherence and heterogeneous user engagement with digital health apps can lead to trial estimates that overestimate or underestimate an app's effectiveness. However, there are no current standards for how researchers should measure adherence or address the risk of bias imposed by nonadherence through efficacy analyses. Objective: This systematic review aims to address 2 critical questions regarding clinical trials of software as a medical device (SaMD) apps: How well do researchers report adherence and engagement metrics for studies of effectiveness and efficacy? and What efficacy analyses do researchers use to account for nonadherence and how appropriate are their methods? Methods: We searched the Food and Drug Administration's registration database for registrations of repeated-use, patient-facing SaMD therapeutics. For each such registration, we searched ClinicalTrials.gov, company websites, and MEDLINE for the corresponding clinical trial and study articles through March 2022. Adherence and engagement data were summarized for each of the 24 identified articles, corresponding to 10 SaMD therapeutics. Each article was analyzed with a framework developed using the Cochrane risk-of-bias questions to estimate the potential effects of imperfect adherence on SaMD effectiveness. This review, funded by the Richard King Mellon Foundation, is registered on the Open Science Framework. Results: We found that although most articles (23/24, 96\%) reported collecting information about SaMD therapeutic engagement, of the 20 articles for apps with prescribed use, only 9 (45\%) reported adherence information across all aspects of prescribed use: 15 (75\%) reported metrics for the initiation of therapeutic use, 16 (80\%) reported metrics reporting adherence between the initiation and discontinuation of the therapeutic (implementation), and 4 (20\%) reported the discontinuation of the therapeutic (persistence). The articles varied in the reported metrics. For trials that reported adherence or engagement, there were 4 definitions of initiation, 8 definitions of implementation, and 4 definitions of persistence. All articles studying a therapeutic with a prescribed use reported effectiveness estimates that might have been affected by nonadherence; only a few (2/20, 10\%) used methods appropriate to evaluate efficacy. Conclusions: This review identifies 5 areas for improving future SaMD trials and studies: use consistent metrics for reporting adherence, use reliable adherence metrics, preregister analyses for observational studies, use less biased efficacy analysis methods, and fully report statistical methods and assumptions. ",
doi="10.2196/46237",
url="https://mhealth.jmir.org/2023/1/e46237",
url="http://www.ncbi.nlm.nih.gov/pubmed/37966871"
}


@Article{info:doi/10.2196/43186,
author="Gomez-Hernandez, Miguel
and Ferre, Xavier
and Moral, Cristian
and Villalba-Mora, Elena",
title="Design Guidelines of Mobile Apps for Older Adults: Systematic Review and Thematic Analysis",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Sep",
day="21",
volume="11",
pages="e43186",
keywords="tablet",
keywords="smartphone",
keywords="older user",
keywords="design recommendations",
keywords="usability testing",
keywords="user experience design",
keywords="UX design",
keywords="design",
keywords="mobile app",
keywords="tool",
keywords="quality of life",
keywords="software",
keywords="training",
keywords="visual design",
keywords="older adults",
keywords="mobile phone",
abstract="Background: Mobile apps are fundamental tools in today's society for practical and social endeavors. However, these technologies are often not usable for older users. Given the increased use of mobile apps by this group of users and the impact that certain services may have on their quality of life, such as mobile health, personal finance, or online administrative procedures, a clear set of guidelines for mobile app designers is needed. Existing recommendations for older adults focus on investigations with certain groups of older adults or have not been extracted from experimental results. Objective: In this research work, we systematically reviewed the scientific literature that provided recommendations for the design of mobile apps based on usability testing with older adults and organized such recommendations into a meaningful set of design guidelines. Methods: We conducted a systematic literature review of journal and conference articles from 2010 to 2021. We included articles that carried out usability tests with populations aged >60 years and presented transferable guidelines on mobile software design, resulting in a final set of 40 articles. We then carried out a thematic analysis with 3 rounds of analysis to provide meaning to an otherwise diverse set of recommendations. At this stage, we discarded recommendations that were made by just 1 article, were based on a specific mobile app and were therefore nontransferrable, were based on other authors' literature (as opposed to recommendations based on the results of usability tests), or were not sufficiently argued. With the remaining recommendations, we identified commonalities, wrote a faithful statement for each guideline, used a common language for the entire set, and organized the guidelines into categories, thereby giving shape to an otherwise diverse set of recommendations. Results: Among the 27 resulting guidelines, the rules Simplify and Increase the size and distance between interactive controls were transversal and of the greatest significance. The rest of the guidelines were divided into 5 categories (Help \& Training, Navigation, Visual Design, Cognitive Load, and Interaction) and consequent subcategories in Visual Design (Layout, Icons, and Appearance) and Interaction (Input and Output). The recommendations were structured, explained in detail, and illustrated with applied examples extracted from the selected studies, where appropriate. We discussed the design implications of applying these guidelines, contextualized with relevant studies. We also discussed the limitations of the approach followed, stressing the need for further experimentation to gain a better understanding of how older adults use mobile apps and how to better design such apps with these users in mind. Conclusions: The compiled guidelines support the design of mobile apps that cater to the needs of older adults because they are based on the results of actual usability tests with users aged >60 years. ",
doi="10.2196/43186",
url="https://mhealth.jmir.org/2023/1/e43186",
url="http://www.ncbi.nlm.nih.gov/pubmed/37733401"
}


@Article{info:doi/10.2196/43993,
author="Wong, Willis
and Ming, David
and Pateras, Sara
and Fee, Holmes Casey
and Coleman, Cara
and Docktor, Michael
and Shah, Nirmish
and Antonelli, Richard",
title="Outcomes of End-User Testing of a Care Coordination Mobile App With Families of Children With Special Health Care Needs: Simulation Study",
journal="JMIR Form Res",
year="2023",
month="Aug",
day="28",
volume="7",
pages="e43993",
keywords="mobile health",
keywords="mHealth",
keywords="complex care",
keywords="care coordination",
keywords="digital health tools",
keywords="simulation",
keywords="family-centered design",
keywords="user-centered design",
keywords="participatory design",
keywords="co-design",
abstract="Background: Care for children with special health care needs relies on a network of providers who work to address the medical, behavioral, developmental, educational, social, and economic needs of the child and their family. Family-directed, manually created visual depictions of care team composition (ie, care mapping) and detailed note-taking curated by caregivers (eg, care binders) have been shown to enhance care coordination for families of these children, but they are difficult to implement in clinical settings owing to a lack of integration with electronic health records and limited visibility of family-generated insights for care providers. Caremap is an electronic health record--integrated digital personal health record mobile app designed to integrate the benefits of care mapping and care binders. Currently, there is sparse literature describing end-user participation in the co-design of digital health tools. In this paper, we describe a project that evaluated the usability and proof of concept of the Caremap app through end-user simulation. Objective: This study aimed to conduct proof-of-concept testing of the Caremap app to coordinate care for children with special health care needs and explore early end-user engagement in simulation testing. The specific aims included engaging end users in app co-design via app simulation, evaluating the usability of the app using validated measures, and exploring user perspectives on how to make further improvements to the app. Methods: Caregivers of children with special health care needs were recruited to participate in a simulation exercise using Caremap to coordinate care for a simulated case of a child with complex medical and behavioral needs. Participants completed a postsimulation questionnaire adapted from 2 validated surveys: the Pediatric Integrated Care Survey (PICS) and the user version of the Mobile Application Rating Scale (uMARS). A key informant interview was also conducted with a liaison to Spanish-speaking families regarding app accessibility for non--English-speaking users. Results: A Caremap simulation was successfully developed in partnership with families of children with special health care needs. Overall, 38 families recruited from 19 different US states participated in the simulation exercise and completed the survey. The average rating for the survey adapted from the PICS was 4.1 (SD 0.82) out of 5, and the average rating for the adapted uMARS survey was 4 (SD 0.83) out of 5. The highest-rated app feature was the ability to track progress toward short-term, patient- and family-defined care goals. Conclusions: Internet-based simulation successfully facilitated end-user engagement and feedback for a digital health care coordination app for families of children with special health care needs. The families who completed simulation with Caremap rated it highly across several domains related to care coordination. The simulation study results elucidated key areas for improvement that translated into actionable next steps in app development. ",
doi="10.2196/43993",
url="https://formative.jmir.org/2023/1/e43993",
url="http://www.ncbi.nlm.nih.gov/pubmed/37639303"
}


@Article{info:doi/10.2196/41815,
author="Cumpanasoiu, Catalina Diana
and Enrique, Angel
and Palacios, E. Jorge
and Duffy, Daniel
and McNamara, Scott
and Richards, Derek",
title="Trajectories of Symptoms in Digital Interventions for Depression and Anxiety Using Routine Outcome Monitoring Data: Secondary Analysis Study",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Jul",
day="12",
volume="11",
pages="e41815",
keywords="internet-delivered cognitive behavioral therapy",
keywords="iCBT",
keywords="depression",
keywords="anxiety",
keywords="trajectory of symptom change",
keywords="routine outcome monitoring data",
abstract="Background: Research suggests there is heterogeneity in treatment response for internet-delivered cognitive behavioral therapy (iCBT) users, but few studies have investigated the trajectory of individual symptom change across iCBT treatment. Large patient data sets using routine outcome measures allows the investigation of treatment effects over time as well as the relationship between outcomes and platform use. Understanding trajectories of symptom change, as well as associated characteristics, may prove important for tailoring interventions or identifying patients who may not benefit from the intervention. Objective: We aimed to identify latent trajectories of symptom change during the iCBT treatment course for depression and anxiety and to investigate the patients' characteristics and platform use for each of these classes. Methods: This is a secondary analysis of data from a randomized controlled trial designed to examine the effectiveness of guided iCBT for anxiety and depression in the UK Improving Access to Psychological Therapies (IAPT) program. This study included patients from the intervention group (N=256) and followed a longitudinal retrospective design. As part of the IAPT's routine outcome monitoring system, patients were prompted to complete the Patient Health Questionnaire-9 (PHQ-9) and Generalized Anxiety Disorder-7 (GAD-7) after each supporter review during the treatment period. Latent class growth analysis was used to identify the underlying trajectories of symptom change across the treatment period for both depression and anxiety. Differences in patient characteristics were then evaluated between these trajectory classes, and the presence of a time-varying relationship between platform use and trajectory classes was investigated. Results: Five-class models were identified as optimal for both PHQ-9 and GAD-7. Around two-thirds (PHQ-9: 155/221, 70.1\%; GAD-7: 156/221, 70.6\%) of the sample formed various trajectories of improvement classes that differed in baseline score, the pace of symptom change, and final clinical outcome score. The remaining patients were in 2 smaller groups: one that saw minimal to no gains and another with consistently high scores across the treatment journey. Baseline severity, medication status, and program assigned were significantly associated (P<.001) with different trajectories. Although we did not find a time-varying relationship between use and trajectory classes, we found an overall effect of time on platform use, suggesting that all participants used the intervention significantly more in the first 4 weeks (P<.001). Conclusions: Most patients benefit from treatment, and the various patterns of improvement have implications for how the iCBT intervention is delivered. Identifying predictors of nonresponse or early response might inform the level of support and monitoring required for different types of patients. Further work is necessary to explore the differences between these trajectories to understand what works best for whom and to identify early on those patients who are less likely to benefit from treatment. ",
doi="10.2196/41815",
url="https://mhealth.jmir.org/2023/1/e41815",
url="http://www.ncbi.nlm.nih.gov/pubmed/37436812"
}


@Article{info:doi/10.2196/43826,
author="Tonkin, Sarah
and Gass, Julie
and Wray, Jennifer
and Maguin, Eugene
and Mahoney, Martin
and Colder, Craig
and Tiffany, Stephen
and Hawk Jr, W. Larry",
title="Evaluating Declines in Compliance With Ecological Momentary Assessment in Longitudinal Health Behavior Research: Analyses From a Clinical Trial",
journal="J Med Internet Res",
year="2023",
month="Jun",
day="22",
volume="25",
pages="e43826",
keywords="ecological momentary assessment",
keywords="compliance",
keywords="health behavior",
keywords="methodology",
keywords="longitudinal",
keywords="smoking",
keywords="smoker",
keywords="cessation",
keywords="quit",
keywords="adherence",
keywords="dropout",
keywords="RCT",
keywords="cigar",
keywords="retention",
abstract="Background: Ecological momentary assessment (EMA) is increasingly used to evaluate behavioral health processes over extended time periods. The validity of EMA for providing representative, real-world data with high temporal precision is threatened to the extent that EMA compliance drops over time. Objective: This research builds on prior short-term studies by evaluating the time course of EMA compliance over 9 weeks and examines predictors of weekly compliance rates among cigarette-using adults. Methods: A total of 257 daily cigarette-using adults participating in a randomized controlled trial for smoking cessation completed daily smartphone EMA assessments, including 1 scheduled morning assessment and 4 random assessments per day. Weekly EMA compliance was calculated and multilevel modeling assessed the rate of change in compliance over the 9-week assessment period. Participant and study characteristics were examined as predictors of overall compliance and changes in compliance rates over time. Results: Compliance was higher for scheduled morning assessments (86\%) than for random assessments (58\%) at the beginning of the EMA period (P<.001). EMA compliance declined linearly across weeks, and the rate of decline was greater for morning assessments (2\% per week) than for random assessments (1\% per week; P<.001). Declines in compliance were stronger for younger participants (P<.001), participants who were employed full-time (P=.03), and participants who subsequently dropped out of the study (P<.001). Overall compliance was higher among White participants compared to Black or African American participants (P=.001). Conclusions: This study suggests that EMA compliance declines linearly but modestly across lengthy EMA protocols. In general, these data support the validity of EMA for tracking health behavior and hypothesized treatment mechanisms over the course of several months. Future work should target improving compliance among subgroups of participants and investigate the extent to which rapid declines in EMA compliance might prove useful for triggering interventions to prevent study dropout. Trial Registration: ClinicalTrials.gov NCT03262662; https://clinicaltrials.gov/ct2/show/NCT03262662 ",
doi="10.2196/43826",
url="https://www.jmir.org/2023/1/e43826",
url="http://www.ncbi.nlm.nih.gov/pubmed/37347538"
}


@Article{info:doi/10.2196/43990,
author="Luken, Amanda
and Desjardins, R. Michael
and Moran, B. Meghan
and Mendelson, Tamar
and Zipunnikov, Vadim
and Kirchner, R. Thomas
and Naughton, Felix
and Latkin, Carl
and Thrul, Johannes",
title="Using Smartphone Survey and GPS Data to Inform Smoking Cessation Intervention Delivery: Case Study",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Jun",
day="16",
volume="11",
pages="e43990",
keywords="adult",
keywords="application",
keywords="case study",
keywords="cessation",
keywords="delivery",
keywords="GIS",
keywords="GPS",
keywords="health interventions",
keywords="mHealth",
keywords="mobile phone",
keywords="smartphone application",
keywords="smartphone",
keywords="smoker",
keywords="smoking cessation",
keywords="smoking",
abstract="Background: Interest in quitting smoking is common among young adults who smoke, but it can prove challenging. Although evidence-based smoking cessation interventions exist and are effective, a lack of access to these interventions specifically designed for young adults remains a major barrier for this population to successfully quit smoking. Therefore, researchers have begun to develop modern, smartphone-based interventions to deliver smoking cessation messages at the appropriate place and time for an individual. A promising approach is the delivery of interventions using geofences---spatial buffers around high-risk locations for smoking that trigger intervention messages when an individual's phone enters the perimeter. Despite growth in personalized and ubiquitous smoking cessation interventions, few studies have incorporated spatial methods to optimize intervention delivery using place and time information. Objective: This study demonstrates an exploratory method of generating person-specific geofences around high-risk areas for smoking by presenting 4 case studies using a combination of self-reported smartphone-based surveys and passively tracked location data. The study also examines which geofence construction method could inform a subsequent study design that will automate the process of deploying coping messages when young adults enter geofence boundaries. Methods: Data came from an ecological momentary assessment study with young adult smokers conducted from 2016 to 2017 in the San Francisco Bay area. Participants reported smoking and nonsmoking events through a smartphone app for 30 days, and GPS data was recorded by the app. We sampled 4 cases along ecological momentary assessment compliance quartiles and constructed person-specific geofences around locations with self-reported smoking events for each 3-hour time interval using zones with normalized mean kernel density estimates exceeding 0.7. We assessed the percentage of smoking events captured within geofences constructed for 3 types of zones (census blocks, 500 ft2 fishnet grids, and 1000 ft2 fishnet grids). Descriptive comparisons were made across the 4 cases to better understand the strengths and limitations of each geofence construction method. Results: The number of reported past 30-day smoking events ranged from 12 to 177 for the 4 cases. Each 3-hour geofence for 3 of the 4 cases captured over 50\% of smoking events. The 1000 ft2 fishnet grid captured the highest percentage of smoking events compared to census blocks across the 4 cases. Across 3-hour periods except for 3:00 AM-5:59 AM for 1 case, geofences contained an average of 36.4\%-100\% of smoking events. Findings showed that fishnet grid geofences may capture more smoking events compared to census blocks. Conclusions: Our findings suggest that this geofence construction method can identify high-risk smoking situations by time and place and has potential for generating individually tailored geofences for smoking cessation intervention delivery. In a subsequent smartphone-based smoking cessation intervention study, we plan to use fishnet grid geofences to inform the delivery of intervention messages. ",
doi="10.2196/43990",
url="https://mhealth.jmir.org/2023/1/e43990",
url="http://www.ncbi.nlm.nih.gov/pubmed/37327031"
}


@Article{info:doi/10.2196/44685,
author="Leong, Utek
and Chakraborty, Bibhas",
title="Participant Engagement in Microrandomized Trials of mHealth Interventions: Scoping Review",
journal="JMIR Mhealth Uhealth",
year="2023",
month="May",
day="22",
volume="11",
pages="e44685",
keywords="microrandomized trials",
keywords="engagement",
keywords="adherence",
keywords="mobile health",
keywords="mHealth interventions",
keywords="mobile phone",
abstract="Background: Microrandomized trials (MRTs) have emerged as the gold standard for the development and evaluation of multicomponent, adaptive mobile health (mHealth) interventions. However, not much is known about the state of participant engagement measurement in MRTs of mHealth interventions. Objective: In this scoping review, we aimed to quantify the proportion of existing or planned MRTs of mHealth interventions to date that have assessed (or have planned to assess) engagement. In addition, for the trials that have explicitly assessed (or have planned to assess) engagement, we aimed to investigate how engagement has been operationalized and to identify the factors that have been studied as determinants of engagement in MRTs of mHealth interventions. Methods: We conducted a broad search for MRTs of mHealth interventions in 5 databases and manually searched preprint servers and trial registries. Study characteristics of each included evidence source were extracted. We coded and categorized these data to identify how engagement has been operationalized and which determinants, moderators, and covariates have been assessed in existing MRTs. Results: Our database and manual search yielded 22 eligible evidence sources. Most of these studies (14/22, 64\%) were designed to evaluate the effects of intervention components. The median sample size of the included MRTs was 110.5. At least 1 explicit measure of engagement was included in 91\% (20/22) of the included MRTs. We found that objective measures such as system usage data (16/20, 80\%) and sensor data (7/20, 35\%) are the most common methods of measuring engagement. All studies included at least 1 measure of the physical facet of engagement, but the affective and cognitive facets of engagement have largely been neglected (only measured by 1 study each). Most studies measured engagement with the mHealth intervention (Little e) and not with the health behavior of interest (Big E). Only 6 (30\%) of the 20 studies that measured engagement assessed the determinants of engagement in MRTs of mHealth interventions; notification-related variables were the most common determinants of engagement assessed (4/6, 67\% studies). Of the 6 studies, 3 (50\%) examined the moderators of participant engagement---2 studies investigated time-related moderators exclusively, and 1 study planned to investigate a comprehensive set of physiological and psychosocial moderators in addition to time-related moderators. Conclusions: Although the measurement of participant engagement in MRTs of mHealth interventions is prevalent, there is a need for future trials to diversify the measurement of engagement. There is also a need for researchers to address the lack of attention to how engagement is determined and moderated. We hope that by mapping the state of engagement measurement in existing MRTs of mHealth interventions, this review will encourage researchers to pay more attention to these issues when planning for engagement measurement in future trials. ",
doi="10.2196/44685",
url="https://mhealth.jmir.org/2023/1/e44685",
url="http://www.ncbi.nlm.nih.gov/pubmed/37213178"
}


@Article{info:doi/10.2196/43033,
author="Agachi, Elena
and Bijmolt, A. Tammo H.
and van Ittersum, Koert
and Mierau, O. Jochen",
title="The Effect of Periodic Email Prompts on Participant Engagement With a Behavior Change mHealth App: Longitudinal Study",
journal="JMIR Mhealth Uhealth",
year="2023",
month="May",
day="11",
volume="11",
pages="e43033",
keywords="mobile health",
keywords="behavior change",
keywords="mobile app",
keywords="digital health",
keywords="engagement",
keywords="retention",
keywords="email",
keywords="hidden Markov model",
abstract="Background: Following the need for the prevention of noncommunicable diseases, mobile health (mHealth) apps are increasingly used for promoting lifestyle behavior changes. Although mHealth apps have the potential to reach all population segments, providing accessible and personalized services, their effectiveness is often limited by low participant engagement and high attrition rates. Objective: This study concerns a large-scale, open-access mHealth app, based in the Netherlands, focused on improving the lifestyle behaviors of its participants. The study examines whether periodic email prompts increased participant engagement with the mHealth app and how this effect evolved over time. Points gained from the activities in the app were used as an objective measure of participant engagement with the program. The activities considered were physical workouts tracked through the mHealth app and interactions with the web-based coach. Methods: The data analyzed covered 22,797 unique participants over a period of 78 weeks. A hidden Markov model (HMM) was used for disentangling the overtime effects of periodic email prompts on participant engagement with the mHealth app. The HMM accounted for transitions between latent activity states, which generated the observed measure of points received in a week. Results: The HMM indicated that, on average, 70\% (15,958/22,797) of the participants were in the inactivity state, gaining 0 points in total per week; 18\% (4103/22,797) of the participants were in the average activity state, gaining 27 points per week; and 12\% (2736/22,797) of the participants were in the high activity state, gaining 182 points per week. Receiving and opening a generic email was associated with a 3 percentage point increase in the likelihood of becoming active in that week, compared with the weeks when no email was received. Examining detailed email categories revealed that the participants were more likely to increase their activity level following emails that were in line with the program's goal, such as emails regarding health campaigns, while being resistant to emails that deviated from the program's goal, such as emails regarding special deals. Conclusions: Participant engagement with a behavior change mHealth app can be positively influenced by email prompts, albeit to a limited extent. Given the relatively low costs associated with emails and the high population reach that mHealth apps can achieve, such instruments can be a cost-effective means of increasing participant engagement in the stride toward improving program effectiveness. ",
doi="10.2196/43033",
url="https://mhealth.jmir.org/2023/1/e43033",
url="http://www.ncbi.nlm.nih.gov/pubmed/37166974"
}


@Article{info:doi/10.2196/36815,
author="Weil, Marie-Theres
and Spinler, Kristin
and Lieske, Berit
and Dingoyan, Demet
and Walther, Carolin
and Heydecke, Guido
and Kofahl, Christopher
and Aarabi, Ghazal",
title="An Evidence-Based Digital Prevention Program to Improve Oral Health Literacy of People With a Migration Background: Intervention Mapping Approach",
journal="JMIR Form Res",
year="2023",
month="May",
day="11",
volume="7",
pages="e36815",
keywords="oral health",
keywords="health behavior",
keywords="oral health knowledge",
keywords="migration",
keywords="mobile health",
keywords="mHealth",
keywords="preventive dentistry",
keywords="intervention mapping",
keywords="mobile phone",
abstract="Background: Studies in Germany have shown that susceptible groups, such as people with a migration background, have poorer oral health than the majority of the population. Limited oral health literacy (OHL) appears to be an important factor that affects the oral health of these groups. To increase OHL and to promote prevention-oriented oral health behavior, we developed an evidence-based prevention program in the form of an app for smartphones or tablets, the F{\"o}rderung der Mundgesundheitskompetenz und Mundgesundheit von Menschen mit Migrationshintergrund (MuMi) app. Objective: This study aims to describe the development process of the MuMi app. Methods: For the description and analysis of the systematic development process of the MuMi app, we used the intervention mapping approach. The approach was implemented in 6 steps: needs assessment, formulation of intervention goals, selection of evidence-based methods and practical strategies for behavior change, planning and designing the intervention, planning the implementation and delivery of the intervention, and planning the evaluation. Results: On the basis of our literature search, expert interviews, and a focus group with the target population, we identified limited knowledge of behavioral risk factors or proper oral hygiene procedures, limited proficiency of the German language, and differing health care socialization as the main barriers to good oral health. Afterward, we selected modifiable determinants of oral health behavior that were in line with behavior change theories. On this basis, performance objectives and change objectives for the relevant population at risk were formalized. Appropriate behavior change techniques to achieve the program objectives, such as the provision of health information, encouragement of self-control and self-monitoring, and sending reminders, were identified. Subsequently, these were translated into practical strategies, such as multiple-choice quizzes or videos. The resulting program, the MuMi app, is available in the Apple app store and Android app store. The effectiveness of the app was evaluated in the MuMi intervention study. The analyses showed that users of the MuMi app had a substantial increase in their OHL and improved oral hygiene (as measured by clinical parameters) after 6 months compared with the control group. Conclusions: The intervention mapping approach provided a transparent, structured, and evidence-based process for the development of our prevention program. It allowed us to identify the most appropriate and effective techniques to initiate behavior change in the target population. The MuMi app takes into account the cultural and specific determinants of people with a migration background in Germany. To our knowledge, it is the first evidence-based app that addresses OHL among people with a migration background. ",
doi="10.2196/36815",
url="https://formative.jmir.org/2023/1/e36815",
url="http://www.ncbi.nlm.nih.gov/pubmed/37166956"
}


@Article{info:doi/10.2196/40736,
author="Nguyen, Nhung
and Thrul, Johannes
and Neilands, B. Torsten
and Ling, M. Pamela",
title="Associations Between Product Type and Intensity of Tobacco and Cannabis Co-use on the Same Day Among Young Adult Smokers: Smartphone-Based Daily-Diary Study",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Feb",
day="20",
volume="11",
pages="e40736",
keywords="tobacco",
keywords="cannabis",
keywords="substance co-use",
keywords="young adults",
keywords="intensive longitudinal data",
keywords="EMA",
keywords="mHealth",
keywords="smartphone-based data collection",
keywords="data collection",
keywords="smartphone data",
keywords="substance use",
abstract="Background: Co-use of tobacco and cannabis is highly prevalent among young US adults. Same-day co-use of tobacco and cannabis (ie, use of both substances on the same day) may increase the extent of use and negative health consequences among young adults. However, much remains unknown about same-day co-use of tobacco and cannabis, in part due to challenges in measuring this complex behavior. Nuanced understanding of tobacco and cannabis co-use in terms of specific products and intensity (ie, quantity of tobacco and cannabis use within a day) is critical to inform prevention and intervention efforts. Objective: We used a daily-diary data collection method via smartphone to capture occurrence of tobacco and cannabis co-use within a day. We examined (1) whether the same route of administration would facilitate co-use of 2 substances on the same day and (2) whether participants would use more tobacco on a day when they use more cannabis. Methods: This smartphone-based study collected 2891 daily assessments from 147 cigarette smokers (aged 18-26 years, n=76, 51.7\% female) during 30 consecutive days. Daily assessments measured type (ie, cigarette, cigarillo, or e-cigarette) and intensity (ie, number of cigarettes or cigarillos smoked or number of times vaping e-cigarettes per day) of tobacco use and type (ie, combustible, vaporized, or edible) and intensity (ie, number of times used per day) of cannabis use. We estimated multilevel models to examine day-level associations between types of cannabis use and each type of tobacco use, as well as day-level associations between intensities of using cannabis and tobacco. All models controlled for demographic covariates, day-level alcohol use, and time effects (ie, study day and weekend vs weekday). Results: Same-day co-use was reported in 989 of the total 2891 daily assessments (34.2\%). Co-use of cigarettes and combustible cannabis (885 of the 2891 daily assessments; 30.6\%) was most commonly reported. Participants had higher odds of using cigarettes (adjusted odds ratio [AOR] 1.92, 95\% CI 1.31-2.81) and cigarillos (AOR 244.29, 95\% CI 35.51-1680.62) on days when they used combustible cannabis. Notably, participants had higher odds of using e-cigarettes on days when they used vaporized cannabis (AOR 23.21, 95\% CI 8.66-62.24). Participants reported a greater intensity of using cigarettes (AOR 1.35, 95\% CI 1.23-1.48), cigarillos (AOR 2.04, 95\% CI 1.70-2.46), and e-cigarettes (AOR 1.48, 95\% CI 1.16-1.88) on days when they used more cannabis. Conclusions: Types and intensities of tobacco and cannabis use within a day among young adult smokers were positively correlated, including co-use of vaporized products. Prevention and intervention efforts should address co-use and pay attention to all forms of use and timeframes of co-use (eg, within a day or at the same time), including co-use of e-cigarettes and vaporized cannabis, to reduce negative health outcomes. ",
doi="10.2196/40736",
url="https://mhealth.jmir.org/2023/1/e40736",
url="http://www.ncbi.nlm.nih.gov/pubmed/36806440"
}


@Article{info:doi/10.2196/42219,
author="Inamoto, Yoko
and Mukaino, Masahiko
and Imaeda, Sayuri
and Sawada, Manami
and Satoji, Kumi
and Nagai, Ayako
and Hirano, Satoshi
and Okazaki, Hideto
and Saitoh, Eiichi
and Sonoda, Shigeru
and Otaka, Yohei",
title="A Tablet-Based Aphasia Assessment System ``STELA'': Feasibility and Validation Study",
journal="JMIR Form Res",
year="2023",
month="Feb",
day="8",
volume="7",
pages="e42219",
keywords="aphasia",
keywords="tablet",
keywords="assessment",
keywords="validity",
keywords="internal consistency",
keywords="psychometric",
keywords="psychological health",
keywords="stress",
keywords="digital mental health intervention",
keywords="digital health intervention",
keywords="heuristic evaluation",
keywords="system usability",
keywords="auditory comprehension",
keywords="reading comprehension",
keywords="naming and sentence formation",
keywords="repetition",
keywords="reading aloud",
keywords="Cronbach $\alpha$",
keywords="speech",
abstract="Background: There is an extensive library of language tests, each with excellent psychometric properties; however, many of the tests available take considerable administration time, possibly bearing psychological strain on patients. The Short and Tailored Evaluation of Language Ability (STELA) is a simplified, tablet-based language ability assessment system developed to address this issue, with a reduced number of items and automated testing process. Objective: The aim of this paper is to assess the administration time, internal consistency, and validity of the STELA. Methods: The STELA consists of a tablet app, a microphone, and an input keypad for clinician's use. The system is designed to assess language ability with 52 questions grouped into 2 comprehension modalities (auditory comprehension and reading comprehension) and 3 expression modalities (naming and sentence formation, repetition, and reading aloud). Performance in each modality was scored as the correct answer rate (0-100), and overall performance expressed as the sum of modality scores (out of 500 points). Results: The time taken to complete the STELA was significantly less than the time for the WAB (mean 16.2, SD 9.4 vs mean 149.3, SD 64.1 minutes; P<.001). The STELA's total score was strongly correlated with the WAB Aphasia Quotient (r=0.93, P<.001), supporting the former's concurrent validity concerning the WAB, which is a gold-standard aphasia assessment. Strong correlations were also observed at the subscale level; STELA auditory comprehension versus WAB auditory comprehension (r=0.75, P<.001), STELA repetition versus WAB repetition (r=0.96, P<.001), STELA naming and sentence formation versus WAB naming and word finding (r=0.81, P<.001), and the sum of STELA reading comprehension or reading aloud versus WAB reading (r=0.82, P<.001). Cronbach $\alpha$ obtained for each modality was .862 for auditory comprehension, .872 for reading comprehension, .902 for naming and sentence formation, .787 for repetition, and .892 for reading aloud. Global Cronbach $\alpha$ was .961. The average of the values of item-total correlation to each subscale was 0.61 (SD 0.17). Conclusions: Our study confirmed significant time reduction in the assessment of language ability and provided evidence for good internal consistency and validity of the STELA tablet-based aphasia assessment system. ",
doi="10.2196/42219",
url="https://formative.jmir.org/2023/1/e42219",
url="http://www.ncbi.nlm.nih.gov/pubmed/36753308"
}


@Article{info:doi/10.2196/41873,
author="Quialheiro, Anna
and Miranda, Andr{\'e}
and Garcia Jr, Miguel
and Carvalho, de Adriana Camargo
and Costa, Patr{\'i}cio
and Correia-Neves, Margarida
and Santos, Correia Nadine",
title="Promoting Digital Proficiency and Health Literacy in Middle-aged and Older Adults Through Mobile Devices With the Workshops for Online Technological Inclusion (OITO) Project: Experimental Study",
journal="JMIR Form Res",
year="2023",
month="Feb",
day="8",
volume="7",
pages="e41873",
keywords="digital proficiency",
keywords="health literacy",
keywords="older adults",
keywords="mobile devices",
abstract="Background: Digital inclusion and literacy facilitate access to health information and can contribute to self-care behaviors and informed decision-making. However, digital literacy is not an innate skill, but rather requires knowledge acquisition. Objective: The present study aimed to develop, conduct, and measure the impact, on digital and health literacy, of a digital inclusion program aimed at community dwellers. Methods: The program targeted the recruitment of people aged 55 and older that owned mobile devices with an internet connection in 3 cities in northern Portugal (Paredes de Coura, Guimar{\~a}es, and Barcelos). The program was titled the Workshops for Online Technological Inclusion (OITO) project and, in each city, was promoted by the coordinator of municipal projects and organized as an in-person 8-workshop program, using mobile devices, smartphones, or tablets. A quasi-experimental design was used with a nonrandomized allocation of participants in each set of 8 workshops. Sociodemographic, health status, and mobile use information were collected at baseline. Digital and health literacy were measured via the Mobile Device Proficiency Questionnaire and the Health Literacy Scale questionnaires, respectively, at baseline (T1), program completion (T2), and a 1-month follow-up (T3). A self-reported measure of autonomy was evaluated at T1 and T2 using a visual scale. Results: Most participants were women with primary schooling (up to 4 years) aged between 65 and 74 years and retired. The intervention had an 81\% (97/120) recruitment rate, 53\% (43/81) adherence, and 94\% (67/71) satisfaction rate, with 81 participants completing the entire 8-workshop program. Most participants had owned their mobile device for more than one year (64/81, 79\%), were frequent daily users (70/81, 86\%), and had received their mobile device from someone else (33/64, 52\%). Over 80\% (71/81) of the participants who completed the intervention used Android smartphones. At baseline, participants had low baseline scores in digital literacy, but medium-high baseline scores in health literacy. They showed significant improvement in digital literacy at T2 and T3 compared to T1, but without a significant difference between T2 and T3, regardless of sex, age, or schooling. A significant improvement in self-reported autonomy was observed at T3 compared with baseline. Regarding health literacy, no significant differences were found at T2 or T3 compared to the baseline. Conclusions: The feasibility indicators showed that the OITO project methodology had a substantial rate of recruitment and satisfaction. Program participants had significant improvement in digital literacy after 8 workshops and maintained their score 1 month after completing the intervention. There was no significant change in health literacy during the project period. ",
doi="10.2196/41873",
url="https://formative.jmir.org/2023/1/e41873",
url="http://www.ncbi.nlm.nih.gov/pubmed/36753331"
}


@Article{info:doi/10.2196/41660,
author="Choi, Woohyeok
and Lee, Uichin",
title="Loss-Framed Adaptive Microcontingency Management for Preventing Prolonged Sedentariness: Development and Feasibility Study",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Jan",
day="27",
volume="11",
pages="e41660",
keywords="contingency management",
keywords="incentive",
keywords="sedentary behavior",
keywords="sedentariness",
keywords="behavior change",
keywords="health promotion",
keywords="financial incentives",
keywords="health intervention",
keywords="user compliance",
keywords="incentive-based intervention",
keywords="mobile phone",
abstract="Background: A growing body of evidence shows that financial incentives can effectively reinforce individuals' positive behavior change and improve compliance with health intervention programs. A critical factor in the design of incentive-based interventions is to set a proper incentive magnitude. However, it is highly challenging to determine such magnitudes as the effects of incentive magnitude depend on personal attitudes and contexts. Objective: This study aimed to illustrate loss-framed adaptive microcontingency management (L-AMCM) and the lessons learned from a feasibility study. L-AMCM discourages an individual's adverse health behaviors by deducting particular expenses from a regularly assigned budget, where expenses are adaptively estimated based on the individual's previous responses to varying expenses and contexts. Methods: We developed a mobile health intervention app for preventing prolonged sedentary lifestyles. This app delivered a behavioral mission (ie, suggesting taking an active break for a while) with an incentive bid when 50 minutes of uninterrupted sedentary behavior happened. Participants were assigned to either the fixed (ie, deducting the monotonous expense for each mission failure) or adaptive (ie, deducting varying expenses estimated by the L-AMCM for each mission failure) incentive group. The intervention lasted 3 weeks. Results: We recruited 41 participants (n=15, 37\% women; fixed incentive group: n=20, 49\% of participants; adaptive incentive group: n=21, 51\% of participants) whose mean age was 24.0 (SD 3.8; range 19-34) years. Mission success rates did not show statistically significant differences by group (P=.54; fixed incentive group mean 0.66, SD 0.24; adaptive incentive group mean 0.61, SD 0.22). The follow-up analysis of the adaptive incentive group revealed that the influence of incentive magnitudes on mission success was not statistically significant (P=.18; odds ratio 0.98, 95\% CI 0.95-1.01). On the basis of the qualitative interviews, such results were possibly because the participants had sufficient intrinsic motivation and less sensitivity to incentive magnitudes. Conclusions: Although our L-AMCM did not significantly affect users' mission success rate, this study configures a pioneering work toward adaptively estimating incentives by considering user behaviors and contexts through leveraging mobile sensing and machine learning. We hope that this study inspires researchers to develop incentive-based interventions. ",
doi="10.2196/41660",
url="https://mhealth.jmir.org/2023/1/e41660",
url="http://www.ncbi.nlm.nih.gov/pubmed/36705949"
}


@Article{info:doi/10.2196/37716,
author="Vlahu-Gjorgievska, Elena
and Burazor, Andrea
and Win, Than Khin
and Trajkovik, Vladimir",
title="mHealth Apps Targeting Obesity and Overweight in Young People: App Review and Analysis",
journal="JMIR Mhealth Uhealth",
year="2023",
month="Jan",
day="19",
volume="11",
pages="e37716",
keywords="behavior change techniques",
keywords="user interface design patterns",
keywords="mHealth apps",
keywords="obesity",
keywords="lifestyle",
keywords="mobile app",
keywords="mobile health",
keywords="mobile phone",
abstract="Background: Overweight and obesity have been linked to several serious health problems and medical conditions. With more than a quarter of the young population having weight problems, the impacts of overweight and obesity on this age group are particularly critical. Mobile health (mHealth) apps that support and encourage positive health behaviors have the potential to achieve better health outcomes. These apps represent a unique opportunity for young people (age range 10-24 years), for whom mobile phones are an indispensable part of their everyday living. However, despite the potential of mHealth apps for improved engagement in health interventions, user adherence to these health interventions in the long term is low. Objective: The aims of this research were to (1) review and analyze mHealth apps targeting obesity and overweight and (2) propose guidelines for the inclusion of user interface design patterns (UIDPs) in the development of mHealth apps for obese young people that maximizes the impact and retention of behavior change techniques (BCTs). Methods: A search for apps was conducted in Google Play Store using the following search string: [``best weight loss app for obese teens 2020''] OR [``obesity applications for teens''] OR [``popular weight loss applications'']. The most popular apps available in both Google Play and Apple App Store that fulfilled the requirements within the inclusion criteria were selected for further analysis. The designs of 17 mHealth apps were analyzed for the inclusion of BCTs supported by various UIDPs. Based on the results of the analysis, BCT-UI design guidelines were developed. The usability of the guidelines was presented using a prototype app. Results: The results of our analysis showed that only half of the BCTs are implemented in the reviewed apps, with a subset of those BCTs being supported by UIDPs. Based on these findings, we propose design guidelines that associate the BCTs with UIDPs. The focus of our guidelines is the implementation of BCTs using design patterns that are impactful for the young people demographics. The UIDPs are classified into 6 categories, with each BCT having one or more design patterns appropriate for its implementation. The applicability of the proposed guidelines is presented by mock-ups of the mHealth app ``Morphe,'' intended for young people (age range 10-24 years). The presented use cases showcase the 5 main functionalities of Morphe: learn, challenge, statistics, social interaction, and settings. Conclusions: The app analysis results showed that the implementation of BCTs using UIDPs is underutilized. The purposed guidelines will help developers in designing mHealth apps for young people that are easy to use and support behavior change. Future steps involve the development and deployment of the Morphe app and the validation of its usability and effectiveness. ",
doi="10.2196/37716",
url="https://mhealth.jmir.org/2023/1/e37716",
url="http://www.ncbi.nlm.nih.gov/pubmed/36656624"
}


@Article{info:doi/10.2196/39322,
author="Kanning, Martina
and Bollenbach, Lukas
and Schmitz, Julian
and Niermann, Christina
and Fina, Stefan",
title="Analyzing Person-Place Interactions During Walking Episodes: Innovative Ambulatory Assessment Approach of Walking-Triggered e-Diaries",
journal="JMIR Form Res",
year="2022",
month="Nov",
day="25",
volume="6",
number="11",
pages="e39322",
keywords="ecological momentary assessment",
keywords="active transport",
keywords="socio-ecological model",
keywords="subjective well-being",
keywords="mental health",
keywords="urban health",
keywords="GEMA",
keywords="geographically explicit ecological momentary assessment",
keywords="behaviour change",
keywords="walking",
keywords="experience",
keywords="environment",
keywords="monitoring",
keywords="activity",
keywords="tracking",
keywords="e-diary",
keywords="assessment",
abstract="Background: Walking behavior is positively associated with physiological and mental health as much evidence has already shown. Walking is also becoming a critical issue for health promotion in urban environments as it is the most often used form of active mobility and helps to replace carbon dioxide emissions from motorized forms of transport. It therefore contributes to mitigate the negative effects of climate change and heat islands within cities. However, to promote walking among urban dwellers and to utilize its health-enhancing potential, we need to know more about the way in which physical and social environments shape individual experiences during walking episodes. Such person-place interactions could not adequately be analyzed in former studies owing to methodological constraints. Objective: This study introduces walking-triggered e-diaries as an innovative ambulatory assessment approach for time-varying associations, and investigates its accuracy with 2 different validation strategies. Methods: The walking trigger consists of a combination of movement acceleration via an accelerometer and mobile positioning of the cellphone via GPS and transmission towers to track walking activities. The trigger starts an e-diary whenever a movement acceleration exceeds a predetermined threshold and participants' locations are identified as nonstationary outside a predefined place of residence. Every 420 ({\textpm}300) seconds, repeated e-diaries were prompted as long as the trigger conditions were met. Data were assessed on 10 consecutive days. First, to investigate accuracy, we reconstructed walking routes and calculated a percentage score for all triggered prompts in relation to all walking routes where a prompt could have been triggered. Then, to provide data about its specificity, we used momentary self-reports and objectively assessed movement behavior to describe activity levels before the trigger prompted an e-diary. Results: Data of 67 participants could be analyzed and the walking trigger led to 3283 e-diary prompts, from which 2258 (68.8\%) were answered. Regarding accuracy, the walking trigger prompted an e-diary on 732 of 842 (86.9\%) reconstructed walking routes. Further, in 838 of 1206 (69.5\%) triggered e-diaries, participants self-reported that they were currently walking outdoors. Steps and acceleration movement was higher during these self-reported walking episodes than when participants denied walking outdoors (steps: 106 vs 32; acceleration>0.2 g in 58.4\% vs 19\% of these situations). Conclusions: Accuracy analysis revealed that walking-triggered e-diaries are suitable to collect different data of individuals' current experiences in situations in which a person walks outdoors. Combined with environmental data, such an approach increases knowledge about person-place interactions and provides the possibility to gain knowledge about user preferences for health-enhancing urban environments. From a methodological viewpoint, however, specificity analysis showed how changes in trigger conditions (eg, increasing the threshold for movement acceleration) lead to changes in accuracy. ",
doi="10.2196/39322",
url="https://formative.jmir.org/2022/11/e39322",
url="http://www.ncbi.nlm.nih.gov/pubmed/36427231"
}


@Article{info:doi/10.2196/38740,
author="Dhinagaran, Ardhithy Dhakshenya
and Martinengo, Laura
and Ho, Ringo Moon-Ho
and Joty, Shafiq
and Kowatsch, Tobias
and Atun, Rifat
and Tudor Car, Lorainne",
title="Designing, Developing, Evaluating, and Implementing a Smartphone-Delivered, Rule-Based Conversational Agent (DISCOVER): Development of a Conceptual Framework",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Oct",
day="4",
volume="10",
number="10",
pages="e38740",
keywords="conceptual framework",
keywords="conversational agent",
keywords="chatbot",
keywords="mobile health",
keywords="mHealth",
keywords="digital health",
keywords="mobile phone",
abstract="Background: Conversational agents (CAs), also known as chatbots, are computer programs that simulate human conversations by using predetermined rule-based responses or artificial intelligence algorithms. They are increasingly used in health care, particularly via smartphones. There is, at present, no conceptual framework guiding the development of smartphone-based, rule-based CAs in health care. To fill this gap, we propose structured and tailored guidance for their design, development, evaluation, and implementation. Objective: The aim of this study was to develop a conceptual framework for the design, evaluation, and implementation of smartphone-delivered, rule-based, goal-oriented, and text-based CAs for health care. Methods: We followed the approach by Jabareen, which was based on the grounded theory method, to develop this conceptual framework. We performed 2 literature reviews focusing on health care CAs and conceptual frameworks for the development of mobile health interventions. We identified, named, categorized, integrated, and synthesized the information retrieved from the literature reviews to develop the conceptual framework. We then applied this framework by developing a CA and testing it in a feasibility study. Results: The Designing, Developing, Evaluating, and Implementing a Smartphone-Delivered, Rule-Based Conversational Agent (DISCOVER) conceptual framework includes 8 iterative steps grouped into 3 stages, as follows: design, comprising defining the goal, creating an identity, assembling the team, and selecting the delivery interface; development, including developing the content and building the conversation flow; and the evaluation and implementation of the CA. They were complemented by 2 cross-cutting considerations---user-centered design and privacy and security---that were relevant at all stages. This conceptual framework was successfully applied in the development of a CA to support lifestyle changes and prevent type 2 diabetes. Conclusions: Drawing on published evidence, the DISCOVER conceptual framework provides a step-by-step guide for developing rule-based, smartphone-delivered CAs. Further evaluation of this framework in diverse health care areas and settings and for a variety of users is needed to demonstrate its validity. Future research should aim to explore the use of CAs to deliver health care interventions, including behavior change and potential privacy and safety concerns. ",
doi="10.2196/38740",
url="https://mhealth.jmir.org/2022/10/e38740",
url="http://www.ncbi.nlm.nih.gov/pubmed/36194462"
}


@Article{info:doi/10.2196/40576,
author="McGowan, Aleise
and Sittig, Scott
and Bourrie, David
and Benton, Ryan
and Iyengar, Sriram",
title="The Intersection of Persuasive System Design and Personalization in Mobile Health: Statistical Evaluation",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Sep",
day="14",
volume="10",
number="9",
pages="e40576",
keywords="persuasive technology",
keywords="personalization",
keywords="psychological characteristics",
keywords="self-efficacy",
keywords="health consciousness",
keywords="health motivation",
keywords="personality traits",
keywords="mobile health",
keywords="mHealth",
keywords="mobile phone",
abstract="Background: Persuasive technology is an umbrella term that encompasses software (eg, mobile apps) or hardware (eg, smartwatches) designed to influence users to perform preferable behavior once or on a long-term basis. Considering the ubiquitous nature of mobile devices across all socioeconomic groups, user behavior modification thrives under the personalized care that persuasive technology can offer. However, there is no guidance for developing personalized persuasive technologies based on the psychological characteristics of users. Objective: This study examined the role that psychological characteristics play in interpreted mobile health (mHealth) screen perceived persuasiveness. In addition, this study aims to explore how users' psychological characteristics drive the perceived persuasiveness of digital health technologies in an effort to assist developers and researchers of digital health technologies by creating more engaging solutions. Methods: An experiment was designed to evaluate how psychological characteristics (self-efficacy, health consciousness, health motivation, and the Big Five personality traits) affect the perceived persuasiveness of digital health technologies, using the persuasive system design framework. Participants (n=262) were recruited by Qualtrics International, Inc, using the web-based survey system of the XM Research Service. This experiment involved a survey-based design with a series of 25 mHealth app screens that featured the use of persuasive principles, with a focus on physical activity. Exploratory factor analysis and linear regression were used to evaluate the multifaceted needs of digital health users based on their psychological characteristics. Results: The results imply that an individual user's psychological characteristics (self-efficacy, health consciousness, health motivation, and extraversion) affect interpreted mHealth screen perceived persuasiveness, and combinations of persuasive principles and psychological characteristics lead to greater perceived persuasiveness. The F test (ie, ANOVA) for model 1 was significant (F9,6540=191.806; P<.001), with an adjusted R2 of 0.208, indicating that the demographic variables explained 20.8\% of the variance in perceived persuasiveness. Gender was a significant predictor, with women having higher perceived persuasiveness (P=.008) relative to men. Age was a significant predictor of perceived persuasiveness with individuals aged 40 to 59 years (P<.001) and ?60 years (P<.001). Model 2 was significant (F13,6536=341.035; P<.001), with an adjusted R2 of 0.403, indicating that the demographic variables self-efficacy, health consciousness, health motivation, and extraversion together explained 40.3\% of the variance in perceived persuasiveness. Conclusions: This study evaluates the role that psychological characteristics play in interpreted mHealth screen perceived persuasiveness. Findings indicate that self-efficacy, health consciousness, health motivation, extraversion, gender, age, and education significantly influence the perceived persuasiveness of digital health technologies. Moreover, this study showed that varying combinations of psychological characteristics and demographic variables affected the perceived persuasiveness of the primary persuasive technology category. ",
doi="10.2196/40576",
url="https://mhealth.jmir.org/2022/9/e40576",
url="http://www.ncbi.nlm.nih.gov/pubmed/36103226"
}


@Article{info:doi/10.2196/36912,
author="Woulfe, Fionn
and Fadahunsi, Philip Kayode
and O'Grady, Michael
and Chirambo, Baxter Griphin
and Mawkin, Mala
and Majeed, Azeem
and Smith, Simon
and Henn, Patrick
and O'Donoghue, John",
title="Modification and Validation of an mHealth App Quality Assessment Methodology for International Use: Cross-sectional and eDelphi Studies",
journal="JMIR Form Res",
year="2022",
month="Aug",
day="19",
volume="6",
number="8",
pages="e36912",
keywords="evaluation tool",
keywords="mobile health",
keywords="mHealth",
keywords="smartphone app",
keywords="app",
keywords="international mHealth",
abstract="Background: Over 325,000 mobile health (mHealth) apps are available to download across various app stores. However, quality assurance in this field of medicine remains relatively undefined. Globally, around 84\% of the population have access to mobile broadband networks. Given the potential for mHealth app use in health promotion and disease prevention, their role in patient care worldwide is ever apparent. Quality assurance regulations both nationally and internationally will take time to develop. Frameworks such as the Mobile App Rating Scale and Enlight Suite have demonstrated potential for use in the interim. However, these frameworks require adaptation to be suitable for international use. Objective: This study aims to modify the Enlight Suite, a comprehensive app quality assessment methodology, to improve its applicability internationally and to assess the preliminary validity and reliability of this modified tool in practice. Methods: A two-round Delphi study involving 7 international mHealth experts with varied backgrounds in health, technology, and clinical psychology was conducted to modify the Enlight Suite for international use and to improve its content validity. The Modified Enlight Suite (MES) was then used by 800 health care professionals and health care students in Ireland to assess a COVID-19 tracker app in an online survey. The reliability of the MES was assessed using Cronbach alpha, while the construct validity was evaluated using confirmatory factor analysis. Results: The final version of the MES has 7 sections with 32 evaluating items. Of these items, 5 were novel and based on consensus for inclusion by Delphi panel members. The MES has satisfactory reliability with a Cronbach alpha score of .925. The subscales also demonstrated acceptable internal consistency. Similarly, the confirmatory factor analysis demonstrated a positive and significant factor loading for all 32 items in the MES with a modestly acceptable model fit, thus indicating the construct validity of the MES. Conclusions: The Enlight Suite was modified to improve its international relevance to app quality assessment by introducing new items relating to cultural appropriateness, accessibility, and readability of mHealth app content.  This study indicates both the reliability and validity of the MES for assessing the quality of mHealth apps in a high-income country, with further studies being planned to extrapolate these findings to low- and middle-income countries. ",
doi="10.2196/36912",
url="https://formative.jmir.org/2022/8/e36912",
url="http://www.ncbi.nlm.nih.gov/pubmed/35984688"
}


@Article{info:doi/10.2196/37290,
author="Hyzy, Maciej
and Bond, Raymond
and Mulvenna, Maurice
and Bai, Lu
and Dix, Alan
and Leigh, Simon
and Hunt, Sophie",
title="System Usability Scale Benchmarking for Digital Health Apps: Meta-analysis",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Aug",
day="18",
volume="10",
number="8",
pages="e37290",
keywords="mHealth SUS scores meta-analysis",
keywords="SUS for digital health",
keywords="digital health apps usability",
keywords="mHealth usability",
keywords="SUS meta-analysis",
keywords="mHealth",
keywords="mobile app",
keywords="mobile health",
keywords="digital health",
keywords="System Usability Scale",
abstract="Background: The System Usability Scale (SUS) is a widely used scale that has been used to quantify the usability of many software and hardware products. However, the SUS was not specifically designed to evaluate mobile apps, or in particular digital health apps (DHAs). Objective: The aim of this study was to examine whether the widely used SUS distribution for benchmarking (mean 68, SD 12.5) can be used to reliably assess the usability of DHAs. Methods: A search of the literature was performed using the ACM Digital Library, IEEE Xplore, CORE, PubMed, and Google Scholar databases to identify SUS scores related to the usability of DHAs for meta-analysis. This study included papers that published the SUS scores of the evaluated DHAs from 2011 to 2021 to get a 10-year representation. In total, 117 SUS scores for 114 DHAs were identified. R Studio and the R programming language were used to model the DHA SUS distribution, with a 1-sample, 2-tailed t test used to compare this distribution with the standard SUS distribution. Results: The mean SUS score when all the collected apps were included was 76.64 (SD 15.12); however, this distribution exhibited asymmetrical skewness (--0.52) and was not normally distributed according to Shapiro-Wilk test (P=.002). The mean SUS score for ``physical activity'' apps was 83.28 (SD 12.39) and drove the skewness. Hence, the mean SUS score for all collected apps excluding ``physical activity'' apps was 68.05 (SD 14.05). A 1-sample, 2-tailed t test indicated that this health app SUS distribution was not statistically significantly different from the standard SUS distribution (P=.98). Conclusions: This study concludes that the SUS and the widely accepted benchmark of a mean SUS score of 68 (SD 12.5) are suitable for evaluating the usability of DHAs. We speculate as to why physical activity apps received higher SUS scores than expected. A template for reporting mean SUS scores to facilitate meta-analysis is proposed, together with future work that could be done to further examine the SUS benchmark scores for DHAs. ",
doi="10.2196/37290",
url="https://mhealth.jmir.org/2022/8/e37290",
url="http://www.ncbi.nlm.nih.gov/pubmed/35980732"
}


@Article{info:doi/10.2196/37303,
author="Kamstra, M. Regina J.
and Boorsma, Andr{\'e}
and Krone, Tanja
and van Stokkum, M. Robin
and Eggink, M. Hannah
and Peters, Ton
and Pasman, J. Wilrike",
title="Validation of the Mobile App Version of the EQ-5D-5L Quality of Life Questionnaire Against the Gold Standard Paper-Based Version: Randomized Crossover Study",
journal="JMIR Form Res",
year="2022",
month="Aug",
day="11",
volume="6",
number="8",
pages="e37303",
keywords="quality of life assessment",
keywords="EQ-5D-5L questionnaire",
keywords="mobile app",
keywords="test-retest reliability",
keywords="mobile phone",
abstract="Background: Study participants and patients often perceive (long) questionnaires as burdensome. In addition, paper-based questionnaires are prone to errors such as (unintentionally) skipping questions or filling in a wrong type of answer. Such errors can be prevented with the emergence of mobile questionnaire apps. Objective: This study aimed to validate an innovative way to measure the quality of life using a mobile app based on the EQ-5D-5L questionnaire. This validation study compared the EQ-5D-5L questionnaire requested by a mobile app with the gold standard paper-based version of the EQ-5D-5L. Methods: This was a randomized, crossover, and open study. The main criteria for participation were participants should be aged ?18 years, healthy at their own discretion, in possession of a smartphone with at least Android version 4.1 or higher or iOS version 9 or higher, digitally skilled in downloading the mobile app, and able to read and answer questionnaires in Dutch. Participants were recruited by a market research company that divided them into 2 groups balanced for age, gender, and education. Each participant received a digital version of the EQ-5D-5L questionnaire via a mobile app and the EQ-5D-5L paper-based questionnaire by postal mail. In the mobile app, participants received, for 5 consecutive days, 1 question in the morning and 1 question in the afternoon; as such, all questions were asked twice (at time point 1 [App T1] and time point 2 [App T2]). The primary outcomes were the correlations between the answers (scores) of each EQ-5D-5L question answered via the mobile app compared with the paper-based questionnaire to assess convergent validity. Results: A total of 255 participants (healthy at their own discretion), 117 (45.9\%) men and 138 (54.1\%) women in the age range of 18 to 64 years, completed the study. To ensure randomization, the measured demographics were checked and compared between groups. To compare the results of the electronic and paper-based questionnaires, polychoric correlation analysis was performed. All questions showed a high correlation (0.64-0.92; P<.001) between the paper-based and the mobile app--based questions at App T1 and App T2. The scores and their variance remained similar over the questionnaires, indicating no clear difference in the answer tendency. In addition, the correlation between the 2 app-based questionnaires was high (>0.73; P<.001), illustrating a high test-retest reliability, indicating it to be a reliable replacement for the paper-based questionnaire. Conclusions: This study indicates that the mobile app is a valid tool for measuring the quality of life and is as reliable as the paper-based version of the EQ-5D-5L, while reducing the response burden. ",
doi="10.2196/37303",
url="https://formative.jmir.org/2022/8/e37303",
url="http://www.ncbi.nlm.nih.gov/pubmed/35969437"
}


@Article{info:doi/10.2196/33850,
author="Ng, Ada
and Wei, Boyang
and Jain, Jayalakshmi
and Ward, A. Erin
and Tandon, Darius S.
and Moskowitz, T. Judith
and Krogh-Jespersen, Sheila
and Wakschlag, S. Lauren
and Alshurafa, Nabil",
title="Predicting the Next-Day Perceived and Physiological Stress of Pregnant Women by Using Machine Learning and Explainability: Algorithm Development and Validation",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Aug",
day="2",
volume="10",
number="8",
pages="e33850",
keywords="explainability",
keywords="just-in-time interventions",
keywords="machine learning",
keywords="prenatal stress",
keywords="stress prediction",
keywords="wearable",
keywords="mobile phone",
abstract="Background: Cognitive behavioral therapy--based interventions are effective in reducing prenatal stress, which can have severe adverse health effects on mothers and newborns if unaddressed. Predicting next-day physiological or perceived stress can help to inform and enable pre-emptive interventions for a likely physiologically and perceptibly stressful day. Machine learning models are useful tools that can be developed to predict next-day physiological and perceived stress by using data collected from the previous day. Such models can improve our understanding of the specific factors that predict physiological and perceived stress and allow researchers to develop systems that collect selected features for assessment in clinical trials to minimize the burden of data collection. Objective: The aim of this study was to build and evaluate a machine-learned model that predicts next-day physiological and perceived stress by using sensor-based, ecological momentary assessment (EMA)--based, and intervention-based features and to explain the prediction results. Methods: We enrolled pregnant women into a prospective proof-of-concept study and collected electrocardiography, EMA, and cognitive behavioral therapy intervention data over 12 weeks. We used the data to train and evaluate 6 machine learning models to predict next-day physiological and perceived stress. After selecting the best performing model, Shapley Additive Explanations were used to identify the feature importance and explainability of each feature. Results: A total of 16 pregnant women enrolled in the study. Overall, 4157.18 hours of data were collected, and participants answered 2838 EMAs. After applying feature selection, 8 and 10 features were found to positively predict next-day physiological and perceived stress, respectively. A random forest classifier performed the best in predicting next-day physiological stress (F1 score of 0.84) and next-day perceived stress (F1 score of 0.74) by using all features. Although any subset of sensor-based, EMA-based, or intervention-based features could reliably predict next-day physiological stress, EMA-based features were necessary to predict next-day perceived stress. The analysis of explainability metrics showed that the prolonged duration of physiological stress was highly predictive of next-day physiological stress and that physiological stress and perceived stress were temporally divergent. Conclusions: In this study, we were able to build interpretable machine learning models to predict next-day physiological and perceived stress, and we identified unique features that were highly predictive of next-day stress that can help to reduce the burden of data collection. ",
doi="10.2196/33850",
url="https://mhealth.jmir.org/2022/8/e33850",
url="http://www.ncbi.nlm.nih.gov/pubmed/35917157"
}


@Article{info:doi/10.2196/38077,
author="Karas, Marta
and Muschelli, John
and Leroux, Andrew
and Urbanek, K. Jacek
and Wanigatunga, A. Amal
and Bai, Jiawei
and Crainiceanu, M. Ciprian
and Schrack, A. Jennifer",
title="Comparison of Accelerometry-Based Measures of Physical Activity: Retrospective Observational Data Analysis Study",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Jul",
day="22",
volume="10",
number="7",
pages="e38077",
keywords="accelerometry",
keywords="actigraphy",
keywords="activity counts",
keywords="wearable computing",
keywords="monitor-independent movement summary",
keywords="MIMS",
keywords="physical activity",
keywords="aging",
keywords="older adult population",
keywords="wearable device",
keywords="health monitoring",
keywords="digital health",
keywords="wearable technology",
keywords="health technology",
abstract="Background: Given the evolution of processing and analysis methods for accelerometry data over the past decade, it is important to understand how newer summary measures of physical activity compare with established measures. Objective: We aimed to compare objective measures of physical activity to increase the generalizability and translation of findings of studies that use accelerometry-based data. Methods: High-resolution accelerometry data from the Baltimore Longitudinal Study on Aging were retrospectively analyzed. Data from 655 participants who used a wrist-worn ActiGraph GT9X device continuously for a week were summarized at the minute level as ActiGraph activity count, monitor-independent movement summary, Euclidean norm minus one, mean amplitude deviation, and activity intensity. We calculated these measures using open-source packages in R. Pearson correlations between activity count and each measure were quantified both marginally and conditionally on age, sex, and BMI. Each measures pair was harmonized using nonparametric regression of minute-level data. Results: Data were from a sample (N=655; male: n=298, 45.5\%; female: n=357, 54.5\%) with a mean age of 69.8 years (SD 14.2) and mean BMI of 27.3 kg/m2 (SD 5.0). The mean marginal participant-specific correlations between activity count and monitor-independent movement summary, Euclidean norm minus one, mean amplitude deviation, and activity were r=0.988 (SE 0.0002324), r=0.867 (SE 0.001841), r=0.913 (SE 0.00132), and r=0.970 (SE 0.0006868), respectively. After harmonization, mean absolute percentage errors of predicting total activity count from monitor-independent movement summary, Euclidean norm minus one, mean amplitude deviation, and activity intensity were 2.5, 14.3, 11.3, and 6.3, respectively. The accuracies for predicting sedentary minutes for an activity count cut-off of 1853 using monitor-independent movement summary, Euclidean norm minus one, mean amplitude deviation, and activity intensity were 0.981, 0.928, 0.904, and 0.960, respectively. An R software package called SummarizedActigraphy, with a unified interface for computation of the measures from raw accelerometry data, was developed and published. Conclusions: The findings from this comparison of accelerometry-based measures of physical activity can be used by researchers and facilitate the extension of knowledge from existing literature by demonstrating the high correlation between activity count and monitor-independent movement summary (and other measures) and by providing harmonization mapping. ",
doi="10.2196/38077",
url="https://mhealth.jmir.org/2022/7/e38077",
url="http://www.ncbi.nlm.nih.gov/pubmed/35867392"
}


@Article{info:doi/10.2196/38683,
author="Tossaint-Schoenmakers, Rosian
and Kasteleyn, J. Marise
and Rauwerdink, Anneloek
and Chavannes, Niels
and Willems, Sofie
and Talboom-Kamp, A. Esther P. W.",
title="Development of a Quality Management Model and Self-assessment Questionnaire for Hybrid Health Care: Concept Mapping Study",
journal="JMIR Form Res",
year="2022",
month="Jul",
day="7",
volume="6",
number="7",
pages="e38683",
keywords="quality assessment",
keywords="hybrid health care",
keywords="blended health care",
keywords="eHealth",
keywords="digital health",
keywords="structure",
keywords="process",
keywords="outcome",
keywords="concept mapping",
abstract="Background: Working with eHealth requires health care organizations to make structural changes in the way they work. Organizational structure and process must be adjusted to provide high-quality care. This study is a follow-up study of a systematic literature review on optimally organizing hybrid health care (eHealth and face to face) using the Donabedian Structure-Process-Outcome (SPO) framework to translate the findings into a modus operandi for health care organizations. Objective: This study aimed to develop an SPO-based quality assessment model for organizing hybrid health care using an accompanying self-assessment questionnaire. Health care organizations can use this model and a questionnaire to manage and improve their hybrid health care. Methods: Concept mapping was used to enrich and validate evidence-based knowledge from a literature review using practice-based knowledge from experts. First, brainstorming was conducted. The participants listed all the factors that contributed to the effective organization of hybrid health care and the associated outcomes. Data from the brainstorming phase were combined with data from the literature study, and duplicates were removed. Next, the participants rated the factors on importance and measurability and grouped them into clusters. Finally, using multivariate statistical analysis (multidimensional scaling and hierarchical cluster analysis) and group interpretation, an SPO-based quality management model and an accompanying questionnaire were constructed. Results: All participants (n=39) were familiar with eHealth and were health care professionals, managers, researchers, patients, or eHealth suppliers. The brainstorming and literature review resulted in a list of 314 factors. After removing the duplicates, 78 factors remained. Using multivariate statistical analyses and group interpretations, a quality management model and questionnaire incorporating 8 clusters and 33 factors were developed. The 8 clusters included the following: Vision, strategy, and organization; Quality information technology infrastructure and systems; Quality eHealth application; Providing support to health care professionals; Skills, knowledge, and attitude of health care professionals; Attentiveness to the patient; Patient outcomes; and Learning system. The SPO categories were positioned as overarching themes to emphasize the interrelations between the clusters. Finally, a proposal was made to use the self-assessment questionnaire in practice, allowing measurement of the quality of each factor. Conclusions: The quality of hybrid care is determined by organizational, technological, process, and personal factors. The 33 most important factors were clustered in a quality management model and self-assessment questionnaire called the Hybrid Health Care Quality Assessment. The model visualizes the interrelations between the factors. Using a questionnaire, each factor can be assessed to determine how effectively it is organized and developed over time. Health care organizations can use the Hybrid Health Care Quality Assessment to identify improvement opportunities for solid and sustainable hybrid health care. ",
doi="10.2196/38683",
url="https://formative.jmir.org/2022/7/e38683",
url="http://www.ncbi.nlm.nih.gov/pubmed/35797097"
}


@Article{info:doi/10.2196/33867,
author="Choi, Ki Seul
and Golinkoff, Jesse
and Michna, Mark
and Connochie, Daniel
and Bauermeister, Jos{\'e}",
title="Correlates of Engagement Within an Online HIV Prevention Intervention for Single Young Men Who Have Sex With Men: Randomized Controlled Trial",
journal="JMIR Public Health Surveill",
year="2022",
month="Jun",
day="27",
volume="8",
number="6",
pages="e33867",
keywords="paradata",
keywords="mobile health",
keywords="mHealth",
keywords="digital health intervention",
keywords="risk reduction",
keywords="HIV prevention",
keywords="public health",
keywords="digital health",
keywords="sexual health",
keywords="sexual risks",
abstract="Background: Digital HIV interventions (DHI) have been efficacious in reducing sexual risk behaviors among sexual minority populations, yet challenges in promoting and sustaining users' engagement in DHI persist. Understanding the correlates of DHI engagement and their impact on HIV-related outcomes remains a priority. This study used data from a DHI (myDEx) designed to promote HIV prevention behaviors among single young men who have sex with men (YMSM; ages 18-24 years) seeking partners online. Objective: The goal of this study is to conduct a secondary analysis of the myDex project data to examine whether YMSM's online behaviors (eg, online partner-seeking behaviors and motivations) are linked to participants' engagement (ie, the number of log-ins and the number of sessions viewed). Methods: We recruited 180 YMSM who were randomized into either myDEx arm or attention-control arm using a stratified 2:1 block randomization. In the myDEx arm, we had 120 YMSM who had access to the 6-session intervention content over a 3-month period. We used Poisson regressions to assess the association between YMSM's baseline characteristics on their DHI engagement. We then examined the association between the participants' engagement and their self-reported changes in HIV-related outcomes at the 3-month follow-up. Results: The mean number of log-ins was 5.44 (range 2-14), and the number of sessions viewed was 6.93 (range 0-22) across the 3-month trial period. In multivariable models, the number of log-ins was positively associated with high education attainment (estimated Poisson regression coefficient [$\beta$]=.22; P=.045). The number of sessions viewed was associated with several baseline characteristics, including the greater number of sessions viewed among non-Hispanic YMSM ($\beta$=.27; P=.002), higher education attainment ($\beta$=.22; P=.003), higher perceived usefulness of online dating for hookups ($\beta$=.13; P=.002) and perceived loneliness ($\beta$=.06; P=.004), as well as lower experienced online discrimination ($\beta$=--.01; P=.007) and limerence ($\beta$=--.02; P=.004). The number of sessions viewed was negatively associated with changes in internalized homophobia ($\beta$=--.06; P<.001) and with changes in perceived usefulness of online dating for hookups ($\beta$=--.20; P<.001). There were no significant associations between the number of log-ins and changes in the participants' behaviors at the 90-day follow-up. Conclusions: DHI engagement is linked to participants' sociodemographic and online behaviors. Given the importance of intervention engagement in the intervention's effectiveness, DHIs with personalized intervention components that consider the individuals' differences could increase the overall engagement and efficacy of DHIs. Trial Registration: ClinicalTrials.gov NCT02842060; https://clinicaltrials.gov/ct2/show/NCT02842060. ",
doi="10.2196/33867",
url="https://publichealth.jmir.org/2022/6/e33867",
url="http://www.ncbi.nlm.nih.gov/pubmed/35759333"
}


@Article{info:doi/10.2196/31491,
author="Dramburg, Stephanie
and Perna, Serena
and Di Fraia, Marco
and Tripodi, Salvatore
and Arasi, Stefania
and Castelli, Sveva
and Villalta, Danilo
and Buzzulini, Francesca
and Sfika, Ifigenia
and Villella, Valeria
and Potapova, Ekaterina
and Brighetti, Antonia Maria
and Travaglini, Alessandro
and Verardo, Pierluigi
and Pelosi, Simone
and Matricardi, Maria Paolo",
title="Validation Parameters of Patient-Generated Data for Digitally Recorded Allergic Rhinitis Symptom and Medication Scores in the @IT.2020 Project: Exploratory Study",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Jun",
day="3",
volume="10",
number="6",
pages="e31491",
keywords="allergic rhinitis",
keywords="symptom scores",
keywords="patient-generated data",
keywords="patient-reported outcomes",
keywords="mHealth",
keywords="mobile health",
keywords="health applications",
keywords="allergies",
keywords="allergy monitor",
keywords="digital health",
keywords="medication scores",
abstract="Background: Mobile health technologies enable allergists to monitor disease trends by collecting daily patient-reported outcomes of allergic rhinitis. To this end, patients with allergies are usually required to enter their symptoms and medication repetitively over long time periods, which may present a risk to data completeness and quality in the case of insufficient effort reporting. Completeness of patient's recording is easily measured. In contrast, the intrinsic quality and accuracy of the data entered by the patients are more elusive. Objective: The aim of this study was to explore the association of adherence to digital symptom recording with a predefined set of parameters of the patient-generated symptom and medication scores and to identify parameters that may serve as proxy measure of the quality and reliability of the information recorded by the patient. Methods: The @IT.2020 project investigates the diagnostic synergy of mobile health and molecular allergology in patients with seasonal allergic rhinitis. In its pilot phase, 101 children with seasonal allergic rhinitis were recruited in Rome and instructed to record their symptoms, medication intake, and general conditions daily via a mobile app (AllergyMonitor) during the relevant pollen season. We measured adherence to daily recording as the percentage of days with data recording in the observation period. We examined the patient's trajectories of 3 disease indices (Rhinoconjunctivitis Total Symptom Score [RTSS], Combined Symptom and Medication Score [CSMS], and Visual Analogue Scale [VAS]) as putative proxies of data quality with the following 4 parameters: (1) intravariation index, (2) percentage of zero values, (3) coefficient of variation, and (4) percentage of changes in trend. Lastly, we examined the relationship between adherence to recording and each of the 4 proxy measures. Results: Adherence to recording ranged from 20\% (11/56) to 100\% (56/56), with 64.4\% (65/101) and 35.6\% (36/101) of the patients' values above (highly adherent patients) or below (low adherent patients) the threshold of 80\%, respectively. The percentage of zero values, the coefficient of variation, and the intravariation index did not significantly change with the adherence to recording. By contrast, the proportion of changes in trend was significantly higher among highly adherent patients, independently from the analyzed score (RTSS, CSMS, and VAS). Conclusions: The percentage of changes in the trend of RTSS, CSMS, and VAS is a valuable candidate to validate the quality and accuracy of the data recorded by patients with allergic rhinitis during the pollen season. The performance of this parameter must be further investigated in real-life conditions before it can be recommended for routine use in apps and electronic diaries devoted to the management of patients with allergic rhinitis. ",
doi="10.2196/31491",
url="https://mhealth.jmir.org/2022/6/e31491",
url="http://www.ncbi.nlm.nih.gov/pubmed/35657659"
}


@Article{info:doi/10.2196/31810,
author="Schmieding, L. Malte
and Kopka, Marvin
and Schmidt, Konrad
and Schulz-Niethammer, Sven
and Balzer, Felix
and Feufel, A. Markus",
title="Triage Accuracy of Symptom Checker Apps: 5-Year Follow-up Evaluation",
journal="J Med Internet Res",
year="2022",
month="May",
day="10",
volume="24",
number="5",
pages="e31810",
keywords="digital health",
keywords="triage",
keywords="symptom checker",
keywords="patient-centered care",
keywords="eHealth apps",
keywords="mobile phone",
abstract="Background: Symptom checkers are digital tools assisting laypersons in self-assessing the urgency and potential causes of their medical complaints. They are widely used but face concerns from both patients and health care professionals, especially regarding their accuracy. A 2015 landmark study substantiated these concerns using case vignettes to demonstrate that symptom checkers commonly err in their triage assessment. Objective: This study aims to revisit the landmark index study to investigate whether and how symptom checkers' capabilities have evolved since 2015 and how they currently compare with laypersons' stand-alone triage appraisal. Methods: In early 2020, we searched for smartphone and web-based applications providing triage advice. We evaluated these apps on the same 45 case vignettes as the index study. Using descriptive statistics, we compared our findings with those of the index study and with publicly available data on laypersons' triage capability. Results: We retrieved 22 symptom checkers providing triage advice. The median triage accuracy in 2020 (55.8\%, IQR 15.1\%) was close to that in 2015 (59.1\%, IQR 15.5\%). The apps in 2020 were less risk averse (odds 1.11:1, the ratio of overtriage errors to undertriage errors) than those in 2015 (odds 2.82:1), missing >40\% of emergencies. Few apps outperformed laypersons in either deciding whether emergency care was required or whether self-care was sufficient. No apps outperformed the laypersons on both decisions. Conclusions: Triage performance of symptom checkers has, on average, not improved over the course of 5 years. It decreased in 2 use cases (advice on when emergency care is required and when no health care is needed for the moment). However, triage capability varies widely within the sample of symptom checkers. Whether it is beneficial to seek advice from symptom checkers depends on the app chosen and on the specific question to be answered. Future research should develop resources (eg, case vignette repositories) to audit the capabilities of symptom checkers continuously and independently and provide guidance on when and to whom they should be recommended. ",
doi="10.2196/31810",
url="https://www.jmir.org/2022/5/e31810",
url="http://www.ncbi.nlm.nih.gov/pubmed/35536633"
}


@Article{info:doi/10.2196/32630,
author="Ni{\ss}en, Marcia
and R{\"u}egger, Dominik
and Stieger, Mirjam
and Fl{\"u}ckiger, Christoph
and Allemand, Mathias
and v Wangenheim, Florian
and Kowatsch, Tobias",
title="The Effects of Health Care Chatbot Personas With Different Social Roles on the Client-Chatbot Bond and Usage Intentions: Development of a Design Codebook and Web-Based Study",
journal="J Med Internet Res",
year="2022",
month="Apr",
day="27",
volume="24",
number="4",
pages="e32630",
keywords="chatbot",
keywords="conversational agent",
keywords="social roles",
keywords="interpersonal closeness",
keywords="social role theory",
keywords="working alliance",
keywords="design",
keywords="persona",
keywords="digital health intervention",
keywords="web-based experiment",
abstract="Background: The working alliance refers to an important relationship quality between health professionals and clients that robustly links to treatment success. Recent research shows that clients can develop an affective bond with chatbots. However, few research studies have investigated whether this perceived relationship is affected by the social roles of differing closeness a chatbot can impersonate and by allowing users to choose the social role of a chatbot. Objective: This study aimed at understanding how the social role of a chatbot can be expressed using a set of interpersonal closeness cues and examining how these social roles affect clients' experiences and the development of an affective bond with the chatbot, depending on clients' characteristics (ie, age and gender) and whether they can freely choose a chatbot's social role. Methods: Informed by the social role theory and the social response theory, we developed a design codebook for chatbots with different social roles along an interpersonal closeness continuum. Based on this codebook, we manipulated a fictitious health care chatbot to impersonate one of four distinct social roles common in health care settings---institution, expert, peer, and dialogical self---and examined effects on perceived affective bond and usage intentions in a web-based lab study. The study included a total of 251 participants, whose mean age was 41.15 (SD 13.87) years; 57.0\% (143/251) of the participants were female. Participants were either randomly assigned to one of the chatbot conditions (no choice: n=202, 80.5\%) or could freely choose to interact with one of these chatbot personas (free choice: n=49, 19.5\%). Separate multivariate analyses of variance were performed to analyze differences (1) between the chatbot personas within the no-choice group and (2) between the no-choice and the free-choice groups. Results: While the main effect of the chatbot persona on affective bond and usage intentions was insignificant (P=.87), we found differences based on participants' demographic profiles: main effects for gender (P=.04, $\eta$p2=0.115) and age (P<.001, $\eta$p2=0.192) and a significant interaction effect of persona and age (P=.01, $\eta$p2=0.102). Participants younger than 40 years reported higher scores for affective bond and usage intentions for the interpersonally more distant expert and institution chatbots; participants 40 years or older reported higher outcomes for the closer peer and dialogical-self chatbots. The option to freely choose a persona significantly benefited perceptions of the peer chatbot further (eg, free-choice group affective bond: mean 5.28, SD 0.89; no-choice group affective bond: mean 4.54, SD 1.10; P=.003, $\eta$p2=0.117). Conclusions: Manipulating a chatbot's social role is a possible avenue for health care chatbot designers to tailor clients' chatbot experiences using user-specific demographic factors and to improve clients' perceptions and behavioral intentions toward the chatbot. Our results also emphasize the benefits of letting clients freely choose between chatbots. ",
doi="10.2196/32630",
url="https://www.jmir.org/2022/4/e32630",
url="http://www.ncbi.nlm.nih.gov/pubmed/35475761"
}


@Article{info:doi/10.2196/36762,
author="Adamowicz, Lukas
and Christakis, Yiorgos
and Czech, D. Matthew
and Adamusiak, Tomasz",
title="SciKit Digital Health: Python Package for Streamlined Wearable Inertial Sensor Data Processing",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Apr",
day="21",
volume="10",
number="4",
pages="e36762",
keywords="wearable sensors",
keywords="digital medicine",
keywords="gait analysis",
keywords="human movement analysis",
keywords="digital biomarkers",
keywords="uHealth",
keywords="wearable",
keywords="sensor",
keywords="gait",
keywords="movement",
keywords="mobility",
keywords="physical activity",
keywords="sleep",
keywords="Python",
keywords="coding",
keywords="open source",
keywords="software package",
keywords="algorithm",
keywords="machine learning",
keywords="data science",
keywords="computer programming",
doi="10.2196/36762",
url="https://mhealth.jmir.org/2022/4/e36762",
url="http://www.ncbi.nlm.nih.gov/pubmed/35353039"
}


@Article{info:doi/10.2196/32643,
author="Mackey, Rachel
and Gleason, Ann
and Ciulla, Robert",
title="A Novel Method for Evaluating Mobile Apps (App Rating Inventory): Development Study",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Apr",
day="15",
volume="10",
number="4",
pages="e32643",
keywords="mobile health apps",
keywords="app rating",
keywords="app analysis methodology",
keywords="app market research",
keywords="mobile phone",
abstract="Background: Selecting and integrating health-related apps into patient care is impeded by the absence of objective guidelines for identifying high-quality apps from the many thousands now available. Objective: This study aimed to evaluate the App Rating Inventory, which was developed by the Defense Health Agency's Connected Health branch, to support clinical decisions regarding app selection and evaluate medical and behavioral apps. Methods: To enhance the tool's performance, eliminate item redundancy, reduce scoring system subjectivity, and ensure a broad application of App Rating Inventory--derived results, inventory development included 3 rounds of validation testing and 2 trial periods conducted over a 6-month interval. The development focused on content validity testing, dimensionality (ie, whether the tool's criteria performed as operationalized), factor and commonality analysis, and interrater reliability (reliability scores improved from 0.62 to 0.95 over the course of development). Results: The development phase culminated in a review of 248 apps for a total of 6944 data points and a final 28-item, 3-category app rating system. The App Rating Inventory produces scores for the following three categories: evidence (6 items), content (11 items), and customizability (11 items). The final (fourth) metric is the total score, which constitutes the sum of the 3 categories. All 28 items are weighted equally; no item is considered more (or less) important than any other item. As the scoring system is binary (either the app contains the feature or it does not), the ratings' results are not dependent on a rater's nuanced assessments. Conclusions: Using predetermined search criteria, app ratings begin with an environmental scan of the App Store and Google Play. This first step in market research funnels hundreds of apps in a given disease category down to a manageable top 10 apps that are, thereafter, rated using the App Rating Inventory. The category and final scores derived from the rating system inform the clinician about whether an app is evidence informed and easy to use. Although a rating allows a clinician to make focused decisions about app selection in a context where thousands of apps are available, clinicians must weigh the following factors before integrating apps into a treatment plan: clinical presentation, patient engagement and preferences, available resources, and technology expertise. ",
doi="10.2196/32643",
url="https://mhealth.jmir.org/2022/4/e32643",
url="http://www.ncbi.nlm.nih.gov/pubmed/35436227"
}


@Article{info:doi/10.2196/31459,
author="Zhang, Lingmin
and Li, Pengxiang",
title="Problem-Based mHealth Literacy Scale (PB-mHLS): Development and Validation",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Apr",
day="8",
volume="10",
number="4",
pages="e31459",
keywords="mobile health",
keywords="mHealth literacy",
keywords="instrument development",
keywords="problem-based framework",
abstract="Background: Mobile devices have greatly facilitated the use of digital health resources, particularly during the COVID-19 pandemic. Mobile health (mHealth) has become a common and important way to monitor and improve health conditions for people from different social classes. The ability to utilize mHealth affects its effectiveness; therefore, the widespread application of mHealth technologies calls for an instrument that can accurately measure health literacy in the era of mobile media. Objective: We aimed to (1) identify the components of mHealth literacy for ordinary users and (2) develop a systematic scale for appropriately measuring individuals' self-perceived mHealth literacy through a problem-based framework. Methods: We conducted an exploratory study involving in-depth interviews and observations (15 participants) in January 2020 and used exploratory factor analysis and confirmatory factor analysis to identify the components of mHealth literacy and develop an item pool. In February 2020, we conducted a pilot survey with 148 participants to explore the factor structures of items identified during the exploratory study. Subsequently, 2 surveys were administrated using quota sampling. The first survey (conducted in Guangdong, China) collected 552 responses during March 2020; we assessed composite reliability, convergent validity, and discriminant validity. The second survey (conducted in China nationwide) collected 433 responses during October 2021; we assessed criterion-related validity using structural equation modeling. Results: We identified 78 items during the exploratory study. The final scale---the Problem-Based mHealth Literacy Scale---consists of 33 items that reflect 8 domains of mHealth literacy. The first web-based survey suggested that mHealth literacy consists of 8 factors (ie, subscales), namely, mHealth desire, mobile phone operational skills, acquiring mHealth information, acquiring mHealth services, understanding of medical terms, mobile-based patient--doctor communication, evaluating mHealth information, and mHealth decision-making. These factors were found to be reliable (composite reliability >0.7), with good convergent validity (average variance extracted >0.5) and discriminant validity (square root of average variance extracted are greater than the correlation coefficients between factors). The findings also revealed that these 8 factors should be grouped under a second-order factor model ($\chi$2/df=2.701; comparative fit index 0.921; root mean square error of approximation 0.056; target coefficient 0.831). The second survey revealed that mHealth use had a significant impact ($\beta$=0.43, P<.001) on mHealth literacy and that mHealth literacy had a significant impact ($\beta$=0.23, P<.001) on health prevention behavior. Conclusions: This study revealed the distinctiveness of mHealth literacy by placing mHealth needs, the ability to understand medical terms, and the skills in patient--doctor interactions in the foreground. The Problem-Based mHealth Literacy Scale is a useful instrument for comprehensively measuring individuals' mHealth literacy and extends the concept of health literacy to the context of mobile communication. ",
doi="10.2196/31459",
url="https://mhealth.jmir.org/2022/4/e31459",
url="http://www.ncbi.nlm.nih.gov/pubmed/35394446"
}


@Article{info:doi/10.2196/31309,
author="Sanchez, Sherald
and Kundu, Anasua
and Limanto, Elizabeth
and Selby, Peter
and Baskerville, Bruce Neill
and Chaiton, Michael",
title="Smartphone Apps for Vaping Cessation: Quality Assessment and Content Analysis",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Mar",
day="28",
volume="10",
number="3",
pages="e31309",
keywords="e-cigarettes",
keywords="vaping",
keywords="cessation",
keywords="mHealth interventions",
abstract="Background: As the prevalence of electronic cigarette (e-cigarette) use, or vaping, continues to grow, particularly among young people, so does the need for research and interventions to address vaping. Objective: This study examines the quality of free vaping cessation apps, their contents and features, popularity among users, and adherence to evidence-based principles. Methods: A systematic search of existing apps for vaping cessation was conducted in December 2020. Eligible apps were free, in English, and included features specifically targeting vaping cessation. Each app included in the analysis was used daily for at least seven consecutive days, assessed using the Mobile App Rating Scale, and rated by at least two authors (AK, EL, or SS) based on adherence to evidence-based practices. Intraclass correlation coefficient (ICC) estimates were computed to assess interrater reliability (excellent agreement; ICC 0.92; 95\% CI 0.78-0.98). Results: A total of 8 apps were included in the quality assessment and content analysis: 3 were developed specifically for vaping cessation and 5 focused on smoking cessation while also claiming to address vaping cessation. The mean of app quality total scores was 3.66 out of 5. Existing vaping cessation apps employ similar approaches to smoking cessation apps. However, they are very low in number and have limited features developed specifically for vaping cessation. Conclusions: Given the lack of vaping cessation interventions at a time when they are urgently needed, smartphone apps are potentially valuable tools. Therefore, it is recommended that these apps apply evidence-based practices and undergo rigorous evaluations that can assess their quality, contents and features, and popularity among users. Through this process, we can improve our understanding of how apps can be effective in helping users quit vaping. ",
doi="10.2196/31309",
url="https://mhealth.jmir.org/2022/3/e31309",
url="http://www.ncbi.nlm.nih.gov/pubmed/35343904"
}


@Article{info:doi/10.2196/34148,
author="Makhmutova, Mariko
and Kainkaryam, Raghu
and Ferreira, Marta
and Min, Jae
and Jaggi, Martin
and Clay, Ieuan",
title="Predicting Changes in Depression Severity Using the PSYCHE-D (Prediction of Severity Change-Depression) Model Involving Person-Generated Health Data: Longitudinal Case-Control Observational Study",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Mar",
day="25",
volume="10",
number="3",
pages="e34148",
keywords="depression",
keywords="machine learning",
keywords="person-generated health data",
abstract="Background: In 2017, an estimated 17.3 million adults in the United States experienced at least one major depressive episode, with 35\% of them not receiving any treatment. Underdiagnosis of depression has been attributed to many reasons, including stigma surrounding mental health, limited access to medical care, and barriers due to cost. Objective: This study aimed to determine if low-burden personal health solutions, leveraging person-generated health data (PGHD), could represent a possible way to increase engagement and improve outcomes. Methods: Here, we present the development of PSYCHE-D (Prediction of Severity Change-Depression), a predictive model developed using PGHD from more than 4000 individuals, which forecasts the long-term increase in depression severity. PSYCHE-D uses a 2-phase approach. The first phase supplements self-reports with intermediate generated labels, and the second phase predicts changing status over a 3-month period, up to 2 months in advance. The 2 phases are implemented as a single pipeline in order to eliminate data leakage and ensure results are generalizable. Results: PSYCHE-D is composed of 2 Light Gradient Boosting Machine (LightGBM) algorithm--based classifiers that use a range of PGHD input features, including objective activity and sleep, self-reported changes in lifestyle and medication, and generated intermediate observations of depression status. The approach generalizes to previously unseen participants to detect an increase in depression severity over a 3-month interval, with a sensitivity of 55.4\% and a specificity of 65.3\%, nearly tripling sensitivity while maintaining specificity when compared with a random model. Conclusions: These results demonstrate that low-burden PGHD can be the basis of accurate and timely warnings that an individual's mental health may be deteriorating. We hope this work will serve as a basis for improved engagement and treatment of individuals experiencing depression. ",
doi="10.2196/34148",
url="https://mhealth.jmir.org/2022/3/e34148",
url="http://www.ncbi.nlm.nih.gov/pubmed/35333186"
}


@Article{info:doi/10.2196/35799,
author="Voorheis, Paula
and Zhao, Albert
and Kuluski, Kerry
and Pham, Quynh
and Scott, Ted
and Sztur, Peter
and Khanna, Nityan
and Ibrahim, Mohamed
and Petch, Jeremy",
title="Integrating Behavioral Science and Design Thinking to Develop Mobile Health Interventions: Systematic Scoping Review",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Mar",
day="16",
volume="10",
number="3",
pages="e35799",
keywords="behavior change",
keywords="design thinking",
keywords="digital health",
keywords="health behavior",
keywords="mobile application",
keywords="mobile health",
keywords="mobile phone",
keywords="product design",
keywords="scoping review",
keywords="systems design",
keywords="telemedicine",
keywords="user-centered design",
abstract="Background: Mobile health (mHealth) interventions are increasingly being designed to facilitate health-related behavior change. Integrating insights from behavioral science and design science can help support the development of more effective mHealth interventions. Behavioral Design (BD) and Design Thinking (DT) have emerged as best practice approaches in their respective fields. Until now, little work has been done to examine how BD and DT can be integrated throughout the mHealth design process. Objective: The aim of this scoping review was to map the evidence on how insights from BD and DT can be integrated to guide the design of mHealth interventions. The following questions were addressed: (1) what are the main characteristics of studies that integrate BD and DT during the mHealth design process? (2) what theories, models, and frameworks do design teams use during the mHealth design process? (3) what methods do design teams use to integrate BD and DT during the mHealth design process? and (4) what are key design challenges, implementation considerations, and future directions for integrating BD and DT during mHealth design? Methods: This review followed the Joanna Briggs Institute reviewer manual and PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) checklist. Studies were identified from MEDLINE, PsycINFO, Embase, CINAHL, and JMIR by using search terms related to mHealth, BD, and DT. Included studies had to clearly describe their mHealth design process and how behavior change theories, models, frameworks, or techniques were incorporated. Two independent reviewers screened the studies for inclusion and completed the data extraction. A descriptive analysis was conducted. Results: A total of 75 papers met the inclusion criteria. All studies were published between 2012 and 2021. Studies integrated BD and DT in notable ways, which can be referred to as ``Behavioral Design Thinking.'' Five steps were followed in Behavioral Design Thinking: (1) empathize with users and their behavior change needs, (2) define user and behavior change requirements, (3) ideate user-centered features and behavior change content, (4) prototype a user-centered solution that supports behavior change, and (5) test the solution against users' needs and for its behavior change potential. The key challenges experienced during mHealth design included meaningfully engaging patient and public partners in the design process, translating evidence-based behavior change techniques into actual mHealth features, and planning for how to integrate the mHealth intervention into existing clinical systems. Conclusions: Best practices from BD and DT can be integrated throughout the mHealth design process to ensure that mHealth interventions are purposefully developed to effectively engage users. Although this scoping review clarified how insights from BD and DT can be integrated during mHealth design, future research is needed to identify the most effective design approaches. ",
doi="10.2196/35799",
url="https://mhealth.jmir.org/2022/3/e35799",
url="http://www.ncbi.nlm.nih.gov/pubmed/35293871"
}


@Article{info:doi/10.2196/35879,
author="Martinon, Prescilla
and Saliasi, Ina
and Bourgeois, Denis
and Smentek, Colette
and Dussart, Claude
and Fraticelli, Laurie
and Carrouel, Florence",
title="Nutrition-Related Mobile Apps in the French App Stores: Assessment of Functionality and Quality",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Mar",
day="14",
volume="10",
number="3",
pages="e35879",
keywords="mobile apps",
keywords="behavior change",
keywords="diet",
keywords="healthy food",
keywords="nutrition",
keywords="prevention",
keywords="mHealth",
keywords="mobile health",
keywords="lifestyle",
keywords="French",
abstract="Background: The global burden of disease attributes 20\% of deaths to poor nutrition. Although hundreds of nutrition-related mobile apps have been created, and these have been downloaded by millions of users, the effectiveness of these technologies on the adoption of healthy eating has had mixed Objective: The aim of this study was to review which nutrition-related mobile apps are currently available on the French market and assess their quality. Methods: We screened apps on the Google Play Store and the French Apple App Store, from March 10 to 17, 2021, to identify those related to nutritional health. A shortlist of 15 apps was identified, and each was assessed using the French version of the Mobile App Rating Scale: 8 dietitians and nutritionists assessed 7 apps, and the remaining apps were randomly allocated to ensure 4 assessments per app. Intraclass correlation was used to evaluate interrater agreement. Means and standard deviations of scores for each section and each item were calculated. Results: The top scores for overall quality were obtained by Yazio - R{\'e}gime et Calories (mean 3.84, SD 0.32), FeelEat (mean 3.71, SD 0.47), and Bonne App (mean 3.65, SD 0.09). Engagement scores ranged from a mean of 1.95 (SD 0.5) for iEatBetter: Journal alimentaire to a mean of 3.85 (SD 0.44) for FeelEat. Functionality scores ranged from a mean of 2.25 (SD 0.54) for Naor to a mean of 4.25 (SD 0.46) for Yazio. Aesthetics scores ranged from a mean of 2.17 (SD 0.34) for Naor to a mean of 3.88 (SD 0.47) for Yazio. Information scores ranged from a mean of 2.38 (SD 0.60) for iEatBetter to a mean of 3.73 (SD 0.29) for Yazio. Subjective quality scores ranged from a mean of 1.13 (SD 0.25) for iEatBetter to a mean of 2.28 (SD 0.88) for Compteur de calories FatSecret. Specificity scores ranged from a mean of 1.38 (SD 0.64) for iEatBetter to a mean of 3.50 (SD 0.91) for FeelEat. The app-specific score was always lower than the subjective quality score, which was always lower than the quality score, which was lower than the rating from the iOS or Android app stores. Conclusions: Although prevention and information messages in apps regarding nutritional habits are not scientifically verified before marketing, we found that app quality was good. Subjective quality and specificity were associated with lower ratings. Further investigations are needed to assess whether information from these apps is consistent with recommendations and to determine the long-term impacts of these apps on users. ",
doi="10.2196/35879",
url="https://mhealth.jmir.org/2022/3/e35879",
url="http://www.ncbi.nlm.nih.gov/pubmed/35285817"
}


@Article{info:doi/10.2196/30691,
author="Tsvyatkova, Damyanka
and Buckley, Jim
and Beecham, Sarah
and Chochlov, Muslim
and O'Keeffe, R. Ian
and Razzaq, Abdul
and Rekanar, Kaavya
and Richardson, Ita
and Welsh, Thomas
and Storni, Cristiano
and ",
title="Digital Contact Tracing Apps for COVID-19: Development of a Citizen-Centered Evaluation Framework",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Mar",
day="11",
volume="10",
number="3",
pages="e30691",
keywords="COVID-19",
keywords="mHealth",
keywords="digital contact tracing apps",
keywords="framework",
keywords="evaluation",
keywords="mobile health",
keywords="health apps",
keywords="digital health",
keywords="contact tracing",
abstract="Background: The silent transmission of COVID-19 has led to an exponential growth of fatal infections. With over 4 million deaths worldwide, the need to control and stem transmission has never been more critical. New COVID-19 vaccines offer hope. However, administration timelines, long-term protection, and effectiveness against potential variants are still unknown. In this context, contact tracing and digital contact tracing apps (CTAs) continue to offer a mechanism to help contain transmission, keep people safe, and help kickstart economies. However, CTAs must address a wide range of often conflicting concerns, which make their development/evolution complex. For example, the app must preserve citizens' privacy while gleaning their close contacts and as much epidemiological information as possible. Objective: In this study, we derived a compare-and-contrast evaluative framework for CTAs that integrates and expands upon existing works in this domain, with a particular focus on citizen adoption; we call this framework the Citizen-Focused Compare-and-Contrast Evaluation Framework (C3EF) for CTAs. Methods: The framework was derived using an iterative approach. First, we reviewed the literature on CTAs and mobile health app evaluations, from which we derived a preliminary set of attributes and organizing pillars. These attributes and the probing questions that we formulated were iteratively validated, augmented, and refined by applying the provisional framework against a selection of CTAs. Each framework pillar was then subjected to internal cross-team scrutiny, where domain experts cross-checked sufficiency, relevancy, specificity, and nonredundancy of the attributes, and their organization in pillars. The consolidated framework was further validated on the selected CTAs to create a finalized version of C3EF for CTAs, which we offer in this paper. Results: The final framework presents seven pillars exploring issues related to CTA design, adoption, and use: (General) Characteristics, Usability, Data Protection, Effectiveness, Transparency, Technical Performance, and Citizen Autonomy. The pillars encompass attributes, subattributes, and a set of illustrative questions (with associated example answers) to support app design, evaluation, and evolution. An online version of the framework has been made available to developers, health authorities, and others interested in assessing CTAs. Conclusions: Our CTA framework provides a holistic compare-and-contrast tool that supports the work of decision-makers in the development and evolution of CTAs for citizens. This framework supports reflection on design decisions to better understand and optimize the design compromises in play when evolving current CTAs for increased public adoption. We intend this framework to serve as a foundation for other researchers to build on and extend as the technology matures and new CTAs become available. ",
doi="10.2196/30691",
url="https://mhealth.jmir.org/2022/3/e30691",
url="http://www.ncbi.nlm.nih.gov/pubmed/35084338"
}


@Article{info:doi/10.2196/35157,
author="Mason, Madilyn
and Cho, Youmin
and Rayo, Jessica
and Gong, Yang
and Harris, Marcelline
and Jiang, Yun",
title="Technologies for Medication Adherence Monitoring and Technology Assessment Criteria: Narrative Review",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Mar",
day="10",
volume="10",
number="3",
pages="e35157",
keywords="medication adherence",
keywords="technology assessment",
keywords="remote sensing technology",
keywords="telemedicine",
abstract="Background: Accurate measurement and monitoring of patient medication adherence is a global challenge because of the absence of gold standard methods for adherence measurement. Recent attention has been directed toward the adoption of technologies for medication adherence monitoring, as they provide the opportunity for continuous tracking of individual medication adherence behavior. However, current medication adherence monitoring technologies vary according to their technical features and data capture methods, leading to differences in their respective advantages and limitations. Overall, appropriate criteria to guide the assessment of medication adherence monitoring technologies for optimal adoption and use are lacking. Objective: This study aims to provide a narrative review of current medication adherence monitoring technologies and propose a set of technology assessment criteria to support technology development and adoption. Methods: A literature search was conducted on PubMed, Scopus, CINAHL, and ProQuest Technology Collection (2010-present) using the combination of keywords medication adherence, measurement technology, and monitoring technology. The selection focused on studies related to medication adherence monitoring technology and its development and use. The technological features, data capture methods, and potential advantages and limitations of the identified technology applications were extracted. Methods for using data for adherence monitoring were also identified. Common recurring elements were synthesized as potential technology assessment criteria. Results: Of the 3865 articles retrieved, 98 (2.54\%) were included in the final review, which reported a variety of technology applications for monitoring medication adherence, including electronic pill bottles or boxes, ingestible sensors, electronic medication management systems, blister pack technology, patient self-report technology, video-based technology, and motion sensor technology. Technical features varied by technology type, with common expectations for using these technologies to accurately monitor medication adherence and increase adoption in patients' daily lives owing to their unobtrusiveness and convenience of use. Most technologies were able to provide real-time monitoring of medication-taking behaviors but relied on proxy measures of medication adherence. Successful implementation of these technologies in clinical settings has rarely been reported. In all, 28 technology assessment criteria were identified and organized into the following five categories: development information, technology features, adherence to data collection and management, feasibility and implementation, and acceptability and usability. Conclusions: This narrative review summarizes the technical features, data capture methods, and various advantages and limitations of medication adherence monitoring technology reported in the literature and the proposed criteria for assessing medication adherence monitoring technologies. This collection of assessment criteria can be a useful tool to guide the development and selection of relevant technologies, facilitating the optimal adoption and effective use of technology to improve medication adherence outcomes. Future studies are needed to further validate the medication adherence monitoring technology assessment criteria and construct an appropriate technology assessment framework. ",
doi="10.2196/35157",
url="https://mhealth.jmir.org/2022/3/e35157",
url="http://www.ncbi.nlm.nih.gov/pubmed/35266873"
}


@Article{info:doi/10.2196/28697,
author="Kela, Neta
and Eytam, Eleanor
and Katz, Adi",
title="Supporting Management of Noncommunicable Diseases With Mobile Health (mHealth) Apps: Experimental Study",
journal="JMIR Hum Factors",
year="2022",
month="Mar",
day="2",
volume="9",
number="1",
pages="e28697",
keywords="mHealth",
keywords="digital health",
keywords="instrumentality",
keywords="aesthetics",
keywords="symbolic value",
keywords="preference",
abstract="Background: Noncommunicable diseases (NCDs) are the leading global health problem in this century and are the principal causes of death and health care spending worldwide. Mobile health (mHealth) apps can help manage and prevent NCDs if people are willing to use them as supportive tools. Still, many people are reluctant to adopt these technologies. Implementing new apps could result in earlier intervention for many health conditions, preventing more serious complications. Objective: This research project aimed to test the factors that facilitate the adoption of mHealth apps by users with NCDs. We focused on determining, first, what user interface (UI) qualities and complexity levels appeal to users in evaluating mHealth apps. We also wanted to determine whether people prefer that the data collected by an mHealth app be analyzed using a physician or an artificial intelligence (AI) algorithm. The contribution of this work is both theoretical and practical. We examined users' considerations when adopting mHealth apps that promote healthy lifestyles and helped them manage their NCDs. Our results can also help direct mHealth app UI designers to focus on the most appealing aspects of our findings. Methods: A total of 347 respondents volunteered to rate 3 models of mHealth apps based on 16 items that measured instrumentality, aesthetics, and symbolism. Respondents rated each model after reading 1 of 2 different scenarios. In one scenario, a physician analyzed the data, whereas, in the other, the data were analyzed by an AI algorithm. These scenarios tested the degree of trust people placed in AI algorithms versus the ``human touch'' of a human physician regarding analyzing data collected by an mHealth app. Results: As shown by the responses, the involvement of a human physician in the application had a significant effect (P<.001) on the perceived instrumentality of the simple model. The complex model with more controls was rated significantly more aesthetic when associated with a physician performing data analysis rather than an AI algorithm (P=.03). Conclusions: Generally, when participants found a human touch in the mHealth app (connection to a human physician who they assumed would analyze their data), they judged the app more favorably. Simple models were evaluated more positively than complex ones, and aesthetics and symbolism were salient predictors of preference. These trends suggest that designers and developers of mHealth apps should keep the designs simple and pay special attention to aesthetics and symbolic value. ",
doi="10.2196/28697",
url="https://humanfactors.jmir.org/2022/1/e28697",
url="http://www.ncbi.nlm.nih.gov/pubmed/35234653"
}


@Article{info:doi/10.2196/31327,
author="Chaudhari, Saurabh
and Ghanvatkar, Suparna
and Kankanhalli, Atreyi",
title="Personalization of Intervention Timing for Physical Activity: Scoping Review",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Feb",
day="28",
volume="10",
number="2",
pages="e31327",
keywords="review",
keywords="physical activity",
keywords="personalized intervention",
keywords="intervention timing",
keywords="mobile apps",
keywords="fitness tracker",
keywords="mobile phone",
abstract="Background: The use of sensors in smartphones, smartwatches, and wearable devices has facilitated the personalization of interventions to increase users' physical activity (PA). Recent research has focused on evaluating the effects of personalized interventions in improving PA among users. However, it is critical to deliver the intervention at an appropriate time to each user to increase the likelihood of adoption of the intervention. Earlier review studies have not focused on the personalization of intervention timing for increasing PA. Objective: This review aims to examine studies of information technology--based PA interventions with personalized intervention timing (PIT); identify inputs (eg, user location) used by the system for generating the PIT, the techniques and methods used for generating the PIT, the content of the PA intervention, and delivery mode of the intervention; and identify gaps in existing literature and suggest future research directions. Methods: A scoping review was undertaken using PsycINFO, PubMed, Scopus, and Web of Science databases based on a structured search query. The main inclusion criteria were as follows: the study aimed to promote PA, included some form of PIT, and used some form of information technology for delivery of the intervention to the user. If deemed relevant, articles were included in this review after removing duplicates and examining the title, abstract, and full text of the shortlisted articles. Results: The literature search resulted in 18 eligible studies. In this review, 72\% (13/18) of the studies focused on increasing PA as the primary objective, whereas it was the secondary focus in the remaining studies. The inputs used to generate the PIT were categorized as user preference, activity level, schedule, location, and predicted patterns. On the basis of the intervention technique, studies were classified as manual, semiautomated, or automated. Of these, the automated interventions were either knowledge based (based on rules or guidelines) or data driven. Of the 18 studies, only 6 (33\%) evaluated the effectiveness of the intervention and reported positive outcomes. Conclusions: This work reviewed studies on PIT for PA interventions and identified several aspects of the interventions, that is, inputs, techniques, contents, and delivery mode. The reviewed studies evaluated PIT in conjunction with other personalization approaches such as activity recommendation, with no study evaluating the effectiveness of PIT alone. On the basis of the findings, several important directions for future research are also highlighted in this review. ",
doi="10.2196/31327",
url="https://mhealth.jmir.org/2022/2/e31327",
url="http://www.ncbi.nlm.nih.gov/pubmed/35225811"
}


@Article{info:doi/10.2196/30211,
author="Bell, Marie Brooke
and Alam, Ridwan
and Mondol, Sayeed Abu
and Ma, Meiyi
and Emi, Afrin Ifat
and Preum, Masud Sarah
and de la Haye, Kayla
and Stankovic, A. John
and Lach, John
and Spruijt-Metz, Donna",
title="Validity and Feasibility of the Monitoring and Modeling Family Eating Dynamics System to Automatically Detect In-field Family Eating Behavior: Observational Study",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Feb",
day="18",
volume="10",
number="2",
pages="e30211",
keywords="ecological momentary assessment",
keywords="wearable sensors",
keywords="automatic dietary assessment",
keywords="eating behavior",
keywords="eating context",
keywords="smartwatch",
keywords="mobile phone",
abstract="Background: The field of dietary assessment has a long history, marked by both controversies and advances. Emerging technologies may be a potential solution to address the limitations of self-report dietary assessment methods. The Monitoring and Modeling Family Eating Dynamics (M2FED) study uses wrist-worn smartwatches to automatically detect real-time eating activity in the field. The ecological momentary assessment (EMA) methodology was also used to confirm whether eating occurred (ie, ground truth) and to measure other contextual information, including positive and negative affect, hunger, satiety, mindful eating, and social context. Objective: This study aims to report on participant compliance (feasibility) to the 2 distinct EMA protocols of the M2FED study (hourly time-triggered and eating event--triggered assessments) and on the performance (validity) of the smartwatch algorithm in automatically detecting eating events in a family-based study. Methods: In all, 20 families (58 participants) participated in the 2-week, observational, M2FED study. All participants wore a smartwatch on their dominant hand and responded to time-triggered and eating event--triggered mobile questionnaires via EMA while at home. Compliance to EMA was calculated overall, for hourly time-triggered mobile questionnaires, and for eating event--triggered mobile questionnaires. The predictors of compliance were determined using a logistic regression model. The number of true and false positive eating events was calculated, as well as the precision of the smartwatch algorithm. The Mann-Whitney U test, Kruskal-Wallis test, and Spearman rank correlation were used to determine whether there were differences in the detection of eating events by participant age, gender, family role, and height. Results: The overall compliance rate across the 20 deployments was 89.26\% (3723/4171) for all EMAs, 89.7\% (3328/3710) for time-triggered EMAs, and 85.7\% (395/461) for eating event--triggered EMAs. Time of day (afternoon odds ratio [OR] 0.60, 95\% CI 0.42-0.85; evening OR 0.53, 95\% CI 0.38-0.74) and whether other family members had also answered an EMA (OR 2.07, 95\% CI 1.66-2.58) were significant predictors of compliance to time-triggered EMAs. Weekend status (OR 2.40, 95\% CI 1.25-4.91) and deployment day (OR 0.92, 95\% CI 0.86-0.97) were significant predictors of compliance to eating event--triggered EMAs. Participants confirmed that 76.5\% (302/395) of the detected events were true eating events (ie, true positives), and the precision was 0.77. The proportion of correctly detected eating events did not significantly differ by participant age, gender, family role, or height (P>.05). Conclusions: This study demonstrates that EMA is a feasible tool to collect ground-truth eating activity and thus evaluate the performance of wearable sensors in the field. The combination of a wrist-worn smartwatch to automatically detect eating and a mobile device to capture ground-truth eating activity offers key advantages for the user and makes mobile health technologies more accessible to nonengineering behavioral researchers. ",
doi="10.2196/30211",
url="https://mhealth.jmir.org/2022/2/e30211",
url="http://www.ncbi.nlm.nih.gov/pubmed/35179508"
}


@Article{info:doi/10.2196/29922,
author="Sharma, Shreya
and Gergen Barnett, Katherine
and Maypole, (Jack) John
and Grochow Mishuris, Rebecca",
title="Evaluation of mHealth Apps for Diverse, Low-Income Patient Populations: Framework Development and Application Study",
journal="JMIR Form Res",
year="2022",
month="Feb",
day="11",
volume="6",
number="2",
pages="e29922",
keywords="mobile health application",
keywords="apps",
keywords="mobile health",
keywords="diverse",
keywords="low-income",
keywords="mHealth",
keywords="framework",
keywords="chronic disease",
keywords="condition",
keywords="smoking cessation",
keywords="diabetes",
keywords="medication adherence",
keywords="safety net hospital",
keywords="personal",
keywords="self-management",
keywords="usability test",
abstract="Background: The use of mobile technology or smartphones has grown exponentially in the United States, allowing more individuals than ever internet access. This access has been especially critical to households earning less than US \$30,000, the majority of whom indicate that smartphones are their main source of internet access. The increasing ubiquity of smartphones and virtual care promises to offset some of the health disparities that cut through the United States. However, disparities cannot be addressed if the medical information offered though smartphones is not accessible or reliable. Objective: This study seeks to create a framework to review the strengths and weaknesses of mobile Health (mHealth) apps for diverse, low-income populations. Methods: Focusing on smoking cessation, diabetes management, and medication adherence as models of disease management, we describe the process for selecting, evaluating, and obtaining patient feedback on mHealth apps. Results: The top 2 scoring apps in each category were QuitNow! and Smoke Free-Quit Smoking Now for smoking cessation, Glucosio and MyNetDiary for diabetes management, and Medisafe and MyMeds for medication adherence. Conclusions: We believe that this framework will prove useful for future mHealth app development, and clinicians and patient advisory groups in connecting culturally, educationally, and socioeconomically appropriate mHealth apps with low-income, diverse communities and thus work to bridge health disparities. ",
doi="10.2196/29922",
url="https://formative.jmir.org/2022/2/e29922",
url="http://www.ncbi.nlm.nih.gov/pubmed/35147502"
}


@Article{info:doi/10.2196/33189,
author="Wu, Dan
and Huyan, Xiaoyuan
and She, Yutong
and Hu, Junbin
and Duan, Huilong
and Deng, Ning",
title="Exploring and Characterizing Patient Multibehavior Engagement Trails and Patient Behavior Preference Patterns in Pathway-Based mHealth Hypertension Self-Management: Analysis of Use Data",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Feb",
day="3",
volume="10",
number="2",
pages="e33189",
keywords="hypertension",
keywords="mobile health",
keywords="patient behavior",
keywords="engagement",
keywords="data analysis",
abstract="Background: Hypertension is a long-term medical condition. Mobile health (mHealth) services can help out-of-hospital patients to self-manage. However, not all management is effective, possibly because the behavior mechanism and behavior preferences of patients with various characteristics in hypertension management were unclear. Objective: The purpose of this study was to (1) explore patient multibehavior engagement trails in the pathway-based hypertension self-management, (2) discover patient behavior preference patterns, and (3) identify the characteristics of patients with different behavior preferences. Methods: This study included 863 hypertensive patients who generated 295,855 use records in the mHealth app from December 28, 2016, to July 2, 2020. Markov chain was used to infer the patient multibehavior engagement trails, which contained the type, quantity, time spent, sequence, and transition probability value (TP value) of patient behavior. K-means algorithm was used to group patients by the normalized behavior preference features: the number of behavioral states that a patient performed in each trail. The pages in the app represented the behavior states. Chi-square tests, Z-test, analyses of variance, and Bonferroni multiple comparisons were conducted to characterize the patient behavior preference patterns. Results: Markov chain analysis revealed 3 types of behavior transition (1-way transition, cycle transition, and self-transition) and 4 trails of patient multibehavior engagement. In perform task trail (PT-T), patients preferred to start self-management from the states of task blood pressure (BP), task drug, and task weight (TP value 0.29, 0.18, and 0.20, respectively), and spent more time on the task food state (35.87 s). Some patients entered the states of task BP and task drug (TP value 0.20, 0.25) from the reminder item state. In the result-oriented trail (RO-T), patients spent more energy on the ranking state (19.66 s) compared to the health report state (13.25 s). In the knowledge learning trail (KL-T), there was a high probability of cycle transition (TP value 0.47, 0.31) between the states of knowledge list and knowledge content. In the support acquisition trail (SA-T), there was a high probability of self-transition in the questionnaire (TP value 0.29) state. Cluster analysis discovered 3 patient behavior preference patterns: PT-T cluster, PT-T and KL-T cluster, and PT-T and SA-T cluster. There were statistically significant associations between the behavior preference pattern and gender, education level, and BP. Conclusions: This study identified the dynamic, longitudinal, and multidimensional characteristics of patient behavior. Patients preferred to focus on BP, medications, and weight conditions and paid attention to BP and medications using reminders. The diet management and questionnaires were complicated and difficult to implement and record. Competitive methods such as ranking were more likely to attract patients to pay attention to their own self-management states. Female patients with lower education level and poorly controlled BP were more likely to be highly involved in hypertension health education. ",
doi="10.2196/33189",
url="https://mhealth.jmir.org/2022/2/e33189",
url="http://www.ncbi.nlm.nih.gov/pubmed/35113032"
}


@Article{info:doi/10.2196/28095,
author="Laiou, Petroula
and Kaliukhovich, A. Dzmitry
and Folarin, A. Amos
and Ranjan, Yatharth
and Rashid, Zulqarnain
and Conde, Pauline
and Stewart, Callum
and Sun, Shaoxiong
and Zhang, Yuezhou
and Matcham, Faith
and Ivan, Alina
and Lavelle, Grace
and Siddi, Sara
and Lamers, Femke
and Penninx, WJH Brenda
and Haro, Maria Josep
and Annas, Peter
and Cummins, Nicholas
and Vairavan, Srinivasan
and Manyakov, V. Nikolay
and Narayan, A. Vaibhav
and Dobson, JB Richard
and Hotopf, Matthew
and ",
title="The Association Between Home Stay and Symptom Severity in Major Depressive Disorder: Preliminary Findings From a Multicenter Observational Study Using Geolocation Data From Smartphones",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Jan",
day="28",
volume="10",
number="1",
pages="e28095",
keywords="major depressive disorder",
keywords="PHQ-8",
keywords="smartphone",
keywords="GPS",
keywords="home stay",
keywords="mobile phone",
abstract="Background: Most smartphones and wearables are currently equipped with location sensing (using GPS and mobile network information), which enables continuous location tracking of their users. Several studies have reported that various mobility metrics, as well as home stay, that is, the amount of time an individual spends at home in a day, are associated with symptom severity in people with major depressive disorder (MDD). Owing to the use of small and homogeneous cohorts of participants, it is uncertain whether the findings reported in those studies generalize to a broader population of individuals with MDD symptoms. Objective: The objective of this study is to examine the relationship between the overall severity of depressive symptoms, as assessed by the 8-item Patient Health Questionnaire, and median daily home stay over the 2 weeks preceding the completion of a questionnaire in individuals with MDD. Methods: We used questionnaire and geolocation data of 164 participants with MDD collected in the observational Remote Assessment of Disease and Relapse--Major Depressive Disorder study. The participants were recruited from three study sites: King's College London in the United Kingdom (109/164, 66.5\%); Vrije Universiteit Medisch Centrum in Amsterdam, the Netherlands (17/164, 10.4\%); and Centro de Investigaci{\'o}n Biom{\'e}dica en Red in Barcelona, Spain (38/164, 23.2\%). We used a linear regression model and a resampling technique (n=100 draws) to investigate the relationship between home stay and the overall severity of MDD symptoms. Participant age at enrollment, gender, occupational status, and geolocation data quality metrics were included in the model as additional explanatory variables. The 95\% 2-sided CIs were used to evaluate the significance of model variables. Results: Participant age and severity of MDD symptoms were found to be significantly related to home stay, with older (95\% CI 0.161-0.325) and more severely affected individuals (95\% CI 0.015-0.184) spending more time at home. The association between home stay and symptoms severity appeared to be stronger on weekdays (95\% CI 0.023-0.178, median 0.098; home stay: 25th-75th percentiles 17.8-22.8, median 20.9 hours a day) than on weekends (95\% CI ?0.079 to 0.149, median 0.052; home stay: 25th-75th percentiles 19.7-23.5, median 22.3 hours a day). Furthermore, we found a significant modulation of home stay by occupational status, with employment reducing home stay (employed participants: 25th-75th percentiles 16.1-22.1, median 19.7 hours a day; unemployed participants: 25th-75th percentiles 20.4-23.5, median 22.6 hours a day). Conclusions: Our findings suggest that home stay is associated with symptom severity in MDD and demonstrate the importance of accounting for confounding factors in future studies. In addition, they illustrate that passive sensing of individuals with depression is feasible and could provide clinically relevant information to monitor the course of illness in patients with MDD. ",
doi="10.2196/28095",
url="https://mhealth.jmir.org/2022/1/e28095",
url="http://www.ncbi.nlm.nih.gov/pubmed/35089148"
}


@Article{info:doi/10.2196/32104,
author="Sengupta, Arijit
and Subramanian, Hemang",
title="User Control of Personal mHealth Data Using a Mobile Blockchain App: Design Science Perspective",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Jan",
day="20",
volume="10",
number="1",
pages="e32104",
keywords="blockchain",
keywords="mobile apps",
keywords="mining",
keywords="HIPAA",
keywords="personal health data",
keywords="data privacy preservation",
keywords="security",
keywords="accuracy",
keywords="transaction safety",
abstract="Background: Integrating pervasive computing with blockchain's ability to store privacy-protected mobile health (mHealth) data while providing Health Insurance Portability and Accountability Act (HIPAA) compliance is a challenge. Patients use a multitude of devices, apps, and services to collect and store mHealth data. We present the design of an internet of things (IoT)--based configurable blockchain with different mHealth apps on iOS and Android, which collect the same user's data. We discuss the advantages of using such a blockchain architecture and demonstrate 2 things: the ease with which users can retain full control of their pervasive mHealth data and the ease with which HIPAA compliance can be accomplished by providers who choose to access user data. Objective: The purpose of this paper is to design, evaluate, and test IoT-based mHealth data using wearable devices and an efficient, configurable blockchain, which has been designed and implemented from the first principles to store such data. The purpose of this paper is also to demonstrate the privacy-preserving and HIPAA-compliant nature of pervasive computing-based personalized health care systems that provide users with total control of their own data. Methods: This paper followed the methodical design science approach adapted in information systems, wherein we evaluated prior designs, proposed enhancements with a blockchain design pattern published by the same authors, and used the design to support IoT transactions. We prototyped both the blockchain and IoT-based mHealth apps in different devices and tested all use cases that formed the design goals for such a system. Specifically, we validated the design goals for our system using the HIPAA checklist for businesses and proved the compliance of our architecture for mHealth data on pervasive computing devices. Results: Blockchain-based personalized health care systems provide several advantages over traditional systems. They provide and support extreme privacy protection, provide the ability to share personalized data and delete data upon request, and support the ability to analyze such data. Conclusions: We conclude that blockchains, specifically the consensus, hasher, storer, miner architecture presented in this paper, with configurable modules and software as a service model, provide many advantages for patients using pervasive devices that store mHealth data on the blockchain. Among them is the ability to store, retrieve, and modify ones generated health care data with a single private key across devices. These data are transparent, stored perennially, and provide patients with privacy and pseudoanonymity, in addition to very strong encryption for data access. Firms and device manufacturers would benefit from such an approach wherein they relinquish user data control while giving users the ability to select and offer their own mHealth data on data marketplaces. We show that such an architecture complies with the stringent requirements of HIPAA for patient data access. ",
doi="10.2196/32104",
url="https://mhealth.jmir.org/2022/1/e32104",
url="http://www.ncbi.nlm.nih.gov/pubmed/35049504"
}


@Article{info:doi/10.2196/24483,
author="Fox, Sarah
and Brown, E. Laura J.
and Antrobus, Steven
and Brough, David
and Drake, J. Richard
and Jury, Francine
and Leroi, Iracema
and Parry-Jones, R. Adrian
and Machin, Matthew",
title="Co-design of a Smartphone App for People Living With Dementia by Applying Agile, Iterative Co-design Principles: Development and Usability Study",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Jan",
day="14",
volume="10",
number="1",
pages="e24483",
keywords="agile",
keywords="dementia",
keywords="co-design",
keywords="cognition",
keywords="mHealth",
keywords="patient public involvement",
keywords="software development",
keywords="mobile phone",
abstract="Background: The benefits of involving those with lived experience in the design and development of health technology are well recognized, and the reporting of co-design best practices has increased over the past decade. However, it is important to recognize that the methods and protocols behind patient and public involvement and co-design vary depending on the patient population accessed. This is especially important when considering individuals living with cognitive impairments, such as dementia, who are likely to have needs and experiences unique to their cognitive capabilities. We worked alongside individuals living with dementia and their care partners to co-design a mobile health app. This app aimed to address a gap in our knowledge of how cognition fluctuates over short, microlongitudinal timescales. The app requires users to interact with built-in memory tests multiple times per day, meaning that co-designing a platform that is easy to use, accessible, and appealing is particularly important. Here, we discuss our use of Agile methodology to enable those living with dementia and their care partners to be actively involved in the co-design of a mobile health app. Objective: The aim of this study is to explore the benefits of co-design in the development of smartphone apps. Here, we share our co-design methodology and reflections on how this benefited the completed product. Methods: Our app was developed using Agile methodology, which allowed for patient and care partner input to be incorporated iteratively throughout the design and development process. Our co-design approach comprised 3 core elements, aligned with the values of patient co-design and adapted to meaningfully involve those living with cognitive impairments: end-user representation at research and software development meetings via a patient proxy; equal decision-making power for all stakeholders based on their expertise; and continuous user consultation, user-testing, and feedback. Results: This co-design approach resulted in multiple patient and care partner--led software alterations, which, without consultation, would not have been anticipated by the research team. This included 13 software design alterations, renaming of the product, and removal of a cognitive test deemed to be too challenging for the target demographic. Conclusions: We found patient and care partner input to be critical throughout the development process for early identification of design and usability issues and for identifying solutions not previously considered by our research team. As issues addressed in early co-design workshops did not reoccur subsequently, we believe this process made our product more user-friendly and acceptable, and we will formally test this assumption through future pilot-testing. ",
doi="10.2196/24483",
url="https://mhealth.jmir.org/2022/1/e24483",
url="http://www.ncbi.nlm.nih.gov/pubmed/35029539"
}


@Article{info:doi/10.2196/26563,
author="Malinka, Christin
and von Jan, Ute
and Albrecht, Urs-Vito",
title="Prioritization of Quality Principles for Health Apps Using the Kano Model: Survey Study",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Jan",
day="11",
volume="10",
number="1",
pages="e26563",
keywords="Kano",
keywords="quality principles",
keywords="mobile apps",
keywords="physicians",
keywords="surveys and questionnaires",
keywords="evaluation studies",
keywords="mHealth",
keywords="health apps",
abstract="Background: Health apps are often used without adequately taking aspects related to their quality under consideration. This may partially be due to inadequate awareness about necessary criteria and how to prioritize them when evaluating an app. Objective: The aim of this study was to introduce a method for prioritizing quality attributes in the mobile health context. To this end, physicians were asked about their assessment of nine app quality principles relevant in health contexts and their responses were used as a basis for designing a method for app prioritization. Ultimately, the goal was to aid in making better use of limited resources (eg, time) by assisting with the decision as to the specific quality principles that deserve priority in everyday medical practice and those that can be given lower priority, even in cases where the overall principles are rated similarly. Methods: A total of 9503 members of two German professional societies in the field of orthopedics were invited by email to participate in an anonymous online survey over a 1-month period. Participants were asked to rate a set of nine app quality principles using a Kano survey with functional and dysfunctional (ie, positively and negatively worded) questions. The evaluation was based on the work of Kano (baseline), supplemented by a self-designed approach. Results: Among the 9503 invited members, 382 completed relevant parts of the survey (return rate of 4.02\%). These participants were equally and randomly assigned to two groups (test group and validation group, n=191 each). Demographic characteristics did not significantly differ between groups (all P>.05). Participants were predominantly male (328/382, 85.9\%) and older than 40 years (290/382, 75.9\%). Given similar ratings, common evaluation strategies for Kano surveys did not allow for conclusive prioritization of the principles, and the same was true when using the more elaborate approach of satisfaction and dissatisfaction indices following the work of Timko. Therefore, an extended, so-called ``in-line-of-sight'' method was developed and applied for this evaluation. Modified from the Timko method, this approach is based on a ``point of view'' (POV) metric, which generates a ranking coefficient. Although the principles were previously almost exclusively rated as must-be (with the exception of resource efficiency), which was not conducive to their prioritization, the new method applied from the must-be POV resulted in identical rankings for the test and validation groups: (1) legal conformity, (2) content validity, (3) risk adequacy, (4) practicality, (5) ethical soundness, (6) usability, (7) transparency, (8) technical adequacy, and (9) resource efficiency. Conclusions: Established survey methodologies based on the work of Kano predominantly seek to categorize the attributes to be evaluated. The methodology presented here is an interesting option for prioritization, and enables focusing on the most important criteria, thus saving valuable time when reviewing apps for use in the medical field, even with otherwise largely similar categorization results. The extent to which this approach is applicable beyond the scenario presented herein requires further investigation. ",
doi="10.2196/26563",
url="https://mhealth.jmir.org/2022/1/e26563",
url="http://www.ncbi.nlm.nih.gov/pubmed/35014965"
}


@Article{info:doi/10.2196/25586,
author="Li, Yiran
and Guo, Yan
and Hong, Alicia Y.
and Zeng, Yu
and Monroe-Wise, Aliza
and Zeng, Chengbo
and Zhu, Mengting
and Zhang, Hanxi
and Qiao, Jiaying
and Xu, Zhimeng
and Cai, Weiping
and Li, Linghua
and Liu, Cong",
title="Dose--Response Effects of Patient Engagement on Health Outcomes in an mHealth Intervention: Secondary Analysis of a Randomized Controlled Trial",
journal="JMIR Mhealth Uhealth",
year="2022",
month="Jan",
day="4",
volume="10",
number="1",
pages="e25586",
keywords="mHealth",
keywords="patient engagement",
keywords="dose--response relationship",
keywords="long-term effect",
keywords="generalized linear mixed effects model",
abstract="Background: The dose--response relationship between patient engagement and long-term intervention effects in mobile health (mHealth) interventions are understudied. Studies exploring long-term and potentially changing relationships between patient engagement and health outcomes in mHealth interventions are needed. Objective: This study aims to examine dose--response relationships between patient engagement and 3 psychosocial outcomes in an mHealth intervention, Run4Love, using repeated measurements of outcomes at baseline and 3, 6, and 9 months. Methods: This study is a secondary analysis using longitudinal data from the Run4Love trial, a randomized controlled trial with 300 people living with HIV and elevated depressive symptoms to examine the effects of a 3-month mHealth intervention on reducing depressive symptoms and improving quality of life (QOL). We examined the relationships between patient engagement and depressive symptoms, QOL, and perceived stress in the intervention group (N=150) using 4--time-point outcome measurements. Patient engagement was assessed using the completion rate of course assignments and frequency of items completed. Cluster analysis was used to categorize patients into high- and low-engagement groups. Generalized linear mixed effects models were conducted to investigate the dose--response relationships between patient engagement and outcomes. Results: The cluster analysis identified 2 clusters that were distinctively different from each other. The first cluster comprised 72 participants with good compliance to the intervention, completing an average of 74\% (53/72) of intervention items (IQR 0.22). The second cluster comprised 78 participants with low compliance to the intervention, completing an average of 15\% (11/72) of intervention items (IQR 0.23). Results of the generalized linear mixed effects models showed that, compared with the low-engagement group, the high-engagement group had a significant reduction in more depressive symptoms ($\beta$=?1.93; P=.008) and perceived stress ($\beta$=?1.72; P<.001) and an improved QOL ($\beta$=2.41; P=.01) over 9 months. From baseline to 3, 6, and 9 months, the differences in depressive symptoms between the 2 engagement groups were 0.8, 1.6, 2.3, and 3.7 points, respectively, indicating widening between-group differences over time. Similarly, between-group differences in QOL and perceived stress increased over time (group differences in QOL: 0.9, 1.9, 4.7, and 5.1 points, respectively; group differences in the Perceived Stress Scale: 0.9, 1.4, 2.3, and 3.0 points, respectively). Conclusions: This study revealed a positive long-term dose--response relationship between patient engagement and 3 psychosocial outcomes among people living with HIV and elevated depressive symptoms in an mHealth intervention over 9 months using 4 time-point repeat measurement data. The high- and low-engagement groups showed significant and widening differences in depressive symptoms, QOL, and perceived stress at the 3-, 6-, and 9-month follow-ups. Future mHealth interventions should improve patient engagement to achieve long-term and sustained intervention effects. Trial Registration: Chinese Clinical Trial Registry ChiCTR-IPR-17012606; https://www.chictr.org.cn/showproj.aspx?proj=21019 ",
doi="10.2196/25586",
url="https://mhealth.jmir.org/2022/1/e25586",
url="http://www.ncbi.nlm.nih.gov/pubmed/34982724"
}


@Article{info:doi/10.2196/32660,
author="Acharya, Amish
and Judah, Gaby
and Ashrafian, Hutan
and Sounderajah, Viknesh
and Johnstone-Waddell, Nick
and Stevenson, Anne
and Darzi, Ara",
title="Investigating the Implementation of SMS and Mobile Messaging in Population Screening (the SIPS Study): Protocol for a Delphi Study",
journal="JMIR Res Protoc",
year="2021",
month="Dec",
day="22",
volume="10",
number="12",
pages="e32660",
keywords="mobile messaging",
keywords="digital communication",
keywords="population screening",
keywords="SMS",
keywords="implementation",
abstract="Background: The use of mobile messaging, including SMS, and web-based messaging in health care has grown significantly. Using messaging to facilitate patient communication has been advocated in several circumstances, including population screening. These programs, however, pose unique challenges to mobile communication, as messaging is often sent from a central hub to a diverse population with differing needs. Despite this, there is a paucity of robust frameworks to guide implementation. Objective: The aim of this protocol is to describe the methods that will be used to develop a guide for the principles of use of mobile messaging for population screening programs in England. Methods: This modified Delphi study will be conducted in two parts: evidence synthesis and consensus generation. The former will include a review of literature published from January 1, 2000, to October 1, 2021. This will elicit key themes to inform an online scoping questionnaire posed to a group of experts from academia, clinical medicine, industry, and public health. Thematic analysis of free-text responses by two independent authors will elicit items to be used during consensus generation. Patient and Public Involvement and Engagement groups will be convened to ensure that a comprehensive item list is generated that represents the public's perspective. Each item will then be anonymously voted on by experts as to its importance and feasibility of implementation in screening during three rounds of a Delphi process. Consensus will be defined a priori at 70\%, with items considered important and feasible being eligible for inclusion in the final recommendation. A list of desirable items (ie, important but not currently feasible) will be developed to guide future work. Results: The Institutional Review Board at Imperial College London has granted ethical approval for this study (reference 20IC6088). Results are expected to involve a list of recommendations to screening services, with findings being made available to screening services through Public Health England. This study will, thus, provide a formal guideline for the use of mobile messaging in screening services and will provide future directions in this field. Conclusions: The use of mobile messaging has grown significantly across health care services, especially given the COVID-19 pandemic, but its implementation in screening programs remains challenging. This modified Delphi approach with leading experts will provide invaluable insights into facilitating the incorporation of messaging into these programs and will create awareness of future developments in this area. International Registered Report Identifier (IRRID): PRR1-10.2196/32660 ",
doi="10.2196/32660",
url="https://www.researchprotocols.org/2021/12/e32660",
url="http://www.ncbi.nlm.nih.gov/pubmed/34941542"
}


@Article{info:doi/10.2196/24114,
author="O'Campo, Patricia
and Velonis, Alisa
and Buhariwala, Pearl
and Kamalanathan, Janisha
and Hassan, Awaiz Maha
and Metheny, Nicholas",
title="Design and Development of a Suite of Intimate Partner Violence Screening and Safety Planning Web Apps: User-Centered Approach",
journal="J Med Internet Res",
year="2021",
month="Dec",
day="21",
volume="23",
number="12",
pages="e24114",
keywords="intimate partner violence",
keywords="web-based applications",
keywords="women",
keywords="user-centered design",
abstract="Background: The popularity of mobile health (mHealth) technology has resulted in the development of numerous apps for almost every condition and disease management. mHealth and eHealth solutions for increasing awareness about, and safety around, intimate partner violence are no exception. These apps allow women to control access to these resources and provide unlimited, and with the right design features, safe access when these resources are needed. Few apps, however, have been designed in close collaboration with intended users to ensure relevance and effectiveness. Objective: The objective of this paper is to discuss the design of a suite of evidence-based mHealth and eHealth apps to facilitate early identification of unsafe relationship behaviors and tailored safety planning to reduce harm from violence including the methods by which we collaborated with and sought input from a population of intended users. Methods: A user-centered approach with aspects of human-centered design was followed to design a suite of 3 app-based safety planning interventions. Results: This review of the design suite of app-based interventions revealed challenges faced and lessons learned that may inform future efforts to design evidence-based mHealth and eHealth interventions. Conclusions: Following a user-centered approach can be helpful in designing mHealth and eHealth interventions for marginalized and vulnerable populations, and led to novel insights that improved the design of our interventions. ",
doi="10.2196/24114",
url="https://www.jmir.org/2021/12/e24114",
url="http://www.ncbi.nlm.nih.gov/pubmed/34931998"
}


@Article{info:doi/10.2196/29098,
author="Szinay, Dorothy
and Perski, Olga
and Jones, Andy
and Chadborn, Tim
and Brown, Jamie
and Naughton, Felix",
title="Perceptions of Factors Influencing Engagement With Health and Well-being Apps in the United Kingdom: Qualitative Interview Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Dec",
day="16",
volume="9",
number="12",
pages="e29098",
keywords="behavior change",
keywords="health apps",
keywords="mHealth",
keywords="smartphone app",
keywords="framework analysis",
keywords="COM-B",
keywords="TDF",
keywords="user engagement",
keywords="motivation",
keywords="usability",
keywords="engagement",
keywords="mobile phone",
abstract="Background: Digital health devices, such as health and well-being smartphone apps, could offer an accessible and cost-effective way to deliver health and well-being interventions. A key component of the effectiveness of health and well-being apps is user engagement. However, engagement with health and well-being apps is typically poor. Previous studies have identified a list of factors that could influence engagement; however, most of these studies were conducted on a particular population or for an app targeting a particular behavior. An understanding of the factors that influence engagement with a wide range of health and well-being apps can inform the design and the development of more engaging apps in general. Objective: The aim of this study is to explore user experiences of and reasons for engaging and not engaging with a wide range of health and well-being apps. Methods: A sample of adults in the United Kingdom (N=17) interested in using a health or well-being app participated in a semistructured interview to explore experiences of engaging and not engaging with these apps. Participants were recruited via social media platforms. Data were analyzed with the framework approach, informed by the Capability, Opportunity, Motivation--Behaviour (COM-B) model and the Theoretical Domains Framework, which are 2 widely used frameworks that incorporate a comprehensive set of behavioral influences. Results: Factors that influence the capability of participants included available user guidance, statistical and health information, reduced cognitive load, well-designed reminders, self-monitoring features, features that help establish a routine, features that offer a safety net, and stepping-stone app characteristics. Tailoring, peer support, and embedded professional support were identified as important factors that enhance user opportunities for engagement with health and well-being apps. Feedback, rewards, encouragement, goal setting, action planning, self-confidence, and commitment were judged to be the motivation factors that affect engagement with health and well-being apps. Conclusions: Multiple factors were identified across all components of the COM-B model that may be valuable for the development of more engaging health and well-being apps. Engagement appears to be influenced primarily by features that provide user guidance, promote minimal cognitive load, support self-monitoring (capability), provide embedded social support (opportunity), and provide goal setting with action planning (motivation). This research provides recommendations for policy makers, industry, health care providers, and app developers for increasing effective engagement. ",
doi="10.2196/29098",
url="https://mhealth.jmir.org/2021/12/e29098",
url="http://www.ncbi.nlm.nih.gov/pubmed/34927597"
}


@Article{info:doi/10.2196/31541,
author="Lowe, Cabella
and Hanuman Sing, Harry
and Marsh, William
and Morrissey, Dylan",
title="Validation of a Musculoskeletal Digital Assessment Routing Tool: Protocol for a Pilot Randomized Crossover Noninferiority Trial",
journal="JMIR Res Protoc",
year="2021",
month="Dec",
day="13",
volume="10",
number="12",
pages="e31541",
keywords="mHealth",
keywords="mobile health",
keywords="eHealth",
keywords="digital health",
keywords="digital technology",
keywords="musculoskeletal",
keywords="triage",
keywords="physiotherapy triage",
keywords="validation",
keywords="mobile phone",
abstract="Background: Musculoskeletal conditions account for 16\% of global disability, resulting in a negative effect on millions of patients and an increasing demand for health care use. Digital technologies to improve health care outcomes and efficiency are considered a priority; however, innovations are rarely tested with sufficient rigor in clinical trials, which is the gold standard for clinical proof of safety and efficacy. We have developed a new musculoskeletal digital assessment routing tool (DART) that allows users to self-assess and be directed to the right care. DART requires validation in a real-world setting before implementation. Objective: This pilot study aims to assess the feasibility of a future trial by exploring the key aspects of trial methodology, assessing the procedures, and collecting exploratory data to inform the design of a definitive randomized crossover noninferiority trial to assess DART safety and effectiveness. Methods: We will collect data from 76 adults with a musculoskeletal condition presenting to general practitioners within a National Health Service (NHS) in England. Participants will complete both a DART assessment and a physiotherapist-led triage, with the order determined by randomization. The primary analysis will involve an absolute agreement intraclass correlation (A,1) estimate with 95\% CI between DART and the clinician for assessment outcomes signposting to condition management pathways. Data will be collected to allow the analysis of participant recruitment and retention, randomization, allocation concealment, blinding, data collection process, and bias. In addition, the impact of trial burden and potential barriers to intervention delivery will be considered. The DART user satisfaction will be measured using the system usability scale. Results: A UK NHS ethics submission was done during June 2021 and is pending approval; recruitment will commence in early 2022, with data collection anticipated to last for 3 months. The results will be reported in a follow-up paper in 2022. Conclusions: This study will inform the design of a randomized controlled crossover noninferiority study that will provide evidence concerning mobile health DART system clinical signposting in an NHS setting before real-world implementation. Success should produce evidence of a safe, effective system with good usability, potentially facilitating quicker and easier patient access to appropriate care while reducing the burden on primary and secondary care musculoskeletal services. This rigorous approach to mobile health system testing could be used as a guide for other developers of similar applications. Trial Registration: ClinicalTrials.gov NCT04904029; http://clinicaltrials.gov/ct2/show/NCT04904029 International Registered Report Identifier (IRRID): PRR1-10.2196/31541 ",
doi="10.2196/31541",
url="https://www.researchprotocols.org/2021/12/e31541",
url="http://www.ncbi.nlm.nih.gov/pubmed/34898461"
}


@Article{info:doi/10.2196/11055,
author="Mcgeough, Julienne
and Gallagher-Mitchell, Thomas
and Clark, Andrew Dan Philip
and Harrison, Neil",
title="Reliability and Confirmatory Factor Analysis (CFA) of a Paper- Versus App-Administered Resilience Scale in Scottish Youths: Comparative Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Dec",
day="7",
volume="9",
number="12",
pages="e11055",
keywords="resilience",
keywords="psychometrics",
keywords="app administration",
keywords="cyberpsychology",
abstract="Background: Adequately measuring resilience is important to support young people and children who may need to access resources through social work or educational settings. A widely accepted measure of youth resilience has been developed previously and has been shown to be suitable for vulnerable youth. While the measure is completed by the young person on paper, it has been designed to be worked through with a teacher or social worker in case further clarification is required. However, this method is time consuming and, when faced with large groups of pupils who need assessment, can be overwhelming for schools and practitioners. This study assesses app software with a built-in avatar that can guide young persons through the assessment and its interpretation. Objective: Our primary objective is to compare the reliability and psychometric properties of a mobile software app to a paper version of the Child and Youth Resilience measure (CYRM-28). Second, this study assesses the use of the CYRM-28 in a Scottish youth population (aged 11-18 years). Methods: Following focus groups and discussion with teachers, social workers, and young people, an avatar was developed by a software company and integrated into an android smartphone app designed to ask questions via the device's inbuilt text-to-voice engine. In total, 714 students from 2 schools in North East Scotland completed either a paper version or app version of the CYRM-28. A cross-sectional design was used, and students completed their allocated version twice, with a 2-week period in between each testing. All participants could request clarification either from a guidance teacher (paper version) or from the in-built software glossary (app version). Results: Test and retest correlations showed that the app version performed better than the paper version of the questionnaire (paper version: r303=0.81; P<.001; 95\% CI 0.77-0.85; app version: r413=0.84; P<.001; 95\% CI 0.79-0.89). Fisher r to z transformation revealed a significant difference in the correlations (Z=--2.97, P<.01). Similarly, Cronbach $\alpha$ in both conditions was very high (app version: $\alpha$=.92; paper version: $\alpha$=.87), suggesting item redundancy. Ordinarily, this would lead to a possible removal of highly correlated items; however, our primary objective was to compare app delivery methods over a pen-and-paper mode and was hence beyond the scope of the study. Fisher r to z transformation revealed a significant difference in the correlations (Z=--3.69, P<.01). A confirmatory factor analysis supported the 3-factor solution (individual, relational, and contextual) and reported a good model fit ($\chi$215=27.6 [n=541], P=.24). Conclusions: ALEX, an avatar with an integrated voice guide, had higher reliability when measuring resilience than a paper version with teacher assistance. The CFA reports similar structure using the avatar when compared against the original validation. ",
doi="10.2196/11055",
url="https://mhealth.jmir.org/2021/12/e11055",
url="http://www.ncbi.nlm.nih.gov/pubmed/34878995"
}


@Article{info:doi/10.2196/27533,
author="Vanderloo, M. Leigh
and Carsley, Sarah
and Agarwal, Payal
and Marini, Flavia
and Dennis, Cindy-Lee
and Birken, Catherine",
title="Selecting and Evaluating Mobile Health Apps for the Healthy Life Trajectories Initiative: Development of the eHealth Resource Checklist",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Dec",
day="2",
volume="9",
number="12",
pages="e27533",
keywords="eHealth resources",
keywords="applications",
keywords="quality assessment",
keywords="preconception health",
abstract="Background: The ubiquity of smartphones and mobile devices in the general population presents an unprecedented opportunity for preventative health. Not surprisingly, the use of electronic health (eHealth) resources accessed through mobile devices in clinical trials is becoming more prevalent; the selection, screening, and collation of quality eHealth resources is necessary to clinical trials using these technologies. However, the constant creation and turnover of new eHealth resources can make this task difficult. Although syntheses of eHealth resources are becoming more common, their methodological and reporting quality require improvement so as to be more accessible to nonexperts. Further, there continues to be significant variation in quality criteria employed for assessment, with no clear method for developing the included criteria. There is currently no single existing framework that addresses all six dimensions of mobile health app quality identified in Agarwal et al's recent scoping review (ie, basic descriptions of the design and usage of the resource; technical features and accessibility; health information quality; usability; evidence of impact; and user engagement and behavior change). In instances where highly systematic tactics are not possible (due to time constraints, cost, or lack of expertise), there may be value in adopting practical and pragmatic approaches to helping researchers and clinicians identify and disseminate e-resources. Objective: The study aimed to create a set of guidelines (ie, a checklist) to aid the members of the Healthy Life Trajectories Initiative (HeLTI) Canada trial---a preconception randomized controlled clinical trial to prevent child obesity---to assist their efforts in searching, identifying, screening, and including selected eHealth resources for participant use in the study intervention. Methods: A framework for searching, screening, and selecting eHealth resources was adapted from the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) checklist for systematic and scoping reviews to optimize the rigor, clarity, and transparency of the process. Details regarding searching, selecting, extracting, and assessing quality of eHealth resources are described. Results: This study resulted in the systematic development of a checklist consisting of 12 guiding principles, organized in a chronological versus priority sequence to aid researchers in searching, screening, and assessing the quality of various eHealth resources. Conclusions: The eHealth Resource Checklist will assist researchers in navigating the eHealth resource space by providing a mechanism to detail their process of developing inclusion criteria, identifying search location, selecting and reviewing evidence, extracting information, evaluating the quality of the evidence, and synthesizing the extracted evidence. The overarching goal of this checklist is to provide researchers or generalists new to the eHealth field with a tool that balances pragmatism with rigor and that helps standardize the process of searching and critiquing digital material---a particularly important aspect given the recent explosion of and reliance on eHealth resources. Moreover, this checklist may be useful to other researchers and practitioners developing similar health interventions. ",
doi="10.2196/27533",
url="https://mhealth.jmir.org/2021/12/e27533",
url="http://www.ncbi.nlm.nih.gov/pubmed/34860681"
}


@Article{info:doi/10.2196/15433,
author="Muro-Culebras, Antonio
and Escriche-Escuder, Adrian
and Martin-Martin, Jaime
and Rold{\'a}n-Jim{\'e}nez, Cristina
and De-Torres, Irene
and Ruiz-Mu{\~n}oz, Maria
and Gonzalez-Sanchez, Manuel
and Mayoral-Cleries, Fermin
and Bir{\'o}, Attila
and Tang, Wen
and Nikolova, Borjanka
and Salvatore, Alfredo
and Cuesta-Vargas, Ignacio Antonio",
title="Tools for Evaluating the Content, Efficacy, and Usability of Mobile Health Apps According to the Consensus-Based Standards for the Selection of Health Measurement Instruments: Systematic Review",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Dec",
day="1",
volume="9",
number="12",
pages="e15433",
keywords="mobile health",
keywords="mHealth",
keywords="eHealth",
keywords="mobile apps",
keywords="assessment",
keywords="rating",
keywords="smartphone",
keywords="questionnaire design",
keywords="mobile phone",
abstract="Background: There are several mobile health (mHealth) apps in mobile app stores. These apps enter the business-to-customer market with limited controls. Both, apps that users use autonomously and those designed to be recommended by practitioners require an end-user validation to minimize the risk of using apps that are ineffective or harmful. Prior studies have reviewed the most relevant aspects in a tool designed for assessing mHealth app quality, and different options have been developed for this purpose. However, the psychometric properties of the mHealth quality measurement tools, that is, the validity and reliability of the tools for their purpose, also need to be studied. The Consensus-based Standards for the Selection of Health Measurement Instruments (COSMIN) initiative has developed tools for selecting the most suitable measurement instrument for health outcomes, and one of the main fields of study was their psychometric properties. Objective: This study aims to address and psychometrically analyze, following the COSMIN guideline, the quality of the tools that are used to measure the quality of mHealth apps. Methods: From February 1, 2019, to December 31, 2019, 2 reviewers searched PubMed and Embase databases, identifying mHealth app quality measurement tools and all the validation studies associated with each of them. For inclusion, the studies had to be meant to validate a tool designed to assess mHealth apps. Studies that used these tools for the assessment of mHealth apps but did not include any psychometric validation were excluded. The measurement tools were analyzed according to the 10 psychometric properties described in the COSMIN guideline. The dimensions and items analyzed in each tool were also analyzed. Results: The initial search showed 3372 articles. Only 10 finally met the inclusion criteria and were chosen for analysis in this review, analyzing 8 measurement tools. Of these tools, 4 validated ?5 psychometric properties defined in the COSMIN guideline. Although some of the tools only measure the usability dimension, other tools provide information such as engagement, esthetics, or functionality. Furthermore, 2 measurement tools, Mobile App Rating Scale and mHealth Apps Usability Questionnaire, have a user version, as well as a professional version. Conclusions: The Health Information Technology Usability Evaluation Scale and the Measurement Scales for Perceived Usefulness and Perceived Ease of Use were the most validated tools, but they were very focused on usability. The Mobile App Rating Scale showed a moderate number of validated psychometric properties, measures a significant number of quality dimensions, and has been validated in a large number of mHealth apps, and its use is widespread. It is suggested that the continuation of the validation of this tool in other psychometric properties could provide an appropriate option for evaluating the quality of mHealth apps. ",
doi="10.2196/15433",
url="https://mhealth.jmir.org/2021/12/e15433",
url="http://www.ncbi.nlm.nih.gov/pubmed/34855618"
}


@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/10.2196/27779,
author="Klimis, Harry
and Nothman, Joel
and Lu, Di
and Sun, Chao
and Cheung, Wah N.
and Redfern, Julie
and Thiagalingam, Aravinda
and Chow, K. Clara",
title="Text Message Analysis Using Machine Learning to Assess Predictors of Engagement With Mobile Health Chronic Disease Prevention Programs: Content Analysis",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Nov",
day="10",
volume="9",
number="11",
pages="e27779",
keywords="mHealth",
keywords="machine learning",
keywords="chronic disease",
keywords="cardiovascular",
keywords="text messaging",
keywords="SMS",
keywords="digital health",
keywords="mobile phone",
keywords="engagement",
keywords="prevention",
abstract="Background: SMS text messages as a form of mobile health are increasingly being used to support individuals with chronic diseases in novel ways that leverage the mobility and capabilities of mobile phones. However, there are knowledge gaps in mobile health, including how to maximize engagement. Objective: This study aims to categorize program SMS text messages and participant replies using machine learning (ML) and to examine whether message characteristics are associated with premature program stopping and engagement. Methods: We assessed communication logs from SMS text message--based chronic disease prevention studies that encouraged 1-way (SupportMe/ITM) and 2-way (TEXTMEDS [Text Messages to Improve Medication Adherence and Secondary Prevention]) communication. Outgoing messages were manually categorized into 5 message intents (informative, instructional, motivational, supportive, and notification) and replies into 7 groups (stop, thanks, questions, reporting healthy, reporting struggle, general comment, and other). Grid search with 10-fold cross-validation was implemented to identify the best-performing ML models and evaluated using nested cross-validation. Regression models with interaction terms were used to compare the association of message intent with premature program stopping and engagement (replied at least 3 times and did not prematurely stop) in SupportMe/ITM and TEXTMEDS. Results: We analyzed 1550 messages and 4071 participant replies. Approximately 5.49\% (145/2642) of participants responded with stop, and 11.7\% (309/2642) of participants were engaged. Our optimal ML model correctly classified program message intent with 76.6\% (95\% CI 63.5\%-89.8\%) and replies with 77.8\% (95\% CI 74.1\%-81.4\%) balanced accuracy (average area under the curve was 0.95 and 0.96, respectively). Overall, supportive (odds ratio [OR] 0.53, 95\% CI 0.35-0.81) messages were associated with reduced chance of stopping, as were informative messages in SupportMe/ITM (OR 0.35, 95\% CI 0.20-0.60) but not in TEXTMEDS (for interaction, P<.001). Notification messages were associated with a higher chance of stopping in SupportMe/ITM (OR 5.76, 95\% CI 3.66-9.06) but not TEXTMEDS (for interaction, P=.01). Overall, informative (OR 1.76, 95\% CI 1.46-2.12) and instructional (OR 1.47, 95\% CI 1.21-1.80) messages were associated with higher engagement but not motivational messages (OR 1.18, 95\% CI 0.82-1.70; P=.37). For supportive messages, the association with engagement was opposite with SupportMe/ITM (OR 1.77, 95\% CI 1.21-2.58) compared with TEXTMEDS (OR 0.77, 95\% CI 0.60-0.98; for interaction, P<.001). Notification messages were associated with reduced engagement in SupportMe/ITM (OR 0.07, 95\% CI 0.05-0.10) and TEXTMEDS (OR 0.28, 95\% CI 0.20-0.39); however, the strength of the association was greater in SupportMe/ITM (for interaction P<.001). Conclusions: ML models enable monitoring and detailed characterization of program messages and participant replies. Outgoing message intent may influence premature program stopping and engagement, although the strength and direction of association appear to vary by program type. Future studies will need to examine whether modifying message characteristics can optimize engagement and whether this leads to behavior change. ",
doi="10.2196/27779",
url="https://mhealth.jmir.org/2021/11/e27779",
url="http://www.ncbi.nlm.nih.gov/pubmed/34757324"
}


@Article{info:doi/10.2196/29815,
author="Lazard, J. Allison
and Babwah Brennen, Scott J.
and Belina, P. Stephanie",
title="App Designs and Interactive Features to Increase mHealth Adoption: User Expectation Survey and Experiment",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Nov",
day="4",
volume="9",
number="11",
pages="e29815",
keywords="smartphone",
keywords="interactive design",
keywords="mobile apps",
keywords="preventive health",
keywords="mental models",
keywords="prototypicality",
keywords="attention",
keywords="affordances",
abstract="Background: Despite the ubiquity of smartphones, there is little guidance for how to design mobile health apps to increase use. Specifically, knowing what features users expect, grab their attention, encourage use (via predicted use or through positive app evaluations), and signal beneficial action possibilities can guide and focus app development efforts. Objective: We investigated what features users expect and how the design (prototypicality) impacts app adoption. Methods: In a web-based survey, we elicited expectations, including presence and placement, for 12 app features. Thereafter, participants (n=462) viewed 2 health apps (high prototypicality similar to top downloaded apps vs low prototypicality similar to research interventions) and reported willingness to download, attention, and predicted use of app features. Participants rated both apps (high and low) for aesthetics, ease of use, usefulness, perceived affordances, and intentions to use. Results: Most participants (425/462, 92\%) expected features for navigation or personal settings (eg, menu) in specific regions (eg, top corners). Features with summary graphs or statics were also expected by many (395-396 of 462, 86\%), with a center placement expectation. A feature to ``share with friends'' was least expected among participants (203/462, 44\%). Features fell into 4 unique categories based on attention and predicted use, including essential features with high (>50\% or >231 of 462) predicted use and attention (eg, calorie trackers), flashy features with high attention but lower predicted use (eg, links to specific diets), functional features with modest attention and low use (eg, settings), and mundane features with low attention and use (eg, discover tabs). When given a choice, 347 of 462 (75\%) participants would download the high-prototypicality app. High prototypicality apps (vs low) led to greater aesthetics, ease of use, usefulness, and intentions, (for all, P<.001). Participants thought that high prototypicality apps had more perceived affordances. Conclusions: Intervention designs that fail to meet a threshold of mHealth expectations will be dismissed as less usable or beneficial. Individuals who download health apps have shared expectations for features that should be there, as well as where these features should appear. Meeting these expectations can improve app evaluations and encourage use. Our typology should guide presence and placement of expected app features to signal value and increase use to impact preventive health behaviors. Features that will likely be used and are attention-worthy---essential, flashy, and functional---should be prioritized during app development. ",
doi="10.2196/29815",
url="https://mhealth.jmir.org/2021/11/e29815",
url="http://www.ncbi.nlm.nih.gov/pubmed/34734829"
}


@Article{info:doi/10.2196/28384,
author="Woulfe, Fionn
and Fadahunsi, Philip Kayode
and Smith, Simon
and Chirambo, Baxter Griphin
and Larsson, Emma
and Henn, Patrick
and Mawkin, Mala
and O' Donoghue, John",
title="Identification and Evaluation of Methodologies to Assess the Quality of Mobile Health Apps in High-, Low-, and Middle-Income Countries: Rapid Review",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Oct",
day="12",
volume="9",
number="10",
pages="e28384",
keywords="mHealth app",
keywords="health app",
keywords="mobile health",
keywords="health website",
keywords="quality",
keywords="quality assessment",
keywords="methodology",
keywords="high-income country",
keywords="low-income country",
keywords="middle-income country",
keywords="LMIC",
keywords="mobile phone",
abstract="Background: In recent years, there has been rapid growth in the availability and use of mobile health (mHealth) apps around the world. A consensus regarding an accepted standard to assess the quality of such apps has yet to be reached. A factor that exacerbates the challenge of mHealth app quality assessment is variations in the interpretation of quality and its subdimensions. Consequently, it has become increasingly difficult for health care professionals worldwide to distinguish apps of high quality from those of lower quality. This exposes both patients and health care professionals to unnecessary risks. Despite progress, limited understanding of the contributions of researchers in low- and middle-income countries (LMICs) exists on this topic. Furthermore, the applicability of quality assessment methodologies in LMIC settings remains relatively unexplored. Objective: This rapid review aims to identify current methodologies in the literature to assess the quality of mHealth apps, understand what aspects of quality these methodologies address, determine what input has been made by authors from LMICs, and examine the applicability of such methodologies in LMICs. Methods: This review was registered with PROSPERO (International Prospective Register of Systematic Reviews). A search of PubMed, EMBASE, Web of Science, and Scopus was performed for papers related to mHealth app quality assessment methodologies, which were published in English between 2005 and 2020. By taking a rapid review approach, a thematic and descriptive analysis of the papers was performed. Results: Electronic database searches identified 841 papers. After the screening process, 52 papers remained for inclusion. Of the 52 papers, 5 (10\%) proposed novel methodologies that could be used to evaluate mHealth apps of diverse medical areas of interest, 8 (15\%) proposed methodologies that could be used to assess apps concerned with a specific medical focus, and 39 (75\%) used methodologies developed by other published authors to evaluate the quality of various groups of mHealth apps. The authors in 6\% (3/52) of papers were solely affiliated to institutes in LMICs. A further 15\% (8/52) of papers had at least one coauthor affiliated to an institute in an LMIC. Conclusions: Quality assessment of mHealth apps is complex in nature and at times subjective. Despite growing research on this topic, to date, an all-encompassing appropriate means for evaluating the quality of mHealth apps does not exist. There has been engagement with authors affiliated to institutes across LMICs; however, limited consideration of current generic methodologies for application in LMIC settings has been identified. Trial Registration: PROSPERO CRD42020205149; https://www.crd.york.ac.uk/prospero/display\_record.php?RecordID=205149 ",
doi="10.2196/28384",
url="https://mhealth.jmir.org/2021/10/e28384",
url="http://www.ncbi.nlm.nih.gov/pubmed/34636737"
}


@Article{info:doi/10.2196/22653,
author="Maliwichi, Priscilla
and Chigona, Wallace
and Sowon, Karen",
title="Appropriation of mHealth Interventions for Maternal Health Care in Sub-Saharan Africa: Hermeneutic Review",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Oct",
day="6",
volume="9",
number="10",
pages="e22653",
keywords="mHealth",
keywords="appropriation",
keywords="mobile phones",
keywords="model of technology appropriation",
keywords="maternal health",
keywords="community of purpose",
keywords="hermeneutic literature review",
abstract="Background: Many maternal clients from poorly resourced communities die from preventable pregnancy-related complications. The situation is especially grave in sub-Saharan Africa. Mobile health (mHealth) interventions have the potential to improve maternal health outcomes. mHealth interventions are used to encourage behavioral change for health care--seeking by maternal clients. However, the appropriation of such interventions among maternal health clients is not always guaranteed. Objective: This study aims to understand how maternal clients appropriate mHealth interventions and the factors that affect this appropriation. Methods: This study used a hermeneutic literature review informed by the model of technology appropriation. We used data from three mHealth case studies in sub-Saharan Africa: Mobile Technology for Community Health, MomConnect, and Chipatala Cha Pa Foni. We used the search and acquisition hermeneutic circle to identify and retrieve peer-reviewed and gray literature from the Web of Science, Google Scholar, Google, and PubMed. We selected 17 papers for analysis. We organized the findings using three levels of the appropriation process: adoption, adaptation, and integration. Results: This study found that several factors affected how maternal clients appropriated mHealth interventions. The study noted that it is paramount that mHealth designers and implementers should consider the context of mHealth interventions when designing and implementing interventions. However, the usefulness of an mHealth intervention may enhance how maternal health clients appropriate it. Furthermore, a community of purpose around the maternal client may be vital to the success of the mHealth intervention. Conclusions: The design and implementation of interventions have the potential to exacerbate inequalities within communities. To mitigate against inequalities during appropriation, it is recommended that communities of purpose be included in the design and implementation of maternal mHealth interventions. ",
doi="10.2196/22653",
url="https://mhealth.jmir.org/2021/10/e22653",
url="http://www.ncbi.nlm.nih.gov/pubmed/34612835"
}


@Article{info:doi/10.2196/25630,
author="Wu, Dan
and An, Jiye
and Yu, Ping
and Lin, Hui
and Ma, Li
and Duan, Huilong
and Deng, Ning",
title="Patterns for Patient Engagement with the Hypertension Management and Effects of Electronic Health Care Provider Follow-up on These Patterns: Cluster Analysis",
journal="J Med Internet Res",
year="2021",
month="Sep",
day="28",
volume="23",
number="9",
pages="e25630",
keywords="hypertension",
keywords="health care services",
keywords="mHealth",
keywords="patient engagement",
keywords="electronic follow-up",
keywords="cluster analysis",
abstract="Background: Hypertension is a long-term medical condition. Electronic and mobile health care services can help patients to self-manage this condition. However, not all management is effective, possibly due to different levels of patient engagement (PE) with health care services. Health care provider follow-up is an intervention to promote PE and blood pressure (BP) control. Objective: This study aimed to discover and characterize patterns of PE with a hypertension self-management app, investigate the effects of health care provider follow-up on PE, and identify the follow-up effects on BP in each PE pattern. Methods: PE was represented as the number of days that a patient recorded self-measured BP per week. The study period was the first 4 weeks for a patient to engage in the hypertension management service. K-means algorithm was used to group patients by PE. There was compliance follow-up, regular follow-up, and abnormal follow-up in management. The follow-up effect was calculated by the change in PE (CPE) and the change in systolic blood pressure (CSBP, SBP) before and after each follow-up. Chi-square tests and z scores were used to ascertain the distribution of gender, age, education level, SBP, and the number of follow-ups in each cluster. The follow-up effect was identified by analysis of variances. Once a significant effect was detected, Bonferroni multiple comparisons were further conducted to identify the difference between 2 clusters. Results: Patients were grouped into 4 clusters according to PE: (1) PE started low and dropped even lower (PELL), (2) PE started high and remained high (PEHH), (3) PE started high and dropped to low (PEHL), and (4) PE started low and rose to high (PELH). Significantly more patients over 60 years old were found in the PEHH cluster (P?.05). Abnormal follow-up was significantly less frequent (P?.05) in the PELL cluster. Compliance follow-up and regular follow-up can improve PE. In the clusters of PEHH and PELH, the improvement in PE in the first 3 weeks and the decrease in SBP in all 4 weeks were significant after follow-up. The SBP of the clusters of PELL and PELH decreased more (--6.1 mmHg and --8.4 mmHg) after follow-up in the first week. Conclusions: Four distinct PE patterns were identified for patients engaging in the hypertension self-management app. Patients aged over 60 years had higher PE in terms of recording self-measured BP using the app. Once SBP reduced, patients with low PE tended to stop using the app, and a continued decline in PE occurred simultaneously with the increase in SBP. The duration and depth of the effect of health care provider follow-up were more significant in patients with high or increased engagement after follow-up. ",
doi="10.2196/25630",
url="https://www.jmir.org/2021/9/e25630",
url="http://www.ncbi.nlm.nih.gov/pubmed/34581680"
}


@Article{info:doi/10.2196/31421,
author="Markowski, L. Kelly
and Smith, A. Jeffrey
and Gauthier, Robin G.
and Harcey, R. Sela",
title="Patterns of Missing Data With Ecological Momentary Assessment Among People Who Use Drugs: Feasibility Study Using Pilot Study Data",
journal="JMIR Form Res",
year="2021",
month="Sep",
day="24",
volume="5",
number="9",
pages="e31421",
keywords="EMA",
keywords="ecological momentary assessment",
keywords="PWUD",
keywords="people who use drugs",
keywords="noncompliance",
keywords="missing data",
keywords="mobile phone",
abstract="Background: Ecological momentary assessment (EMA) is a set of research methods that capture events, feelings, and behaviors as they unfold in their real-world setting. Capturing data in the moment reduces important sources of measurement error but also generates challenges for noncompliance (ie, missing data). To date, EMA research has only examined the overall rates of noncompliance. Objective: In this study, we identify four types of noncompliance among people who use drugs and aim to examine the factors associated with the most common types. Methods: Data were obtained from a recent pilot study of 28 Nebraskan people who use drugs who answered EMA questions for 2 weeks. We examined questions that were not answered because they were skipped, they expired, the phone was switched off, or the phone died after receiving them. Results: We found that the phone being switched off and questions expiring comprised 93.34\% (1739/1863 missing question-instances) of our missing data. Generalized structural equation model results show that participant-level factors, including age (relative risk ratio [RRR]=0.93; P=.005), gender (RRR=0.08; P=.006), homelessness (RRR=3.80; P=.04), personal device ownership (RRR=0.14; P=.008), and network size (RRR=0.57; P=.001), are important for predicting off missingness, whereas only question-level factors, including time of day (ie, morning compared with afternoon, RRR=0.55; P<.001) and day of week (ie, Tuesday-Saturday compared with Sunday, RRR=0.70, P=.02; RRR=0.64, P=.005; RRR=0.58, P=.001; RRR=0.55, P<.001; and RRR=0.66, P=.008, respectively) are important for predicting expired missingness. The week of study is important for both (ie, week 2 compared with week 1, RRR=1.21, P=.03, for off missingness and RRR=1.98, P<.001, for expired missingness). Conclusions: We suggest a three-pronged strategy to preempt missing EMA data with high-risk populations: first, provide additional resources for participants likely to experience phone charging problems (eg, people experiencing homelessness); second, ask questions when participants are not likely to experience competing demands (eg, morning); and third, incentivize continued compliance as the study progresses. Attending to these issues can help researchers ensure maximal data quality. ",
doi="10.2196/31421",
url="https://formative.jmir.org/2021/9/e31421",
url="http://www.ncbi.nlm.nih.gov/pubmed/34464327"
}


@Article{info:doi/10.2196/29511,
author="Commiskey, Patricia
and Armstrong, W. April
and Coker, R. Tumaini
and Dorsey, Ray Earl
and Fortney, C. John
and Gaines, J. Kenneth
and Gibbons, M. Brittany
and Nguyen, Q. Huong
and Singla, R. Daisy
and Szigethy, Eva
and Krupinski, A. Elizabeth",
title="A Blueprint for the Conduct of Large, Multisite Trials in Telemedicine",
journal="J Med Internet Res",
year="2021",
month="Sep",
day="20",
volume="23",
number="9",
pages="e29511",
keywords="telemedicine trials",
keywords="randomized trials",
keywords="challenges",
keywords="multisite",
keywords="mobile phone",
doi="10.2196/29511",
url="https://www.jmir.org/2021/9/e29511",
url="http://www.ncbi.nlm.nih.gov/pubmed/34542417"
}


@Article{info:doi/10.2196/27547,
author="Morgado Areia, Carlos
and Santos, Mauro
and Vollam, Sarah
and Pimentel, Marco
and Young, Louise
and Roman, Cristian
and Ede, Jody
and Piper, Philippa
and King, Elizabeth
and Gustafson, Owen
and Harford, Mirae
and Shah, Akshay
and Tarassenko, Lionel
and Watkinson, Peter",
title="A Chest Patch for Continuous Vital Sign Monitoring: Clinical Validation Study During Movement and Controlled Hypoxia",
journal="J Med Internet Res",
year="2021",
month="Sep",
day="15",
volume="23",
number="9",
pages="e27547",
keywords="clinical validation",
keywords="chest patch",
keywords="vital signs",
keywords="remote monitoring",
keywords="wearable",
keywords="heart rate",
keywords="respiratory rate",
abstract="Background: The standard of care in general wards includes periodic manual measurements, with the data entered into track-and-trigger charts, either on paper or electronically. Wearable devices may support health care staff, improve patient safety, and promote early deterioration detection in the interval between periodic measurements. However, regulatory standards for ambulatory cardiac monitors estimating heart rate (HR) and respiratory rate (RR) do not specify performance criteria during patient movement or clinical conditions in which the patient's oxygen saturation varies. Therefore, further validation is required before clinical implementation and deployment of any wearable system that provides continuous vital sign measurements. Objective: The objective of this study is to determine the agreement between a chest-worn patch (VitalPatch) and a gold standard reference device for HR and RR measurements during movement and gradual desaturation (modeling a hypoxic episode) in a controlled environment. Methods: After the VitalPatch and gold standard devices (Philips MX450) were applied, participants performed different movements in seven consecutive stages: at rest, sit-to-stand, tapping, rubbing, drinking, turning pages, and using a tablet. Hypoxia was then induced, and the participants' oxygen saturation gradually reduced to 80\% in a controlled environment. The primary outcome measure was accuracy, defined as the mean absolute error (MAE) of the VitalPatch estimates when compared with HR and RR gold standards (3-lead electrocardiography and capnography, respectively). We defined these as clinically acceptable if the rates were within 5 beats per minute for HR and 3 respirations per minute (rpm) for RR. Results: Complete data sets were acquired for 29 participants. In the movement phase, the HR estimates were within prespecified limits for all movements. For RR, estimates were also within the acceptable range, with the exception of the sit-to-stand and turning page movements, showing an MAE of 3.05 (95\% CI 2.48-3.58) rpm and 3.45 (95\% CI 2.71-4.11) rpm, respectively. For the hypoxia phase, both HR and RR estimates were within limits, with an overall MAE of 0.72 (95\% CI 0.66-0.78) beats per minute and 1.89 (95\% CI 1.75-2.03) rpm, respectively. There were no significant differences in the accuracy of HR and RR estimations between normoxia (?90\%), mild (89.9\%-85\%), and severe hypoxia (<85\%). Conclusions: The VitalPatch was highly accurate throughout both the movement and hypoxia phases of the study, except for RR estimation during the two types of movements. This study demonstrated that VitalPatch can be safely tested in clinical environments to support earlier detection of cardiorespiratory deterioration. Trial Registration: ISRCTN Registry ISRCTN61535692; https://www.isrctn.com/ISRCTN61535692 ",
doi="10.2196/27547",
url="https://www.jmir.org/2021/9/e27547",
url="http://www.ncbi.nlm.nih.gov/pubmed/34524087"
}


@Article{info:doi/10.2196/25797,
author="Desveaux, Laura
and Budhwani, Suman
and Stamenova, Vess
and Bhattacharyya, Onil
and Shaw, James
and Bhatia, Sacha R.",
title="Closing the Virtual Gap in Health Care: A Series of Case Studies Illustrating the Impact of Embedding Evaluation Alongside System Initiatives",
journal="J Med Internet Res",
year="2021",
month="Sep",
day="3",
volume="23",
number="9",
pages="e25797",
keywords="virtual care",
keywords="primary care",
keywords="embedded research",
keywords="implementation",
keywords="knowledge exchange",
keywords="health policy",
doi="10.2196/25797",
url="https://www.jmir.org/2021/9/e25797",
url="http://www.ncbi.nlm.nih.gov/pubmed/34477560"
}


@Article{info:doi/10.2196/24402,
author="Li, Qiaoqin
and Liu, Yongguo
and Zhu, Jiajing
and Chen, Zhi
and Liu, Lang
and Yang, Shangming
and Zhu, Guanyi
and Zhu, Bin
and Li, Juan
and Jin, Rongjiang
and Tao, Jing
and Chen, Lidian",
title="Upper-Limb Motion Recognition Based on Hybrid Feature Selection: Algorithm Development and Validation",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Sep",
day="2",
volume="9",
number="9",
pages="e24402",
keywords="feature selection",
keywords="inertial measurement unit",
keywords="motion recognition",
keywords="rehabilitation exercises",
keywords="machine learning",
abstract="Background: For rehabilitation training systems, it is essential to automatically record and recognize exercises, especially when more than one type of exercise is performed without a predefined sequence. Most motion recognition methods are based on feature engineering and machine learning algorithms. Time-domain and frequency-domain features are extracted from original time series data collected by sensor nodes. For high-dimensional data, feature selection plays an important role in improving the performance of motion recognition. Existing feature selection methods can be categorized into filter and wrapper methods. Wrapper methods usually achieve better performance than filter methods; however, in most cases, they are computationally intensive, and the feature subset obtained is usually optimized only for the specific learning algorithm. Objective: This study aimed to provide a feature selection method for motion recognition of upper-limb exercises and improve the recognition performance. Methods: Motion data from 5 types of upper-limb exercises performed by 21 participants were collected by a customized inertial measurement unit (IMU) node. A total of 60 time-domain and frequency-domain features were extracted from the original sensor data. A hybrid feature selection method by combining filter and wrapper methods (FESCOM) was proposed to eliminate irrelevant features for motion recognition of upper-limb exercises. In the filter stage, candidate features were first selected from the original feature set according to the significance for motion recognition. In the wrapper stage, k-nearest neighbors (kNN), Na{\"i}ve Bayes (NB), and random forest (RF) were evaluated as the wrapping components to further refine the features from the candidate feature set. The performance of the proposed FESCOM method was verified using experiments on motion recognition of upper-limb exercises and compared with the traditional wrapper method. Results: Using kNN, NB, and RF as the wrapping components, the classification error rates of the proposed FESCOM method were 1.7\%, 8.9\%, and 7.4\%, respectively, and the feature selection time in each iteration was 13 seconds, 71 seconds, and 541 seconds, respectively. Conclusions: The experimental results demonstrated that, in the case of 5 motion types performed by 21 healthy participants, the proposed FESCOM method using kNN and NB as the wrapping components achieved better recognition performance than the traditional wrapper method. The FESCOM method dramatically reduces the search time in the feature selection process. The results also demonstrated that the optimal number of features depends on the classifier. This approach serves to improve feature selection and classification algorithm selection for upper-limb motion recognition based on wearable sensor data, which can be extended to motion recognition of more motion types and participants. ",
doi="10.2196/24402",
url="https://mhealth.jmir.org/2021/9/e24402",
url="http://www.ncbi.nlm.nih.gov/pubmed/34473067"
}


@Article{info:doi/10.2196/30480,
author="Saliasi, Ina
and Martinon, Prescilla
and Darlington, Emily
and Smentek, Colette
and Tardivo, Delphine
and Bourgeois, Denis
and Dussart, Claude
and Carrouel, Florence
and Fraticelli, Laurie",
title="Promoting Health via mHealth Applications Using a French Version of the Mobile App Rating Scale: Adaptation and Validation Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Aug",
day="31",
volume="9",
number="8",
pages="e30480",
keywords="mobile health apps",
keywords="eHealth",
keywords="Mobile App Rating Scale",
keywords="MARS",
keywords="quality assessment tool",
keywords="rating scale evolution",
keywords="validation",
keywords="mHealth",
keywords="mHealth applications",
keywords="health applications",
keywords="mobile health",
keywords="digital health",
keywords="digital health tools",
keywords="application validation",
abstract="Background: In the recent decades, the number of apps promoting health behaviors and health-related strategies and interventions has increased alongside the number of smartphone users. Nevertheless, the validity process for measuring and reporting app quality remains unsatisfactory for health professionals and end users and represents a public health concern. The Mobile Application Rating Scale (MARS) is a tool validated and widely used in the scientific literature to evaluate and compare mHealth app functionalities. However, MARS is not adapted to the French culture nor to the language. Objective: This study aims to translate, adapt, and validate the equivalent French version of MARS (ie, MARS-F). Methods: The original MARS was first translated to French by two independent bilingual scientists, and their common version was blind back-translated twice by two native English speakers, culminating in a final well-established MARS-F. Its comprehensibility was then evaluated by 6 individuals (3 researchers and 3 nonacademics), and the final MARS-F version was created. Two bilingual raters independently completed the evaluation of 63 apps using MARS and MARS-F. Interrater reliability was assessed using intraclass correlation coefficients. In addition, internal consistency and validity of both scales were assessed. Mokken scale analysis was used to investigate the scalability of both MARS and MARS-F. Results: MARS-F had a good alignment with the original MARS, with properties comparable between the two scales. The correlation coefficients (r) between the corresponding dimensions of MARS and MARS-F ranged from 0.97 to 0.99. The internal consistencies of the MARS-F dimensions engagement ($\omega$=0.79), functionality ($\omega$=0.79), esthetics ($\omega$=0.78), and information quality ($\omega$=0.61) were acceptable and that for the overall MARS score ($\omega$=0.86) was good. Mokken scale analysis revealed a strong scalability for MARS (Loevinger H=0.37) and a good scalability for MARS-F (H=0.35). Conclusions: MARS-F is a valid tool, and it would serve as a crucial aid for researchers, health care professionals, public health authorities, and interested third parties, to assess the quality of mHealth apps in French-speaking countries. ",
doi="10.2196/30480",
url="https://mhealth.jmir.org/2021/8/e30480",
url="http://www.ncbi.nlm.nih.gov/pubmed/34463623"
}


@Article{info:doi/10.2196/28232,
author="Guest, L. Jodie
and Adam, Elizabeth
and Lucas, L. Iaah
and Chandler, J. Cristian
and Filipowicz, Rebecca
and Luisi, Nicole
and Gravens, Laura
and Leung, Kingsley
and Chavanduka, Tanaka
and Bonar, E. Erin
and Bauermeister, A. Jose
and Stephenson, Rob
and Sullivan, S. Patrick",
title="Methods for Authenticating Participants in Fully Web-Based Mobile App Trials from the iReach Project: Cross-sectional Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Aug",
day="31",
volume="9",
number="8",
pages="e28232",
keywords="HIV",
keywords="mHealth",
keywords="recruitment",
keywords="fraud",
keywords="adolescent MSM",
keywords="prevention",
keywords="MSM",
keywords="RCT",
keywords="enrollment",
keywords="data authentication",
keywords="data quality",
keywords="methods",
keywords="participants",
abstract="Background: Mobile health apps are important interventions that increase the scale and reach of prevention services, including HIV testing and prevention counseling, pre-exposure prophylaxis, condom distribution, and education, of which all are required to decrease HIV incidence rates. The use of these web-based apps as well as fully web-based intervention trials can be challenged by the need to remove fraudulent or duplicate entries and authenticate unique trial participants before randomization to protect the integrity of the sample and trial results. It is critical to ensure that the data collected through this modality are valid and reliable. Objective: The aim of this study is to discuss the electronic and manual authentication strategies for the iReach randomized controlled trial that were used to monitor and prevent fraudulent enrollment. Methods: iReach is a randomized controlled trial that focused on same-sex attracted, cisgender males (people assigned male at birth who identify as men) aged 13-18 years in the United States and on enrolling people of color and those in rural communities. The data were evaluated by identifying possible duplications in enrollment, identifying potentially fraudulent or ineligible participants through inconsistencies in the data collected at screening and survey data, and reviewing baseline completion times to avoid enrolling bots and those who did not complete the baseline questionnaire. Electronic systems flagged questionable enrollment. Additional manual reviews included the verification of age, IP addresses, email addresses, social media accounts, and completion times for surveys. Results: The electronic and manual strategies, including the integration of social media profiles, resulted in the identification and prevention of 624 cases of potential fraudulent, duplicative, or ineligible enrollment. A total of 79\% (493/624) of the potentially fraudulent or ineligible cases were identified through electronic strategies, thereby reducing the burden of manual authentication for most cases. A case study with a scenario, resolution, and authentication strategy response was included. Conclusions: As web-based trials are becoming more common, methods for handling suspicious enrollments that compromise data quality have become increasingly important for inclusion in protocols. International Registered Report Identifier (IRRID): RR2-10.2196/10174 ",
doi="10.2196/28232",
url="https://mhealth.jmir.org/2021/8/e28232",
url="http://www.ncbi.nlm.nih.gov/pubmed/34463631"
}


@Article{info:doi/10.2196/29381,
author="Azevedo, Salome
and Rodrigues, Cipriano Teresa
and Londral, Rita Ana",
title="Domains and Methods Used to Assess Home Telemonitoring Scalability: Systematic Review",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Aug",
day="19",
volume="9",
number="8",
pages="e29381",
keywords="telemonitoring",
keywords="scalability",
keywords="home telecare",
keywords="systematic review",
abstract="Background: The COVID-19 pandemic catalyzed the adoption of home telemonitoring to cope with social distancing challenges. Recent research on home telemonitoring demonstrated benefits concerning the capacity, patient empowerment, and treatment commitment of health care systems. Moreover, for some diseases, it revealed significant improvement in clinical outcomes. Nevertheless, when policy makers and practitioners decide whether to scale-up a technology-based health intervention from a research study to mainstream care delivery, it is essential to assess other relevant domains, such as its feasibility to be expanded under real-world conditions. Therefore, scalability assessment is critical, and it encompasses multiple domains to ensure population-wide access to the benefits of the growing technological potential for home telemonitoring services in health care. Objective: This systematic review aims to identify the domains and methods used in peer-reviewed research studies that assess the scalability of home telemonitoring--based interventions under real-world conditions. Methods: The authors followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) guidelines and used multiple databases (PubMed, Scopus, Web of Science, and EconLit). An integrative synthesis of the eligible studies was conducted to better explore each intervention and summarize relevant information concerning the target audience, intervention duration and setting, and type of technology. Each study design was classified based on the strength of its evidence. Lastly, the authors conducted narrative and thematic analyses to identify the domains, and qualitative and quantitative methods used to support scalability assessment. Results: This review evaluated 13 articles focusing on the potential of scaling up a home telemonitoring intervention. Most of the studies considered the following domains relevant for scalability assessment: problem (13), intervention (12), effectiveness (13), and costs and benefits (10). Although cost-effectiveness was the most common evaluation method, the authors identified seven additional cost analysis methods to evaluate the costs. Other domains were less considered, such as the sociopolitical context (2), workforce (4), and technological infrastructure (3). Researchers used different methodological approaches to assess the effectiveness, costs and benefits, fidelity, and acceptability. Conclusions: This systematic review suggests that when assessing scalability, researchers select the domains specifically related to the intervention while ignoring others related to the contextual, technological, and environmental factors, which are also relevant. Additionally, studies report using different methods to evaluate the same domain, which makes comparison difficult. Future work should address research on the minimum required domains to assess the scalability of remote telemonitoring services and suggest methods that allow comparison among studies to provide better support to decision makers during large-scale implementation. ",
doi="10.2196/29381",
url="https://mhealth.jmir.org/2021/8/e29381",
url="http://www.ncbi.nlm.nih.gov/pubmed/34420917"
}


@Article{info:doi/10.2196/23303,
author="Materia, T. Frank
and Smyth, M. Joshua",
title="Acceptability of Intervention Design Factors in mHealth Intervention Research: Experimental Factorial Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Jul",
day="26",
volume="9",
number="7",
pages="e23303",
keywords="mHealth",
keywords="acceptability",
keywords="implementation",
keywords="health behavior",
keywords="smartphone",
keywords="mobile phone",
keywords="wearable",
abstract="Background: With the growing interest in mobile health (mHealth), behavioral medicine researchers are increasingly conducting intervention studies that use mobile technology (eg, to support healthy behavior change). Such studies' scientific premises are often sound, yet there is a dearth of implementational data on which to base mHealth research methodologies. Notably, mHealth approaches must be designed to be acceptable to research participants to support meaningful engagement, but little empirical data about design factors influencing acceptability in such studies exist.  Objective: This study aims to evaluate the impact of two common design factors in mHealth intervention research---requiring multiple devices (eg, a study smartphone and wrist sensor) relative to requiring a single device and providing individually tailored feedback as opposed to generic content---on reported participant acceptability.  Methods: A diverse US adult convenience sample (female: 104/255, 40.8\%; White: 208/255, 81.6\%; aged 18-74 years) was recruited to complete a web-based experiment. A 2{\texttimes}2 factorial design (number of devices{\texttimes}nature of feedback) was used. A learning module explaining the necessary concepts (eg, behavior change interventions, acceptability, and tailored content) was presented, followed by four vignettes (representing each factorial cell) that were presented to participants in a random order. The vignettes each described a hypothetical mHealth intervention study featuring different combinations of the two design factors (requiring a single device vs multiple devices and providing tailored vs generic content). Participants rated acceptability dimensions (interest, benefit, enjoyment, utility, confidence, difficulty, and overall likelihood of participating) for each study presented.  Results: Reported interest, benefit, enjoyment, confidence in completing study requirements, and perceived utility were each significantly higher for studies featuring tailored (vs generic) content, and the overall estimate of the likelihood of participation was significantly higher. Ratings of interest, benefit, and perceived utility were significantly higher for studies requiring multiple devices (vs a single device); however, multiple device studies also had significantly lower ratings of confidence in completing study requirements, and participation was seen as more difficult and was associated with a lower estimated likelihood of participation. The two factors did not exhibit any evidence of statistical interactions in any of the outcomes tested.  Conclusions: The results suggest that potential research participants are sensitive to mHealth design factors. These mHealth intervention design factors may be important for initial perceptions of acceptability (in research or clinical settings). This, in turn, may be associated with participant (eg, self) selection processes, differential compliance with study or treatment processes, or retention over time. ",
doi="10.2196/23303",
url="https://mhealth.jmir.org/2021/7/e23303",
url="http://www.ncbi.nlm.nih.gov/pubmed/34309563"
}


@Article{info:doi/10.2196/17660,
author="Grau-Corral, Inmaculada
and Pantoja, Efrain Percy
and Grajales III, J. Francisco
and Kostov, Belchin
and Aragunde, Valent{\'i}n
and Puig-Soler, Marta
and Roca, Daria
and Couto, Elvira
and Sis{\'o}-Almirall, Antoni",
title="Assessing Apps for Health Care Workers Using the ISYScore-Pro Scale: Development and Validation Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Jul",
day="21",
volume="9",
number="7",
pages="e17660",
keywords="assessment",
keywords="mobile app",
keywords="mobile application",
keywords="mHealth",
keywords="health care professionals",
keywords="mobile application rating scale",
keywords="scale development",
abstract="Background: The presence of mobile phone and smart devices has allowed for the use of mobile apps to support patient care. However, there is a paucity in our knowledge regarding recommendations for mobile apps specific to health care professionals. Objective: The aim of this study is to establish a validated instrument to assess mobile apps for health care providers and health systems. Our objective is to create and validate a tool that evaluates mobile health apps aimed at health care professionals based on a trust, utility, and interest scale. Methods: A five-step methodology framework guided our approach. The first step consisted of building a scale to evaluate apps for health care professionals based on a literature review. This was followed with expert panel validation through a Delphi method of (rated) web-based questionnaires to empirically evaluate the inclusion and weight of the indicators identified through the literature review. Repeated iterations were followed until a consensus greater than 75\% was reached. The scale was then tested using a pilot to assess reliability. Interrater agreement of the pilot was measured using a weighted Cohen kappa. Results: Using a literature review, a first draft of the scale was developed. This was followed with two Delphi rounds between the local research group and an external panel of experts. After consensus was reached, the resulting ISYScore-Pro 17-item scale was tested. A total of 280 apps were originally identified for potential testing (140 iOS apps and 140 Android apps). These were categorized using International Statistical Classification of Diseases, Tenth Revision. Once duplicates were removed and they were downloaded to confirm their specificity to the target audience (ie, health care professionals), 66 remained. Of these, only 18 met the final criteria for inclusion in validating the ISYScore-Pro scale (interrator reliabilty 92.2\%; kappa 0.840, 95\% CI 0.834-0.847; P<.001). Conclusions: We have developed a reproducible methodology to objectively evaluate mobile health apps targeted to health care professionals and providers, the ISYScore-Pro scale. Future research will be needed to adapt the scale to other languages and across other domains (eg, legal compliance or security). ",
doi="10.2196/17660",
url="https://mhealth.jmir.org/2021/7/e17660",
url="http://www.ncbi.nlm.nih.gov/pubmed/34287216"
}


@Article{info:doi/10.2196/24278,
author="Cunha, Rodrigues Bruna Carolina
and Rodrigues, Hora Kamila Rios Da
and Zaine, Isabela
and da Silva, Nogueira Elias Adriano
and Viel, C{\'e}sar Caio
and Pimentel, Campos Maria Da Gra{\c{c}}a",
title="Experience Sampling and Programmed Intervention Method and System for Planning, Authoring, and Deploying Mobile Health Interventions: Design and Case Reports",
journal="J Med Internet Res",
year="2021",
month="Jul",
day="12",
volume="23",
number="7",
pages="e24278",
keywords="mobile apps",
keywords="mHealth",
keywords="intervention",
keywords="experience sampling",
keywords="method",
keywords="monitoring",
keywords="Experience Sampling and Programmed Intervention Method",
keywords="experience sampling method",
keywords="ecological momentary assessment",
keywords="just-in-time adaptive intervention",
abstract="Background: Health professionals initiating mobile health (mHealth) interventions may choose to adapt apps designed for other activities (eg, peer-to-peer communication) or to employ purpose-built apps specialized in the required intervention, or to exploit apps based on methods such as the experience sampling method (ESM). An alternative approach for professionals would be to create their own apps. While ESM-based methods offer important guidance, current systems do not expose their design at a level that promotes replicating, specializing, or extending their contributions. Thus, a twofold solution is required: a method that directs specialists in planning intervention programs themselves, and a model that guides specialists in adopting existing solutions and advises software developers on building new ones. Objective: The main objectives of this study are to design the Experience Sampling and Programmed Intervention Method (ESPIM), formulated toward supporting specialists in deploying mHealth interventions, and the ESPIM model, which guides health specialists in adopting existing solutions and advises software developers on how to build new ones. Another goal is to conceive and implement a software platform allowing specialists to be users who actually plan, create, and deploy interventions (ESPIM system). Methods: We conducted the design and evaluation of the ESPIM method and model alongside a software system comprising integrated web and mobile apps. A participatory design approach with stakeholders included early software prototype, predesign interviews with 12 health specialists, iterative design sustained by the software as an instance of the method's conceptual model, support to 8 real case studies, and postdesign interviews. Results: The ESPIM comprises (1) a list of requirements for mHealth experience sampling and intervention-based methods and systems, (2) a 4-dimension planning framework, (3) a 7-step-based process, and (4) an ontology-based conceptual model. The ESPIM system encompasses web and mobile apps. Eight long-term case studies, involving professionals in psychology, gerontology, computer science, speech therapy, and occupational therapy, show that the method allowed specialists to be actual users who plan, create, and deploy interventions via the associated system. Specialists' target users were parents of children diagnosed with autism spectrum disorder, older persons, graduate and undergraduate students, children (age 8-12), and caregivers of older persons. The specialists reported being able to create and conduct their own studies without modifying their original design. A qualitative evaluation of the ontology-based conceptual model showed its compliance to the functional requirements elicited. Conclusions: The ESPIM method succeeds in supporting specialists in planning, authoring, and deploying mobile-based intervention programs when employed via a software system designed and implemented according to its conceptual model. The ESPIM ontology--based conceptual model exposes the design of systems involving active or passive sampling interventions. Such exposure supports the evaluation, implementation, adaptation, or extension of new or existing systems. ",
doi="10.2196/24278",
url="https://www.jmir.org/2021/7/e24278",
url="http://www.ncbi.nlm.nih.gov/pubmed/34255652"
}


@Article{info:doi/10.2196/19245,
author="Domingos, C{\'e}lia
and Costa, Soares Patr{\'i}cio
and Santos, Correia Nadine
and P{\^e}go, Miguel Jos{\'e}",
title="European Portuguese Version of the User Satisfaction Evaluation Questionnaire (USEQ): Transcultural Adaptation and Validation Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Jun",
day="29",
volume="9",
number="6",
pages="e19245",
keywords="satisfaction",
keywords="usability",
keywords="reliability",
keywords="validity",
keywords="seniors",
keywords="elderly",
keywords="technology",
keywords="wearables",
abstract="Background: Wearable activity trackers have the potential to encourage users to adopt healthier lifestyles by tracking daily health information. However, usability is a critical factor in technology adoption. Older adults may be more resistant to accepting novel technologies. Understanding the difficulties that older adults face when using activity trackers may be useful for implementing strategies to promote their use. Objective: The purpose of this study was to conduct a transcultural adaptation of the User Satisfaction Evaluation Questionnaire (USEQ) into European Portuguese and validate the adapted questionnaire. Additionally, we aimed to provide information about older adults' satisfaction regarding the use of an activity tracker (Xiaomi Mi Band 2). Methods: The USEQ was translated following internationally accepted guidelines. The psychometric evaluation of the final version of the translated USEQ was assessed based on structural validity using exploratory and confirmatory factor analyses. Construct validity was examined using divergent and discriminant validity analysis, and internal consistency was evaluated using Cronbach $\alpha$ and McDonald $\omega$ coefficients. Results: A total of 110 older adults completed the questionnaire. Confirmatory factor analysis supported the conceptual unidimensionality of the USEQ ($\chi$24=7.313, P=.12, comparative fit index=0.973, Tucker-Lewis index=0.931, goodness of fit index=0.977, root mean square error of approximation=0.087, standardized root mean square residual=0.038). The internal consistency showed acceptable reliability (Cronbach $\alpha$=.677, McDonald $\omega$=0.722). Overall, 90\% of the participants reported excellent satisfaction with the Xiaomi Mi Band 2. Conclusions: The findings support the use of this translated USEQ as a valid and reliable tool for measuring user satisfaction with wearable activity trackers in older adults, with psychometric properties consistent with the original version. ",
doi="10.2196/19245",
url="https://mhealth.jmir.org/2021/6/e19245",
url="http://www.ncbi.nlm.nih.gov/pubmed/34185018"
}


@Article{info:doi/10.2196/27105,
author="Lau, Nancy
and O'Daffer, Alison
and Yi-Frazier, Joyce
and Rosenberg, R. Abby",
title="Goldilocks and the Three Bears: A Just-Right Hybrid Model to Synthesize the Growing Landscape of Publicly Available Health-Related Mobile Apps",
journal="J Med Internet Res",
year="2021",
month="Jun",
day="7",
volume="23",
number="6",
pages="e27105",
keywords="telemedicine",
keywords="smartphone",
keywords="mobile phones",
keywords="mHealth",
keywords="mobile apps",
keywords="health services",
doi="10.2196/27105",
url="https://www.jmir.org/2021/6/e27105",
url="http://www.ncbi.nlm.nih.gov/pubmed/34096868"
}


@Article{info:doi/10.2196/19536,
author="Dani{\"e}ls, M. Naomi E.
and Hochstenbach, J. Laura M.
and van Zelst, Catherine
and van Bokhoven, A. Marloes
and Delespaul, G. Philippe A. E.
and Beurskens, M. Anna J. H.",
title="Factors That Influence the Use of Electronic Diaries in Health Care: Scoping Review",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Jun",
day="1",
volume="9",
number="6",
pages="e19536",
keywords="compliance",
keywords="delivery of health care",
keywords="diary",
keywords="ecological momentary assessment",
keywords="intention",
keywords="motivation",
keywords="scoping review",
abstract="Background: A large number of people suffer from psychosocial or physical problems. Adequate strategies to alleviate needs are scarce or lacking. Symptom variation can offer insights into personal profiles of coping and resilience (detailed functional analyses). Hence, diaries are used to report mood and behavior occurring in daily life. To reduce inaccuracies, biases, and noncompliance with paper diaries, a shift to electronic diaries has occurred. Although these diaries are increasingly used in health care, information is lacking about what determines their use. Objective: The aim of this study was to map the existing empirical knowledge and gaps concerning factors that influence the use of electronic diaries, defined as repeated recording of psychosocial or physical data lasting at least one week using a smartphone or a computer, in health care. Methods: A scoping review of the literature published between January 2000 and December 2018 was conducted using queries in PubMed and PsycInfo databases. English or Dutch publications based on empirical data about factors that influence the use of electronic diaries for psychosocial or physical purposes in health care were included. Both databases were screened, and findings were summarized using a directed content analysis organized by the Consolidated Framework for Implementation Research (CFIR). Results: Out of 3170 articles, 22 studies were selected for qualitative synthesis. Eleven themes were determined in the CFIR categories of intervention, user characteristics, and process. No information was found for the CFIR categories inner (eg, organizational resources, innovation climate) and outer (eg, external policies and incentives, pressure from competitors) settings. Reminders, attractive designs, tailored and clear data visualizations (intervention), smartphone experience, and intrinsic motivation to change behavior (user characteristics) could influence the use of electronic diaries. During the implementation process, attention should be paid to both theoretical and practical training. Conclusions: Design aspects, user characteristics, and training and instructions determine the use of electronic diaries in health care. It is remarkable that there were no empirical data about factors related to embedding electronic diaries in daily clinical practice. More research is needed to better understand influencing factors for optimal electronic diary use. ",
doi="10.2196/19536",
url="https://mhealth.jmir.org/2021/6/e19536",
url="http://www.ncbi.nlm.nih.gov/pubmed/34061036"
}


@Article{info:doi/10.2196/21763,
author="Shaw, Peter Matthew
and Satchell, Paul Liam
and Thompson, Steve
and Harper, Thomas Ed
and Balsalobre-Fern{\'a}ndez, Carlos
and Peart, James Daniel",
title="Smartphone and Tablet Software Apps to Collect Data in Sport and Exercise Settings: Cross-sectional International Survey",
journal="JMIR Mhealth Uhealth",
year="2021",
month="May",
day="13",
volume="9",
number="5",
pages="e21763",
keywords="mobile apps",
keywords="sports",
keywords="smartphone",
keywords="mobile phone",
keywords="questionnaire",
keywords="survey",
abstract="Background: Advances in smartphone technology have facilitated an increase in the number of commercially available smartphone and tablet apps that enable the collection of physiological and biomechanical variables typically monitored in sport and exercise settings. Currently, it is not fully understood whether individuals collect data using mobile devices and tablets, independent of additional hardware, in their practice. Objective: This study aims to explore the use of smartphone and tablet software apps to collect data by individuals working in various sport and exercise settings, such as sports coaching, strength and conditioning, and personal training. Methods: A total of 335 practitioners completed an electronic questionnaire that surveyed their current training practices, with a focus on 2 areas: type of data collection and perceptions of reliability and validity regarding app use. An 18-item questionnaire, using a 5-point Likert scale, evaluated the perception of app use. Results: A total of 204 respondents reported using apps to directly collect data, with most of them (196/335, 58.5\%) collecting biomechanical data, and 41.2\% (138/335) respondents reported using at least one evidence-based app. A binomial general linear model determined that evidence accessibility ($\beta$=.35, 95\% CI 0.04-0.67; P=.03) was significantly related to evidence-based app use. Age ($\beta$=?.03, 95\% CI ?0.06 to 0.00; P=.03) had a significant negative effect on evidence-based app use. Conclusions: This study demonstrates that practitioners show a greater preference for using smartphones and tablet devices to collect biomechanical data such as sprint velocity and jump performance variables. When it is easier to access information on the quality of apps, practitioners are more likely to use evidence-based apps. App developers should seek independent research to validate their apps. In addition, app developers should seek to provide clear signposting to the scientific support of their software in alternative ways. ",
doi="10.2196/21763",
url="https://mhealth.jmir.org/2021/5/e21763",
url="http://www.ncbi.nlm.nih.gov/pubmed/33983122"
}


@Article{info:doi/10.2196/20966,
author="Martinato, Matteo
and Lorenzoni, Giulia
and Zanchi, Tommaso
and Bergamin, Alessia
and Buratin, Alessia
and Azzolina, Danila
and Gregori, Dario",
title="Usability and Accuracy of a Smartwatch for the Assessment of Physical Activity in the Elderly Population: Observational Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="May",
day="5",
volume="9",
number="5",
pages="e20966",
keywords="wearable devices",
keywords="elderly",
keywords="physical activity",
keywords="smartwatches",
abstract="Background: Regular physical activity (PA) contributes to the primary and secondary prevention of several chronic diseases and reduces the risk of premature death. Physical inactivity is a modifiable risk factor for cardiovascular disease and a variety of chronic disorders such as diabetes, obesity,  hypertension, bone and joint diseases (eg, osteoporosis and osteoarthritis), depression, and colon and breast cancer. Population aging and the related increase in chronic diseases have a major impact on the health care systems of most Western countries and will produce an even more significant effect in the future. Monitoring PA is a valuable method of determining whether people are performing enough PA so as to prevent chronic diseases or are showing early symptoms of those diseases. Objective: The aim of this study was to estimate the accuracy of wearable devices in quantifying the PA of elderly people in a real-life setting. Methods: Participants aged 70 to 90 years with the ability to walk safely without any walking aid for at least 300 meters, who had no walking disabilities or episodes of falling while walking in the last 12 months, were asked to walk 150 meters at their preferred pace wearing a v{\'i}voactive HR device (Garmin Ltd) and actual steps were monitored and tallied by a researcher using a hand-tally counter to assess the performance of the device at a natural speed. A Bland-Altman plot was used to analyze the difference between manually counted steps and wearable device--measured steps. The intraclass correlation coefficient (ICC) was computed (with a 95\% confidence interval) between step measurements. The generalized linear mixed-model (GLMM) ICCs were estimated, providing a random effect term (random intercept) for the individual measurements (gold standard and device). Both adjusted and conditional ICCs were computed for the GLMM models considering separately the effect of age, sex, BMI, and obesity. Analyses were performed using R software (R Foundation for Statistical Computing) with the rms package. Results: A total of 23 females and 26 males were enrolled in the study. The median age of the participants was 75 years. The Bland-Altman plot revealed that, excluding one observation, all differences across measurements were in the confidence bounds, demonstrating the substantial agreement between the step count measurements. The results were confirmed by an ICC equal to .98 (.96-.99), demonstrating excellent agreement between the two sets of measurements. Conclusions: The level of accuracy of wearable devices in quantifying the PA of elderly people in a real-life setting that was found in this study supports the idea of considering wrist-wearable nonmedical devices (widely available in nonspecialized stores) as reliable tools. Both health care professionals and informal caregivers could monitor the level of PA of their patients. ",
doi="10.2196/20966",
url="https://mhealth.jmir.org/2021/5/e20966",
url="http://www.ncbi.nlm.nih.gov/pubmed/33949953"
}


@Article{info:doi/10.2196/23681,
author="Davoudi, Anis
and Mardini, T. Mamoun
and Nelson, David
and Albinali, Fahd
and Ranka, Sanjay
and Rashidi, Parisa
and Manini, M. Todd",
title="The Effect of Sensor Placement and Number on Physical Activity Recognition and Energy Expenditure Estimation in Older Adults: Validation Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="May",
day="3",
volume="9",
number="5",
pages="e23681",
keywords="human activity recognition",
keywords="machine learning",
keywords="wearable accelerometers",
keywords="mobile phone",
abstract="Background: Research has shown the feasibility of human activity recognition using wearable accelerometer devices. Different studies have used varying numbers and placements for data collection using sensors. Objective: This study aims to compare accuracy performance between multiple and variable placements of accelerometer devices in categorizing the type of physical activity and corresponding energy expenditure in older adults. Methods: In total, 93 participants (mean age 72.2 years, SD 7.1) completed a total of 32 activities of daily life in a laboratory setting. Activities were classified as sedentary versus nonsedentary, locomotion versus nonlocomotion, and lifestyle versus nonlifestyle activities (eg, leisure walk vs computer work). A portable metabolic unit was worn during each activity to measure metabolic equivalents (METs). Accelerometers were placed on 5 different body positions: wrist, hip, ankle, upper arm, and thigh. Accelerometer data from each body position and combinations of positions were used to develop random forest models to assess activity category recognition accuracy and MET estimation. Results: Model performance for both MET estimation and activity category recognition were strengthened with the use of additional accelerometer devices. However, a single accelerometer on the ankle, upper arm, hip, thigh, or wrist had only a 0.03-0.09 MET increase in prediction error compared with wearing all 5 devices. Balanced accuracy showed similar trends with slight decreases in balanced accuracy for the detection of locomotion (balanced accuracy decrease range 0-0.01), sedentary (balanced accuracy decrease range 0.05-0.13), and lifestyle activities (balanced accuracy decrease range 0.04-0.08) compared with all 5 placements. The accuracy of recognizing activity categories increased with additional placements (accuracy decrease range 0.15-0.29). Notably, the hip was the best single body position for MET estimation and activity category recognition. Conclusions: Additional accelerometer devices slightly enhance activity recognition accuracy and MET estimation in older adults. However, given the extra burden of wearing additional devices, single accelerometers with appropriate placement appear to be sufficient for estimating energy expenditure and activity category recognition in older adults. ",
doi="10.2196/23681",
url="https://mhealth.jmir.org/2021/5/e23681",
url="http://www.ncbi.nlm.nih.gov/pubmed/33938809"
}


@Article{info:doi/10.2196/19163,
author="Cohn, F. Wendy
and Canan, E. Chelsea
and Knight, Sarah
and Waldman, Lena Ava
and Dillingham, Rebecca
and Ingersoll, Karen
and Schexnayder, Julie
and Flickinger, E. Tabor",
title="An Implementation Strategy to Expand Mobile Health Use in HIV Care Settings: Rapid Evaluation Study Using the Consolidated Framework for Implementation Research",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Apr",
day="28",
volume="9",
number="4",
pages="e19163",
keywords="mHealth",
keywords="smartphone",
keywords="mobile health",
keywords="implementation strategy",
keywords="implementation science",
keywords="Consolidated Framework for Implementation Research",
keywords="HIV care engagement",
keywords="viral suppression",
abstract="Background: Mobile health (mHealth) apps can provide support to people living with a chronic disease by offering resources for communication, self-management, and social support. PositiveLinks (PL) is a clinic-deployed mHealth app designed to improve the health of people with HIV. In a pilot study, PL users experienced considerable improvements in care engagement and viral load suppression. To promote its expansion to other HIV clinics, we developed an implementation strategy consisting of training resources and on-demand program support. Objective: The objective of our study was to conduct an interim analysis of the barriers and facilitators to PL implementation at early adopting sites to guide optimization of our implementation strategy. Methods: Semistructured interviews with stakeholders at PL expansion sites were conducted. Analysis of interviews identified facilitators and barriers that were mapped to 22 constructs of the Consolidated Framework for Implementation Research (CFIR). The purpose of the analysis was to identify the facilitators and barriers to PL implementation in order to adapt the PL implementation strategy. Four Ryan White HIV clinics were included. Interviews were conducted with one health care provider, two clinic managers, and five individuals who coordinated site PL activities. Results: Ten common facilitators and eight common barriers were identified. Facilitators to PL implementation included PL's fit with patient and clinic needs, PL training resources, and sites' early engagement with their information technology personnel. Most barriers were specific to mHealth, including access to Wi-Fi networks, maintaining patient smartphone access, patient privacy concerns, and lack of clarity on how to obtain approvals for mHealth use. Conclusions: The CFIR is a useful framework for evaluating mHealth interventions. Although PL training resources were viewed favorably, we identified important barriers to PL implementation in a sample of Ryan White clinics. This enabled our team to expand guidance on identifying information technology stakeholders and procuring and managing mobile resources. Ongoing evaluation results continue to inform improvements to the PL implementation strategy, facilitating PL access for future expansion sites. ",
doi="10.2196/19163",
url="https://mhealth.jmir.org/2021/4/e19163",
url="http://www.ncbi.nlm.nih.gov/pubmed/33908893"
}


@Article{info:doi/10.2196/26471,
author="Mir{\'o}, Jordi
and Llorens-Vernet, Pere",
title="Assessing the Quality of Mobile Health-Related Apps: Interrater Reliability Study of Two Guides",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Apr",
day="19",
volume="9",
number="4",
pages="e26471",
keywords="mHealth",
keywords="mobile health",
keywords="mobile apps",
keywords="evaluation studies, rating",
keywords="interrater reliability",
keywords="MARS",
keywords="MAG",
abstract="Background: There is a huge number of health-related apps available, and the numbers are growing fast. However, many of them have been developed without any kind of quality control. In an attempt to contribute to the development of high-quality apps and enable existing apps to be assessed, several guides have been developed. Objective: The main aim of this study was to study the interrater reliability of a new guide --- the Mobile App Development and Assessment Guide (MAG) --- and compare it with one of the most used guides in the field, the Mobile App Rating Scale (MARS). Moreover, we also focused on whether the interrater reliability of the measures is consistent across multiple types of apps and stakeholders. Methods: In order to study the interrater reliability of the MAG and MARS, we evaluated the 4 most downloaded health apps for chronic health conditions in the medical category of IOS and Android devices (ie, App Store and Google Play). A group of 8 reviewers, representative of individuals that would be most knowledgeable and interested in the use and development of health-related apps and including different types of stakeholders such as clinical researchers, engineers, health care professionals, and end users as potential patients, independently evaluated the quality of the apps using the MAG and MARS. We calculated the Krippendorff alpha for every category in the 2 guides, for each type of reviewer and every app, separately and combined, to study the interrater reliability. Results: Only a few categories of the MAG and MARS demonstrated a high interrater reliability. Although the MAG was found to be superior, there was considerable variation in the scores between the different types of reviewers. The categories with the highest interrater reliability in MAG were ``Security'' ($\alpha$=0.78) and ``Privacy'' ($\alpha$=0.73). In addition, 2 other categories, ``Usability'' and ``Safety,'' were very close to compliance (health care professionals: $\alpha$=0.62 and 0.61, respectively). The total interrater reliability of the MAG (ie, for all categories) was 0.45, whereas the total interrater reliability of the MARS was 0.29. Conclusions: This study shows that some categories of MAG have significant interrater reliability. Importantly, the data show that the MAG scores are better than the ones provided by the MARS, which is the most commonly used guide in the area. However, there is great variability in the responses, which seems to be associated with subjective interpretation by the reviewers. ",
doi="10.2196/26471",
url="https://mhealth.jmir.org/2021/4/e26471",
url="http://www.ncbi.nlm.nih.gov/pubmed/33871376"
}


@Article{info:doi/10.2196/24604,
author="Zhang, Yuezhou
and Folarin, A. Amos
and Sun, Shaoxiong
and Cummins, Nicholas
and Bendayan, Rebecca
and Ranjan, Yatharth
and Rashid, Zulqarnain
and Conde, Pauline
and Stewart, Callum
and Laiou, Petroula
and Matcham, Faith
and White, M. Katie
and Lamers, Femke
and Siddi, Sara
and Simblett, Sara
and Myin-Germeys, Inez
and Rintala, Aki
and Wykes, Til
and Haro, Maria Josep
and Penninx, WJH Brenda
and Narayan, A. Vaibhav
and Hotopf, Matthew
and Dobson, JB Richard
and ",
title="Relationship Between Major Depression Symptom Severity and Sleep Collected Using a Wristband Wearable Device: Multicenter Longitudinal Observational Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Apr",
day="12",
volume="9",
number="4",
pages="e24604",
keywords="mobile health (mHealth)",
keywords="mental health",
keywords="depression",
keywords="sleep",
keywords="wearable device",
keywords="monitoring",
abstract="Background: Sleep problems tend to vary according to the course of the disorder in individuals with mental health problems. Research in mental health has associated sleep pathologies with depression. However, the gold standard for sleep assessment, polysomnography (PSG), is not suitable for long-term, continuous monitoring of daily sleep, and methods such as sleep diaries rely on subjective recall, which is qualitative and inaccurate. Wearable devices, on the other hand, provide a low-cost and convenient means to monitor sleep in home settings. Objective: The main aim of this study was to devise and extract sleep features from data collected using a wearable device and analyze their associations with depressive symptom severity and sleep quality as measured by the self-assessed Patient Health Questionnaire 8-item (PHQ-8). Methods: Daily sleep data were collected passively by Fitbit wristband devices, and depressive symptom severity was self-reported every 2 weeks by the PHQ-8. The data used in this paper included 2812 PHQ-8 records from 368 participants recruited from 3 study sites in the Netherlands, Spain, and the United Kingdom. We extracted 18 sleep features from Fitbit data that describe participant sleep in the following 5 aspects: sleep architecture, sleep stability, sleep quality, insomnia, and hypersomnia. Linear mixed regression models were used to explore associations between sleep features and depressive symptom severity. The z score was used to evaluate the significance of the coefficient of each feature. Results: We tested our models on the entire dataset and separately on the data of 3 different study sites. We identified 14 sleep features that were significantly (P<.05) associated with the PHQ-8 score on the entire dataset, among them awake time percentage (z=5.45, P<.001), awakening times (z=5.53, P<.001), insomnia (z=4.55, P<.001), mean sleep offset time (z=6.19, P<.001), and hypersomnia (z=5.30, P<.001) were the top 5 features ranked by z score statistics. Associations between sleep features and PHQ-8 scores varied across different sites, possibly due to differences in the populations. We observed that many of our findings were consistent with previous studies, which used other measurements to assess sleep, such as PSG and sleep questionnaires. Conclusions: We demonstrated that several derived sleep features extracted from consumer wearable devices show potential for the remote measurement of sleep as biomarkers of depression in real-world settings. These findings may provide the basis for the development of clinical tools to passively monitor disease state and trajectory, with minimal burden on the participant. ",
doi="10.2196/24604",
url="https://mhealth.jmir.org/2021/4/e24604",
url="http://www.ncbi.nlm.nih.gov/pubmed/33843591"
}


@Article{info:doi/10.2196/18534,
author="Staras, Stephanie
and Tauscher, S. Justin
and Rich, Natalie
and Samarah, Esaa
and Thompson, A. Lindsay
and Vinson, M. Michelle
and Muszynski, J. Michael
and Shenkman, A. Elizabeth",
title="Using a Clinical Workflow Analysis to Enhance eHealth Implementation Planning: Tutorial and Case Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Mar",
day="31",
volume="9",
number="3",
pages="e18534",
keywords="workflow",
keywords="implementation science",
keywords="primary care",
keywords="eHealth",
keywords="stakeholder engagement",
doi="10.2196/18534",
url="https://mhealth.jmir.org/2021/3/e18534",
url="http://www.ncbi.nlm.nih.gov/pubmed/33626016"
}


@Article{info:doi/10.2196/27232,
author="Wei{\ss}, Jan-Patrick
and Esdar, Moritz
and H{\"u}bner, Ursula",
title="Analyzing the Essential Attributes of Nationally Issued COVID-19 Contact Tracing Apps: Open-Source Intelligence Approach and Content Analysis",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Mar",
day="26",
volume="9",
number="3",
pages="e27232",
keywords="COVID-19",
keywords="contact tracing",
keywords="app",
keywords="protocol",
keywords="privacy",
keywords="assessment",
keywords="review",
keywords="surveillance",
keywords="monitoring",
keywords="design",
keywords="framework",
keywords="feature",
keywords="usage",
abstract="Background: Contact tracing apps are potentially useful tools for supporting national COVID-19 containment strategies. Various national apps with different technical design features have been commissioned and issued by governments worldwide. Objective: Our goal was to develop and propose an item set that was suitable for describing and monitoring nationally issued COVID-19 contact tracing apps. This item set could provide a framework for describing the key technical features of such apps and monitoring their use based on widely available information. Methods: We used an open-source intelligence approach (OSINT) to access a multitude of publicly available sources and collect data and information regarding the development and use of contact tracing apps in different countries over several months (from June 2020 to January 2021). The collected documents were then iteratively analyzed via content analysis methods. During this process, an initial set of subject areas were refined into categories for evaluation (ie, coherent topics), which were then examined for individual features. These features were paraphrased as items in the form of questions and applied to information materials from a sample of countries (ie, Brazil, China, Finland, France, Germany, Italy, Singapore, South Korea, Spain, and the United Kingdom [England and Wales]). This sample was purposefully selected; our intention was to include the apps of different countries from around the world and to propose a valid item set that can be relatively easily applied by using an OSINT approach. Results: Our OSINT approach and subsequent analysis of the collected documents resulted in the definition of the following five main categories and associated subcategories: (1) background information (open-source code, public information, and collaborators); (2) purpose and workflow (secondary data use and warning process design); (3) technical information (protocol, tracing technology, exposure notification system, and interoperability); (4) privacy protection (the entity of trust and anonymity); and (5) availability and use (release date and the number of downloads). Based on this structure, a set of items that constituted the evaluation framework were specified. The application of these items to the 10 selected countries revealed differences, especially with regard to the centralization of the entity of trust and the overall transparency of the apps' technical makeup. Conclusions: We provide a set of criteria for monitoring and evaluating COVID-19 tracing apps that can be easily applied to publicly issued information. The application of these criteria might help governments to identify design features that promote the successful, widespread adoption of COVID-19 tracing apps among target populations and across national boundaries. ",
doi="10.2196/27232",
url="https://mhealth.jmir.org/2021/3/e27232",
url="http://www.ncbi.nlm.nih.gov/pubmed/33724920"
}


@Article{info:doi/10.2196/23391,
author="Ponnada, Aditya
and Thapa-Chhetry, Binod
and Manjourides, Justin
and Intille, Stephen",
title="Measuring Criterion Validity of Microinteraction Ecological Momentary Assessment (Micro-EMA): Exploratory Pilot Study With Physical Activity Measurement",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Mar",
day="10",
volume="9",
number="3",
pages="e23391",
keywords="ecological momentary assessment (EMA)",
keywords="experience sampling",
keywords="physical activity",
keywords="smartwatch",
keywords="microinteractions",
keywords="criterion validity",
keywords="activity monitor",
keywords="$\mu$EMA",
abstract="Background: Ecological momentary assessment (EMA) is an in situ method of gathering self-report on behaviors using mobile devices. In typical phone-based EMAs, participants are prompted repeatedly with multiple-choice questions, often causing participation burden. Alternatively, microinteraction EMA (micro-EMA or $\mu$EMA) is a type of EMA where all the self-report prompts are single-question surveys that can be answered using a 1-tap glanceable microinteraction conveniently on a smartwatch. Prior work suggests that $\mu$EMA may permit a substantially higher prompting rate than EMA, yielding higher response rates and lower participation burden. This is achieved by ensuring $\mu$EMA prompt questions are quick and cognitively simple to answer. However, the validity of participant responses from $\mu$EMA self-report has not yet been formally assessed. Objective: In this pilot study, we explored the criterion validity of $\mu$EMA self-report on a smartwatch, using physical activity (PA) assessment as an example behavior of interest. Methods: A total of 17 participants answered 72 $\mu$EMA prompts each day for 1 week using a custom-built $\mu$EMA smartwatch app. At each prompt, they self-reported whether they were doing sedentary, light/standing, moderate/walking, or vigorous activities by tapping on the smartwatch screen. Responses were compared with a research-grade activity monitor worn on the dominant ankle simultaneously (and continuously) measuring PA. Results: Participants had an 87.01\% (5226/6006) $\mu$EMA completion rate and a 74.00\% (5226/7062) compliance rate taking an average of only 5.4 (SD 1.5) seconds to answer a prompt. When comparing $\mu$EMA responses with the activity monitor, we observed significantly higher (P<.001) momentary PA levels on the activity monitor when participants self-reported engaging in moderate+vigorous activities compared with sedentary or light/standing activities. The same comparison did not yield any significant differences in momentary PA levels as recorded by the activity monitor when the $\mu$EMA responses were randomly generated (ie, simulating careless taps on the smartwatch). Conclusions: For PA measurement, high-frequency $\mu$EMA self-report could be used to capture information that appears consistent with that of a research-grade continuous sensor for sedentary, light, and moderate+vigorous activity, suggesting criterion validity. The preliminary results show that participants were not carelessly answering $\mu$EMA prompts by randomly tapping on the smartwatch but were reporting their true behavior at that moment. However, more research is needed to examine the criterion validity of $\mu$EMA when measuring vigorous activities. ",
doi="10.2196/23391",
url="https://mhealth.jmir.org/2021/3/e23391",
url="http://www.ncbi.nlm.nih.gov/pubmed/33688843"
}


@Article{info:doi/10.2196/26702,
author="Hill, R. Jordan
and Harrington, B. Addison
and Adeoye, Philip
and Campbell, L. Noll
and Holden, J. Richard",
title="Going Remote---Demonstration and Evaluation of Remote Technology Delivery and Usability Assessment With Older Adults: Survey Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Mar",
day="4",
volume="9",
number="3",
pages="e26702",
keywords="COVID-19",
keywords="mobile usability testing",
keywords="usability inspection",
keywords="methods",
keywords="aging",
keywords="agile",
keywords="mobile phone",
abstract="Background: The COVID-19 pandemic necessitated ``going remote'' with the delivery, support, and assessment of a study intervention targeting older adults enrolled in a clinical trial. While remotely delivering and assessing technology is not new, there are few methods available in the literature that are proven to be effective with diverse populations, and none for older adults specifically.  Older adults comprise a diverse population, including in terms of their experience with and access to technology, making this a challenging endeavor. Objective: Our objective was to remotely deliver and conduct usability testing for a mobile health (mHealth) technology intervention for older adult participants enrolled in a clinical trial of the technology. This paper describes the methodology used, its successes, and its limitations. Methods: We developed a conceptual model for remote operations, called the Framework for Agile and Remote Operations (FAR Ops), that combined the general requirements for spaceflight operations with Agile project management processes to quickly respond to this challenge.  Using this framework, we iteratively created care packages that differed in their contents based on participant needs and were sent to study participants to deliver the study intervention---a medication management app---and assess its usability. Usability data were collected using the System Usability Scale (SUS) and a novel usability questionnaire developed to collect more in-depth data. Results: In the first 6 months of the project, we successfully delivered 21 care packages. We successfully designed and deployed a minimum viable product in less than 6 weeks, generally maintained a 2-week sprint cycle, and achieved a 40\% to 50\% return rate for both usability assessment instruments.  We hypothesize that lack of engagement due to the pandemic and our use of asynchronous communication channels contributed to the return rate of usability assessments being lower than desired.  We also provide general recommendations for performing remote usability testing with diverse populations based on the results of our work, including implementing screen sharing capabilities when possible, and determining participant preference for phone or email communications. Conclusions: The FAR Ops model allowed our team to adopt remote operations for our mHealth trial in response to interruptions from the COVID-19 pandemic. This approach can be useful for other research or practice-based projects under similar circumstances or to improve efficiency, cost, effectiveness, and participant diversity in general. In addition to offering a replicable approach, this paper tells the often-untold story of practical challenges faced by mHealth projects and practical strategies used to address them. Trial Registration: ClinicalTrials.gov NCT04121858; https://clinicaltrials.gov/ct2/show/NCT04121858 ",
doi="10.2196/26702",
url="https://mhealth.jmir.org/2021/3/e26702",
url="http://www.ncbi.nlm.nih.gov/pubmed/33606655"
}


@Article{info:doi/10.2196/17573,
author="Lee, Min-Kyung
and Lee, Young Da
and Ahn, Hong-Yup
and Park, Cheol-Young",
title="A Novel User Utility Score for Diabetes Management Using Tailored Mobile Coaching: Secondary Analysis of a Randomized Controlled Trial",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Feb",
day="24",
volume="9",
number="2",
pages="e17573",
keywords="type 2 diabetes",
keywords="mobile applications",
keywords="diabetes management",
keywords="patient engagement",
abstract="Background: Mobile health applications have been developed to support diabetes self-management, but their effectiveness could depend on patient engagement. Therefore, patient engagement must be examined through multifactorial tailored behavioral interventions from an individual perspective. Objective: This study aims to evaluate the usefulness of a novel user utility score (UUS) as a tool to measure patient engagement by using a mobile health application for diabetes management. Methods: We conducted a subanalysis of results from a 12-month randomized controlled trial of a tailored mobile coaching (TMC) system among insurance policyholders with type 2 diabetes. UUS was calculated as the sum of the scores for 4 major core components (range 0-8): frequency of self-monitoring blood glucose testing, dietary and exercise records, and message reading rate. We explored the association between UUS for the first 3 months and glycemic control over 12 months. In addition, we investigated the relationship of UUS with blood pressure, lipid profile, and self-report scales assessing diabetes self-management. Results: We divided 72 participants into 2 groups based on UUS for the first 3 months: UUS:0-4 (n=38) and UUS:5-8 (n=34). There was a significant between-group difference in glycated hemoglobin test (HbA1c) levels for the 12-months study period (P=.011). The HbA1c decrement at 12 months in the UUS:5-8 group was greater than that of the UUS:0-4 group [--0.92 (SD 1.24\%) vs --0.33 (SD 0.80\%); P=.049]. After adjusting for confounding factors, UUS was significantly associated with changes in HbA1c at 3, 6, and 12 months; the regression coefficients were --0.113 (SD 0.040; P=.006), --0.143 (SD 0.045; P=.002), and --0.136 (SD 0.052; P=.011), respectively. Change differences in other health outcomes between the 2 groups were not observed throughout a 12-month follow-up. Conclusions: UUS as a measure of patient engagement was associated with changes in HbA1c over the study period of the TMC system and could be used to predict improved glycemic control in diabetes self-management through mobile health interventions. Trial Registration: ClinicalTrial.gov NCT03033407; https://clinicaltrials.gov/ct2/show/NCT03033407 ",
doi="10.2196/17573",
url="https://mhealth.jmir.org/2021/2/e17573",
url="http://www.ncbi.nlm.nih.gov/pubmed/33625363"
}


@Article{info:doi/10.2196/20329,
author="Stalujanis, Esther
and Neufeld, Joel
and Glaus Stalder, Martina
and Belardi, Angelo
and Tegethoff, Marion
and Meinlschmidt, Gunther",
title="Induction of Efficacy Expectancies in an Ambulatory Smartphone-Based Digital Placebo Mental Health Intervention: Randomized Controlled Trial",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Feb",
day="17",
volume="9",
number="2",
pages="e20329",
keywords="digital placebo effect",
keywords="efficacy expectancies",
keywords="ecological momentary assessment",
keywords="mHealth",
keywords="mobile phone",
keywords="placebo effect",
keywords="randomized controlled trial",
keywords="smartphone-based intervention",
abstract="Background: There is certain evidence on the efficacy of smartphone-based mental health interventions. However, the mechanisms of action remain unclear. Placebo effects contribute to the efficacy of face-to-face mental health interventions and may also be a potential mechanism of action in smartphone-based interventions. Objective: This study aimed to investigate whether different types of efficacy expectancies as potential factors underlying placebo effects could be successfully induced in a smartphone-based digital placebo mental health intervention, ostensibly targeting mood and stress. Methods: We conducted a randomized, controlled, single-blinded, superiority trial with a multi-arm parallel design. Participants underwent an Android smartphone-based digital placebo mental health intervention for 20 days. We induced prospective efficacy expectancies via initial instructions on the purpose of the intervention and retrospective efficacy expectancies via feedback on the success of the intervention at days 1, 4, 7, 10, and 13. A total of 132 healthy participants were randomized to a prospective expectancy--only condition (n=33), a retrospective expectancy--only condition (n=33), a combined expectancy condition (n=34), or a control condition (n=32). As the endpoint, we assessed changes in efficacy expectancies with the Credibility Expectancy Questionnaire, before the intervention and on days 1, 7, 14, and 20. For statistical analyses, we used a random effects model for the intention-to-treat sample, with intervention day as time variable and condition as two factors: prospective expectancy (yes vs no) and retrospective expectancy (yes vs no), allowed to vary over participant and intervention day. Results: Credibility ($\beta$=?1.63; 95\% CI ?2.37 to ?0.89; P<.001) and expectancy ($\beta$=?0.77; 95\% CI ?1.49 to ?0.05; P=.04) decreased across the intervention days. For credibility and expectancy, we found significant three-way interactions: intervention day{\texttimes}prospective expectancy{\texttimes}retrospective expectancy (credibility: $\beta$=2.05; 95\% CI 0.60-3.50; P=.006; expectancy: $\beta$=1.55; 95\% CI 0.14-2.95; P=.03), suggesting that efficacy expectancies decreased least in the combined expectancy condition and the control condition. Conclusions: To our knowledge, this is the first empirical study investigating whether efficacy expectancies can be successfully induced in a specifically designed placebo smartphone-based mental health intervention. Our findings may pave the way to diminish or exploit digital placebo effects and help to improve the efficacy of digital mental health interventions. Trial Registration: Clinicaltrials.gov NCT02365220; https://clinicaltrials.gov/ct2/show/NCT02365220. ",
doi="10.2196/20329",
url="http://mhealth.jmir.org/2021/2/e20329/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33594991"
}


@Article{info:doi/10.2196/19430,
author="Sun, Yuewen
and Luo, Rong
and Li, Yuan
and He, J. Feng
and Tan, Monique
and MacGregor, A. Graham
and Liu, Hueiming
and Zhang, Puhong",
title="App-Based Salt Reduction Intervention in School Children and Their Families (AppSalt) in China: Protocol for a Mixed Methods Process Evaluation",
journal="JMIR Res Protoc",
year="2021",
month="Feb",
day="10",
volume="10",
number="2",
pages="e19430",
keywords="mobile health",
keywords="mobile phone",
keywords="process evaluation",
keywords="salt reduction",
keywords="health education",
abstract="Background: The app-based salt reduction intervention program in school children and their families (AppSalt) is a multicomponent mobile health (mHealth) intervention program, which involves multiple stakeholders, including students, parents, teachers, school heads, and local health and education authorities. The complexity of the AppSalt program highlights the need for process evaluation to investigate how the implementation will be achieved at different sites. Objective: This paper presents a process evaluation protocol of the AppSalt program, which aims to monitor the implementation of the program, explain its causal mechanisms, and provide evidence for scaling up the program nationwide. Methods: A mixed methods approach will be used to collect data relating to five process evaluation dimensions: fidelity, dose delivered, dose received, reach, and context. Quantitative data, including app use logs, activity logs, and routine monitoring data, will be collected alongside the intervention process to evaluate the quantity and quality of intervention activities. The quantitative data will be summarized as medians, means, and proportions as appropriate. Qualitative data will be collected through semistructured interviews of purposely selected intervention participants and key stakeholders from local health and education authorities. The thematic analysis technique will be used for analyzing the qualitative data with the support of NVivo 12. The qualitative data will be triangulated with the quantitative data during the interpretation phase to explain the 5 process evaluation dimensions. Results: The intervention activities of the AppSalt program were initiated at 27 primary schools in three cities since October 2018. We have completed the 1-year intervention of this program. The quantitative data for this study, including app use log, activity logs, and the routine monitoring data, were collected and organized during the intervention process. After completing the intervention, we conducted semistructured interviews with 32 students, 32 parents, 9 teachers, 9 school heads, and 8 stakeholders from local health and education departments. Data analysis is currently underway. Conclusions: Using mHealth technology for salt reduction among primary school students is an innovation in China. The findings of this study will help researchers understand the implementation of the AppSalt program and similar mHealth interventions in real-world settings. Furthermore, this process evaluation will be informative for other researchers and policy makers interested in replicating the AppSalt program and designing their salt reduction intervention. International Registered Report Identifier (IRRID): DERR1-10.2196/19430 ",
doi="10.2196/19430",
url="http://www.researchprotocols.org/2021/2/e19430/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33565991"
}


@Article{info:doi/10.2196/24457,
author="Mustafa, Norashikin
and Safii, Shanita Nik
and Jaffar, Aida
and Sani, Samsiah Nor
and Mohamad, Izham Mohd
and Abd Rahman, Hadi Abdul
and Mohd Sidik, Sherina",
title="Malay Version of the mHealth App Usability Questionnaire (M-MAUQ): Translation, Adaptation, and Validation Study",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Feb",
day="4",
volume="9",
number="2",
pages="e24457",
keywords="mHealth app",
keywords="questionnaire validation",
keywords="questionnaire translation",
keywords="Malay MAUQ",
keywords="usability",
keywords="mHealth",
keywords="education",
keywords="Malay language",
keywords="Malay",
keywords="questionnaire",
keywords="mobile phone",
abstract="Background: Mobile health (mHealth) apps play an important role in delivering education, providing advice on treatment, and monitoring patients' health. Good usability of mHealth apps is essential to achieve the objectives of mHealth apps efficiently. To date, there are questionnaires available to assess the general system usability but not explicitly tailored to precisely assess the usability of mHealth apps. Hence, the mHealth App Usability Questionnaire (MAUQ) was developed with 4 versions according to the type of app (interactive or standalone) and according to the target user (patient or provider). Standalone MAUQ for patients comprises 3 subscales, which are ease of use, interface and satisfaction, and usefulness. Objective: This study aimed to translate and validate the English version of MAUQ (standalone for patients) into a Malay version of MAUQ (M-MAUQ) for mHealth app research and usage in future in Malaysia. Methods: Forward and backward translation and harmonization of M-MAUQ were conducted by Malay native speakers who also spoke English as their second language. The process began with a forward translation by 2 independent translators followed by harmonization to produce an initial translated version of M-MAUQ. Next, the forward translation was continued by another 2 translators who had never seen the original MAUQ. Lastly, harmonization was conducted among the committee members to resolve any ambiguity and inconsistency in the words and sentences of the items derived with the prefinal adapted questionnaire. Subsequently, content and face validations were performed with 10 experts and 10 target users, respectively. Modified kappa statistic was used to determine the interrater agreement among the raters. The reliability of the M-MAUQ was assessed by 51 healthy young adult mobile phone users. Participants needed to install the MyFitnessPal app and use it for 2 days for familiarization before completing the designated task and answer the M-MAUQ. The MyFitnessPal app was selected because it is one among the most popular installed mHealth apps globally available for iPhone and Android users and represents a standalone mHealth app. Results: The content validity index for the relevancy and clarity of M-MAUQ were determined to be 0.983 and 0.944, respectively, which indicated good relevancy and clarity. The face validity index for understandability was 0.961, which indicated that users understood the M-MAUQ. The kappa statistic for every item in M-MAUQ indicated excellent agreement between the raters ($\kappa$ ranging from 0.76 to 1.09). The Cronbach $\alpha$ for 18 items was .946, which also indicated good reliability in assessing the usability of the mHealth app. Conclusions: The M-MAUQ fulfilled the validation criteria as it revealed good reliability and validity similar to the original version. M-MAUQ can be used to assess the usability of mHealth apps in Malay in the future. ",
doi="10.2196/24457",
url="http://mhealth.jmir.org/2021/2/e24457/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33538704"
}


@Article{info:doi/10.2196/21926,
author="Bahador, Nooshin
and Ferreira, Denzil
and Tamminen, Satu
and Kortelainen, Jukka",
title="Deep Learning--Based Multimodal Data Fusion: Case Study in Food Intake Episodes Detection Using Wearable Sensors",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Jan",
day="28",
volume="9",
number="1",
pages="e21926",
keywords="deep learning",
keywords="image processing",
keywords="data fusion",
keywords="covariance distribution",
keywords="food intake episode",
keywords="wearable sensors",
abstract="Background: Multimodal wearable technologies have brought forward wide possibilities in human activity recognition, and more specifically personalized monitoring of eating habits. The emerging challenge now is the selection of most discriminative information from high-dimensional data collected from multiple sources. The available fusion algorithms with their complex structure are poorly adopted to the computationally constrained environment which requires integrating information directly at the source. As a result, more simple low-level fusion methods are needed. Objective: In the absence of a data combining process, the cost of directly applying high-dimensional raw data to a deep classifier would be computationally expensive with regard to the response time, energy consumption, and memory requirement. Taking this into account, we aimed to develop a data fusion technique in a computationally efficient way to achieve a more comprehensive insight of human activity dynamics in a lower dimension. The major objective was considering statistical dependency of multisensory data and exploring intermodality correlation patterns for different activities. Methods: In this technique, the information in time (regardless of the number of sources) is transformed into a 2D space that facilitates classification of eating episodes from others. This is based on a hypothesis that data captured by various sensors are statistically associated with each other and the covariance matrix of all these signals has a unique distribution correlated with each activity which can be encoded on a contour representation. These representations are then used as input of a deep model to learn specific patterns associated with specific activity. Results: In order to show the generalizability of the proposed fusion algorithm, 2 different scenarios were taken into account. These scenarios were different in terms of temporal segment size, type of activity, wearable device, subjects, and deep learning architecture. The first scenario used a data set in which a single participant performed a limited number of activities while wearing the Empatica E4 wristband. In the second scenario, a data set related to the activities of daily living was used where 10 different participants wore inertial measurement units while performing a more complex set of activities. The precision metric obtained from leave-one-subject-out cross-validation for the second scenario reached 0.803. The impact of missing data on performance degradation was also evaluated. Conclusions: To conclude, the proposed fusion technique provides the possibility of embedding joint variability information over different modalities in just a single 2D representation which results in obtaining a more global view of different aspects of daily human activities at hand, and yet preserving the desired performance level in activity recognition. ",
doi="10.2196/21926",
url="http://mhealth.jmir.org/2021/1/e21926/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33507156"
}


@Article{info:doi/10.2196/14326,
author="Jones, L. Thomas
and Heiden, Emily
and Mitchell, Felicity
and Fogg, Carole
and McCready, Sharon
and Pearce, Laurence
and Kapoor, Melissa
and Bassett, Paul
and Chauhan, J. Anoop",
title="Developing the Accuracy of Vital Sign Measurements Using the Lifelight Software Application in Comparison to Standard of Care Methods: Observational Study Protocol",
journal="JMIR Res Protoc",
year="2021",
month="Jan",
day="28",
volume="10",
number="1",
pages="e14326",
keywords="health technology",
keywords="remote monitoring",
keywords="vital signs",
keywords="patient deterioration",
abstract="Background: Vital sign measurements are an integral component of clinical care, but current challenges with the accuracy and timeliness of patient observations can impact appropriate clinical decision making. Advanced technologies using techniques such as photoplethysmography have the potential to automate noncontact physiological monitoring and recording, improving the quality and accessibility of this essential clinical information. Objective: In this study, we aim to develop the algorithm used in the Lifelight software application and improve the accuracy of its estimated heart rate, respiratory rate, oxygen saturation, and blood pressure measurements. Methods: This preliminary study will compare measurements predicted by the Lifelight software with standard of care measurements for an estimated population sample of 2000 inpatients, outpatients, and healthy people attending a large acute hospital. Both training datasets and validation datasets will be analyzed to assess the degree of correspondence between the vital sign measurements predicted by the Lifelight software and the direct physiological measurements taken using standard of care methods. Subgroup analyses will explore how the performance of the algorithm varies with particular patient characteristics, including age, sex, health condition, and medication. Results: Recruitment of participants to this study began in July 2018, and data collection will continue for a planned study period of 12 months. Conclusions: Digital health technology is a rapidly evolving area for health and social care. Following this initial exploratory study to develop and refine the Lifelight software application, subsequent work will evaluate its performance across a range of health characteristics, and extended validation trials will support its pathway to registration as a medical device. Innovations in health technology such as this may provide valuable opportunities for increasing the efficiency and accessibility of vital sign measurements and improve health care services on a large scale across multiple health and care settings. International Registered Report Identifier (IRRID): DERR1-10.2196/14326 ",
doi="10.2196/14326",
url="http://www.researchprotocols.org/2021/1/e14326/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33507157"
}


@Article{info:doi/10.2196/22846,
author="Kelly, Ryan
and Jones, Simon
and Price, Blaine
and Katz, Dmitri
and McCormick, Ciaran
and Pearce, Oliver",
title="Measuring Daily Compliance With Physical Activity Tracking in Ambulatory Surgery Patients: Comparative Analysis of Five Compliance Criteria",
journal="JMIR Mhealth Uhealth",
year="2021",
month="Jan",
day="26",
volume="9",
number="1",
pages="e22846",
keywords="activity tracking",
keywords="adherence",
keywords="compliance",
keywords="surgery",
keywords="total knee arthroplasty",
abstract="Background: Physical activity trackers such as the Fitbit can allow clinicians to monitor the recovery of their patients following surgery. An important issue when analyzing activity tracker data is to determine patients' daily compliance with wearing their assigned device, using an appropriate criterion to determine a valid day of wear. However, it is currently unclear as to how different criteria can affect the reported compliance of patients recovering from ambulatory surgery. Investigating this issue can help to inform the use of activity data by revealing factors that may impact compliance calculations. Objective: This study aimed to understand how using different criteria can affect the reported compliance with activity tracking in ambulatory surgery patients. It also aimed to investigate factors that explain variation between the outcomes of different compliance criteria. Methods: A total of 62 patients who were scheduled to undergo total knee arthroplasty (TKA, ie, knee replacement) volunteered to wear a commercial Fitbit Zip activity tracker over an 8-week perioperative period. Patients were asked to wear the Fitbit Zip daily, beginning 2 weeks prior to their surgery and ending 6 weeks after surgery. Of the 62 patients who enrolled in the study, 20 provided Fitbit data and underwent successful surgery. The Fitbit data were analyzed using 5 different daily compliance criteria, which consider patients as compliant with daily tracking if they either register >0 steps in a day, register >500 steps in a day, register at least one step in 10 different hours of the day, register >0 steps in 3 distinct time windows, or register >0 steps in 3 out of 4 six-hour time windows. The criteria were compared in terms of compliance outcomes produced for each patient. Data were explored using heatmaps and line graphs. Linear mixed models were used to identify factors that lead to variation between compliance outcomes across the sample. Results: The 5 compliance criteria produce different outcomes when applied to the patients' data, with an average 24\% difference in reported compliance between the most lenient and strictest criteria. However, the extent to which each patient's reported compliance was impacted by different criteria was not uniform. Some individuals were relatively unaffected, whereas others varied by up to 72\%. Wearing the activity tracker as a clip-on device, rather than on the wrist, was associated with greater differences between compliance outcomes at the individual level (P=.004, r=.616). This effect was statistically significant (P<.001) in the first 2 weeks after surgery. There was also a small but significant main effect of age on compliance in the first 2 weeks after surgery (P=.040). Gender and BMI were not associated with differences in individual compliance outcomes. Finally, the analysis revealed that surgery has an impact on patients' compliance, with noticeable reductions in activity following surgery. These reductions affect compliance calculations by discarding greater amounts of data under strict criteria. Conclusions: This study suggests that different compliance criteria cannot be used interchangeably to analyze activity data provided by TKA patients. Surgery leads to a temporary reduction in patients' mobility, which affects their reported compliance when strict thresholds are used. Reductions in mobility suggest that the use of lenient compliance criteria, such as >0 steps or windowed approaches, can avoid unnecessary data exclusion over the perioperative period. Encouraging patients to wear the device at their wrist may improve data quality by increasing the likelihood of patients wearing their tracker and ensuring that activity is registered in the 2 weeks after surgery. Trial Registration: ClinicalTrials.gov NCT03518866; https://clinicaltrials.gov/ct2/show/NCT03518866 ",
doi="10.2196/22846",
url="http://mhealth.jmir.org/2021/1/e22846/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33496677"
}


@Article{info:doi/10.2196/20597,
author="Kim, Ki-Hun
and Kim, Kwang-Jae",
title="Missing-Data Handling Methods for Lifelogs-Based Wellness Index Estimation: Comparative Analysis With Panel Data",
journal="JMIR Med Inform",
year="2020",
month="Dec",
day="17",
volume="8",
number="12",
pages="e20597",
keywords="lifelogs-based wellness index",
keywords="missing-data handling",
keywords="health behavior lifelogs",
keywords="panel data",
keywords="smart wellness service",
abstract="Background: A lifelogs-based wellness index (LWI) is a function for calculating wellness scores based on health behavior lifelogs (eg, daily walking steps and sleep times collected via a smartwatch). A wellness score intuitively shows the users of smart wellness services the overall condition of their health behaviors. LWI development includes estimation (ie, estimating coefficients in LWI with data). A panel data set comprising health behavior lifelogs allows LWI estimation to control for unobserved variables, thereby resulting in less bias. However, these data sets typically have missing data due to events that occur in daily life (eg, smart devices stop collecting data when batteries are depleted), which can introduce biases into LWI coefficients. Thus, the appropriate choice of method to handle missing data is important for reducing biases in LWI estimations with panel data. However, there is a lack of research in this area. Objective: This study aims to identify a suitable missing-data handling method for LWI estimation with panel data. Methods: Listwise deletion, mean imputation, expectation maximization--based multiple imputation, predictive-mean matching--based multiple imputation, k-nearest neighbors--based imputation, and low-rank approximation--based imputation were comparatively evaluated by simulating an existing case of LWI development. A panel data set comprising health behavior lifelogs of 41 college students over 4 weeks was transformed into a reference data set without any missing data. Then, 200 simulated data sets were generated by randomly introducing missing data at proportions from 1\% to 80\%. The missing-data handling methods were each applied to transform the simulated data sets into complete data sets, and coefficients in a linear LWI were estimated for each complete data set. For each proportion for each method, a bias measure was calculated by comparing the estimated coefficient values with values estimated from the reference data set. Results: Methods performed differently depending on the proportion of missing data. For 1\% to 30\% proportions, low-rank approximation--based imputation, predictive-mean matching--based multiple imputation, and expectation maximization--based multiple imputation were superior. For 31\% to 60\% proportions, low-rank approximation--based imputation and predictive-mean matching--based multiple imputation performed best. For over 60\% proportions, only low-rank approximation--based imputation performed acceptably. Conclusions: Low-rank approximation--based imputation was the best of the 6 data-handling methods regardless of the proportion of missing data. This superiority is generalizable to other panel data sets comprising health behavior lifelogs given their verified low-rank nature, for which low-rank approximation--based imputation is known to perform effectively. This result will guide missing-data handling in reducing coefficient biases in new development cases of linear LWIs with panel data. ",
doi="10.2196/20597",
url="http://medinform.jmir.org/2020/12/e20597/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33331831"
}


@Article{info:doi/10.2196/16309,
author="Lin, Yu-Hsuan
and Chen, Si-Yu
and Lin, Pei-Hsuan
and Tai, An-Shun
and Pan, Yuan-Chien
and Hsieh, Chang-En
and Lin, Sheng-Hsuan",
title="Assessing User Retention of a Mobile App: Survival Analysis",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Nov",
day="26",
volume="8",
number="11",
pages="e16309",
keywords="smartphone",
keywords="passive data, user retention",
keywords="mobile application",
keywords="app",
keywords="survival analysis",
keywords="work hours",
abstract="Background: A mobile app generates passive data, such as GPS data traces, without any direct involvement from the user. These passive data have transformed the manner of traditional assessments that require active participation from the user. Passive data collection is one of the most important core techniques for mobile health development because it may promote user retention, which is a unique characteristic of a software medical device. Objective: The primary aim of this study was to quantify user retention for the ``Staff Hours'' app using survival analysis. The secondary aim was to compare user retention between passive data and active data, as well as factors associated with the survival rates of user retention. Methods: We developed an app called ``Staff Hours'' to automatically calculate users' work hours through GPS data (passive data). ``Staff Hours'' not only continuously collects these passive data but also sends an 11-item mental health survey to users monthly (active data). We applied survival analysis to compare user retention in the collection of passive and active data among 342 office workers from the ``Staff Hours'' database. We also compared user retention on Android and iOS platforms and examined the moderators of user retention. Results: A total of 342 volunteers (224 men; mean age 33.8 years, SD 7.0 years) were included in this study. Passive data had higher user retention than active data (P=.011). In addition, user retention for passive data collected via Android devices was higher than that for iOS devices (P=.015). Trainee physicians had higher user retention for the collection of active data than trainees from other occupations, whereas no significant differences between these two groups were observed for the collection of passive data (P=.700). Conclusions: Our findings demonstrated that passive data collected via Android devices had the best user retention for this app that records GPS-based work hours. ",
doi="10.2196/16309",
url="http://mhealth.jmir.org/2020/11/e16309/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33242023"
}


@Article{info:doi/10.2196/13535,
author="Aubourg, Timoth{\'e}e
and Demongeot, Jacques
and Provost, Herv{\'e}
and Vuillerme, Nicolas",
title="Exploitation of Outgoing and Incoming Telephone Calls in the Context of Circadian Rhythms of Social Activity Among Elderly People: Observational Descriptive Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Nov",
day="26",
volume="8",
number="11",
pages="e13535",
keywords="circadian rhythms",
keywords="phone call detail records",
keywords="older population",
keywords="digital phenotype",
abstract="Background: In the elderly population, analysis of the circadian rhythms of social activity may help in supervising homebound disabled and chronically ill populations. Circadian rhythms are monitored over time to determine, for example, the stability of the organization of daily social activity rhythms and the occurrence of particular desynchronizations in the way older adults act and react socially during the day. Recently, analysis of telephone call detail records has led to the possibility of determining circadian rhythms of social activity in an objective unobtrusive way for young patients from their outgoing telephone calls. At this stage, however, the analysis of incoming call rhythms and the comparison of their organization with respect to outgoing calls remains to be performed in underinvestigated populations (in particular, older populations). Objective: This study investigated the persistence and synchronization of circadian rhythms in telephone communication by older adults. Methods: The study used a longitudinal 12-month data set combining call detail records and questionnaire data from 26 volunteers aged 70 years or more to determine the existence of persistent and synchronized circadian rhythms in their telephone communications. The study worked with the following four specific telecommunication parameters: (1) recipient of the telephone call (alter), (2) time at which the call began, (3) duration of the call, and (4) direction of the call. We focused on the following two issues: (1) the existence of persistent circadian rhythms of outgoing and incoming telephone calls in the older population and (2) synchronization with circadian rhythms in the way the older population places and responds to telephone calls. Results: The results showed that older adults have their own specific circadian rhythms for placing telephone calls and receiving telephone calls. These rhythms are partly structured by the way in which older adults allocate their communication time over the day. In addition, despite minor differences between circadian rhythms for outgoing and incoming calls, our analysis suggests the two rhythms could be synchronized. Conclusions: These results suggest the existence of potential persistent and synchronized circadian rhythms in the outgoing and incoming telephone activities of older adults. ",
doi="10.2196/13535",
url="http://mhealth.jmir.org/2020/11/e13535/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33242018"
}


@Article{info:doi/10.2196/21874,
author="Ologeanu-Taddei, Roxana",
title="Assessment of mHealth Interventions: Need for New Studies, Methods, and Guidelines for Study Designs",
journal="JMIR Med Inform",
year="2020",
month="Nov",
day="18",
volume="8",
number="11",
pages="e21874",
keywords="eHealth",
keywords="mHealth",
keywords="usability",
keywords="management",
keywords="survey",
keywords="trust",
keywords="guidelines",
keywords="evaluation",
doi="10.2196/21874",
url="http://medinform.jmir.org/2020/11/e21874/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33206060"
}


@Article{info:doi/10.2196/17577,
author="Bruce, Courtenay
and Harrison, Patricia
and Giammattei, Charlie
and Desai, Shetal-Nicholas
and Sol, R. Joshua
and Jones, Stephen
and Schwartz, Roberta",
title="Evaluating Patient-Centered Mobile Health Technologies: Definitions, Methodologies, and Outcomes",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Nov",
day="11",
volume="8",
number="11",
pages="e17577",
keywords="innovation",
keywords="health care",
keywords="digital technology",
keywords="digital interventions",
keywords="patient-facing technologies",
keywords="patient-centered care",
keywords="patient centeredness",
keywords="patient experience",
keywords="patient engagement",
keywords="patient activation",
keywords="quality",
keywords="effectiveness",
keywords="quality improvement",
keywords="information technologies",
keywords="outcomes",
keywords="readmissions",
keywords="length of stay",
keywords="patient adherence",
doi="10.2196/17577",
url="http://mhealth.jmir.org/2020/11/e17577/",
url="http://www.ncbi.nlm.nih.gov/pubmed/33174846"
}


@Article{info:doi/10.2196/18230,
author="Heynsbergh, Natalie
and O, (Eric) Seung Chul
and Livingston, M. Patricia",
title="Assessment of Data Usage of Cancer e-Interventions (ADUCI) Framework for Health App Use of Cancer Patients and Their Caregivers: Framework Development Study",
journal="JMIR Cancer",
year="2020",
month="Sep",
day="15",
volume="6",
number="2",
pages="e18230",
keywords="multimedia",
keywords="user engagement",
keywords="cancer",
keywords="smartphone",
keywords="framework",
keywords="usage data",
keywords="eHealth technology",
keywords="e-intervention",
keywords="data analysis",
keywords="efficiency",
keywords="e-research",
keywords="apps",
abstract="Background: Multimedia interventions can provide a cost-effective solution to public health needs; however, user engagement is low. Multimedia use within specific populations such as those affected by cancer differs from that of the general population. To our knowledge, there are no frameworks on how to accurately assess usage within this population to ensure that interventions are appropriate for the end users. Therefore, a framework was developed to improve the accuracy of determining data usage. Formative work included creating a data usage framework during target audience testing for smartphone app development and analysis in a pilot study. Objective: The purpose of this study was to develop a framework for assessing smartphone app usage among people living with cancer and their caregivers. Methods: The frequency and duration of use were compared based on manual data extraction from two previous studies and the newly developed Assessment of Data Usage of Cancer e-Interventions (ADUCI) Framework. Results: Manual extraction demonstrated that 279 logins occurred compared with 241 when the ADUCI Framework was applied. The frequency of use in each section of the app also decreased when the ADUCI Framework was used. The total duration of use was 91,256 seconds (25.3 hours) compared with 53,074 seconds (14.7 hours) when using the ADUCI Framework. The ADUCI Framework identified 38 logins with no navigation, and there were 15 discrepancies in the data where time on a specific page of the app exceeded the login time. Practice recommendations to improve user engagement and capturing usage data include tracking data use in external websites, having a login function on apps, creating a five-star page rating functionality, using the ADUCI Framework to thoroughly clean usage data, and validating the Framework between expected and observed use. Conclusions: Applying the ADUCI Framework may eliminate errors and allow for more accurate analysis of usage data in e-research projects. The Framework can also improve the process of capturing usage data by providing a guide for usage data analysis to facilitate evidence-based assessment of user engagement with apps. ",
doi="10.2196/18230",
url="http://cancer.jmir.org/2020/2/e18230/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32930666"
}


@Article{info:doi/10.2196/18355,
author="Xie, Feng Li
and Itzkovitz, Alexandra
and Roy-Fleming, Amelie
and Da Costa, Deborah
and Brazeau, Anne-Sophie",
title="Understanding Self-Guided Web-Based Educational Interventions for Patients With Chronic Health Conditions: Systematic Review of Intervention Features and Adherence",
journal="J Med Internet Res",
year="2020",
month="Aug",
day="13",
volume="22",
number="8",
pages="e18355",
keywords="chronic disease",
keywords="online learning",
keywords="self-management",
keywords="mobile phone",
abstract="Background: Chronic diseases contribute to 71\% of deaths worldwide every year, and an estimated 15 million people between the ages of 30 and 69 years die mainly because of cardiovascular disease, cancer, chronic respiratory diseases, or diabetes. Web-based educational interventions may facilitate disease management. These are also considered to be a flexible and low-cost method to deliver tailored information to patients. Previous studies concluded that the implementation of different features and the degree of adherence to the intervention are key factors in determining the success of the intervention. However, limited research has been conducted to understand the acceptability of specific features and user adherence to self-guided web interventions. Objective: This systematic review aims to understand how web-based intervention features are evaluated, to investigate their acceptability, and to describe how adherence to web-based self-guided interventions is defined and measured. Methods: Studies published on self-guided web-based educational interventions for people (?14 years old) with chronic health conditions published between January 2005 and June 2020 were reviewed following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) Statement protocol. The search was performed using the PubMed, Cochrane Library, and EMBASE (Excerpta Medica dataBASE) databases; the reference lists of the selected articles were also reviewed. The comparison of the interventions and analysis of the features were based on the published content from the selected articles. Results: A total of 20 studies were included. Seven principal features were identified, with goal setting, self-monitoring, and feedback being the most frequently used. The acceptability of the features was measured based on the comments collected from users, their association with clinical outcomes, or device adherence. The use of quizzes was positively reported by participants. Self-monitoring, goal setting, feedback, and discussion forums yielded mixed results. The negative acceptability was related to the choice of the discussion topic, lack of face-to-face contact, and technical issues. This review shows that the evaluation of adherence to educational interventions was inconsistent among the studies, limiting comparisons. A clear definition of adherence to an intervention is lacking. Conclusions: Although limited information was available, it appears that features related to interaction and personalization are important for improving clinical outcomes and users' experience. When designing web-based interventions, the selection of features should be based on the targeted population's needs, the balance between positive and negative impacts of having human involvement in the intervention, and the reduction of technical barriers. There is a lack of consensus on the method of evaluating adherence to an intervention. Both investigations of the acceptability features and adherence should be considered when designing and evaluating web-based interventions. A proof-of-concept or pilot study would be useful for establishing the required level of engagement needed to define adherence. ",
doi="10.2196/18355",
url="http://www.jmir.org/2020/8/e18355/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32788152"
}


@Article{info:doi/10.2196/17774,
author="Bonten, N. Tobias
and Rauwerdink, Anneloek
and Wyatt, C. Jeremy
and Kasteleyn, J. Marise
and Witkamp, Leonard
and Riper, Heleen
and van Gemert-Pijnen, JEWC Lisette
and Cresswell, Kathrin
and Sheikh, Aziz
and Schijven, P. Marlies
and Chavannes, H. Niels
and ",
title="Online Guide for Electronic Health Evaluation Approaches: Systematic Scoping Review and Concept Mapping Study",
journal="J Med Internet Res",
year="2020",
month="Aug",
day="12",
volume="22",
number="8",
pages="e17774",
keywords="eHealth",
keywords="mHealth",
keywords="digital health",
keywords="methodology",
keywords="study design",
keywords="health technology assessment",
keywords="evaluation",
keywords="scoping review",
keywords="concept mapping",
abstract="Background: Despite the increase in use and high expectations of digital health solutions, scientific evidence about the effectiveness of electronic health (eHealth) and other aspects such as usability and accuracy is lagging behind. eHealth solutions are complex interventions, which require a wide array of evaluation approaches that are capable of answering the many different questions that arise during the consecutive study phases of eHealth development and implementation. However, evaluators seem to struggle in choosing suitable evaluation approaches in relation to a specific study phase. Objective: The objective of this project was to provide a structured overview of the existing eHealth evaluation approaches, with the aim of assisting eHealth evaluators in selecting a suitable approach for evaluating their eHealth solution at a specific evaluation study phase. Methods: Three consecutive steps were followed. Step 1 was a systematic scoping review, summarizing existing eHealth evaluation approaches. Step 2 was a concept mapping study asking eHealth researchers about approaches for evaluating eHealth. In step 3, the results of step 1 and 2 were used to develop an ``eHealth evaluation cycle'' and subsequently compose the online ``eHealth methodology guide.'' Results: The scoping review yielded 57 articles describing 50 unique evaluation approaches. The concept mapping study questioned 43 eHealth researchers, resulting in 48 unique approaches. After removing duplicates, 75 unique evaluation approaches remained. Thereafter, an ``eHealth evaluation cycle'' was developed, consisting of six evaluation study phases: conceptual and planning, design, development and usability, pilot (feasibility), effectiveness (impact), uptake (implementation), and all phases. Finally, the ``eHealth methodology guide'' was composed by assigning the 75 evaluation approaches to the specific study phases of the ``eHealth evaluation cycle.'' Conclusions: Seventy-five unique evaluation approaches were found in the literature and suggested by eHealth researchers, which served as content for the online ``eHealth methodology guide.'' By assisting evaluators in selecting a suitable evaluation approach in relation to a specific study phase of the ``eHealth evaluation cycle,'' the guide aims to enhance the quality, safety, and successful long-term implementation of novel eHealth solutions. ",
doi="10.2196/17774",
url="https://www.jmir.org/2020/8/e17774",
url="http://www.ncbi.nlm.nih.gov/pubmed/32784173"
}


@Article{info:doi/10.2196/17760,
author="Llorens-Vernet, Pere
and Mir{\'o}, Jordi",
title="The Mobile App Development and Assessment Guide (MAG): Delphi-Based Validity Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jul",
day="31",
volume="8",
number="7",
pages="e17760",
keywords="assessment",
keywords="Delphi method",
keywords="MAG",
keywords="mobile apps",
keywords="mobile health",
keywords="validity",
keywords="guide",
abstract="Background: In recent years, there has been an exponential growth of mobile health (mHealth)--related apps. This has occurred in a somewhat unsupervised manner. Therefore, having a set of criteria that could be used by all stakeholders to guide the development process and the assessment of the quality of the apps is of most importance. Objective: The aim of this paper is to study the validity of the Mobile App Development and Assessment Guide (MAG), a guide recently created to help stakeholders develop and assess mobile health apps. Methods: To conduct a validation process of the MAG, we used the Delphi method to reach a consensus among participating stakeholders. We identified 158 potential participants: 45 patients as potential end users, 41 health care professionals, and 72 developers. We sent participants an online survey and asked them to rate how important they considered each item in the guide to be on a scale from 0 to 10. Two rounds were enough to reach consensus. Results: In the first round, almost one-third (n=42) of those invited participated, and half of those (n=24) also participated in the second round. Most items in the guide were found to be important to a quality mHealth-related app; a total of 48 criteria were established as important. ``Privacy,'' ``security,'' and ``usability'' were the categories that included most of the important criteria. Conclusions: The data supports the validity of the MAG. In addition, the findings identified the criteria that stakeholders consider to be most important. The MAG will help advance the field by providing developers, health care professionals, and end users with a valid guide so that they can develop and identify mHealth-related apps that are of quality. ",
doi="10.2196/17760",
url="http://mhealth.jmir.org/2020/7/e17760/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32735226"
}


@Article{info:doi/10.2196/16471,
author="Willemse, Cornelis Bastiaan Johannes Paulus
and Kaptein, Clemens Maurits
and Hasaart, Fleur",
title="Developing Effective Methods for Electronic Health Personalization: Protocol for Health Telescope, a Prospective Interventional Study",
journal="JMIR Res Protoc",
year="2020",
month="Jul",
day="31",
volume="9",
number="7",
pages="e16471",
keywords="eHealth",
keywords="mHealth",
keywords="personalization",
keywords="longitudinal study",
keywords="wearables",
keywords="panel study",
keywords="persuasive technology",
keywords="gdpr",
abstract="Background: Existing evaluations of the effects of mobile apps to encourage physical activity have been criticized owing to their common lack of external validity, their short duration, and their inability to explain the drivers of the observed effects. This protocol describes the setup of Health Telescope, a longitudinal panel study in which the long-term effects of mobile electronic health (eHealth) apps are investigated. By setting up Health Telescope, we aim to (1) understand more about the long-term use of eHealth apps in an externally valid setting, (2) understand the relationships between short-term and long-term outcomes of the usage of eHealth apps, and (3) test different ways in which eHealth app allocation can be personalized. Objective: The objectives of this paper are to (1) demonstrate and motivate the validity of the many choices that we made in setting up an intensive longitudinal study, (2) provide a resource for researchers interested in using data generated by our study, and (3) act as a guideline for researchers interested in setting up their own longitudinal data collection using wearable devices. For the third objective, we explicitly discuss the General Data Protection Regulation and ethical requirements that need to be addressed. Methods: In this 4-month study, a group of approximately 450 participants will have their daily step count measured and will be asked daily about their mood using experience sampling. Once per month, participants will receive an intervention containing a recommendation to download an app that focuses on increasing physical activity. The mechanism for assigning recommendations to participants will be personalized over time, using contextual data obtained from previous interventions. Results: The data collection software has been developed, and all the legal and ethical checks are in place. Recruitment will start in Q4 of 2020. The initial results will be published in 2021. Conclusions: The aim of Health Telescope is to investigate how different individuals respond to different ways of being encouraged to increase their physical activity. In this paper, we detail the setup, methods, and analysis plan that will enable us to reach this aim. International Registered Report Identifier (IRRID): PRR1-10.2196/16471 ",
doi="10.2196/16471",
url="http://www.researchprotocols.org/2020/7/e16471/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32734930"
}


@Article{info:doi/10.2196/17447,
author="Byambasuren, Oyungerel
and Beller, Elaine
and Hoffmann, Tammy
and Glasziou, Paul",
title="Barriers to and Facilitators of the Prescription of mHealth Apps in Australian General Practice: Qualitative Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jul",
day="30",
volume="8",
number="7",
pages="e17447",
keywords="mobile apps",
keywords="mHealth",
keywords="apps",
keywords="app prescription",
keywords="general practice",
abstract="Background: The ubiquity of smartphones and health apps make them a potential self-management tool for patients that could be prescribed by medical professionals. However, little is known about how Australian general practitioners and their patients view the possibility of prescribing mobile health (mHealth) apps as a nondrug intervention. Objective: This study aimed to determine barriers and facilitators to prescribing mHealth apps in Australian general practice from the perspective of general practitioners and their patients. Methods: We conducted semistructured interviews in Australian general practice settings with purposively sampled general practitioners and patients. The audio-recorded interviews were transcribed, coded, and thematically analyzed by two researchers. Results: Interview participants included 20 general practitioners and 15 adult patients. General practitioners' perceived barriers to prescribing apps included a generational difference in the digital propensity for providers and patients; lack of knowledge of prescribable apps and trustworthy sources to access them; the time commitment required of providers and patients to learn and use the apps; and concerns about privacy, safety, and trustworthiness of health apps. General practitioners perceived facilitators as trustworthy sources to access prescribable apps and information, and younger generation and widespread smartphone ownership. For patients, the main barriers were older age and usability of mHealth apps. Patients were not concerned about privacy and data safety issues regarding health app use. Facilitators for patients included the ubiquity of smartphones and apps, especially for the younger generation and recommendation of apps by doctors. We identified evidence of effectiveness as an independent theme from both the provider and patient perspectives. Conclusions: mHealth app prescription appears to be feasible in general practice. The barriers and facilitators identified by the providers and patients overlapped, though privacy was of less concern to patients. The involvement of health professionals and patients is vital for the successful integration of effective, evidence-based mHealth apps with clinical practice. ",
doi="10.2196/17447",
url="http://mhealth.jmir.org/2020/7/e17447/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32729839"
}


@Article{info:doi/10.2196/18413,
author="Scherr, Foster Thomas
and Moore, Paige Carson
and Thuma, Philip
and Wright, Wilson David",
title="Evaluating Network Readiness for mHealth Interventions Using the Beacon Mobile Phone App: Application Development and Validation Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jul",
day="28",
volume="8",
number="7",
pages="e18413",
keywords="mHealth",
keywords="network readiness",
keywords="network assessment",
keywords="mobile network",
abstract="Background: Mobile health (mHealth) interventions have the potential to transform the global health care landscape. The processing power of mobile devices continues to increase, and growth of mobile phone use has been observed worldwide. Uncertainty remains among key stakeholders and decision makers as to whether global health interventions can successfully tap into this trend. However, when correctly implemented, mHealth can reduce geographic, financial, and social barriers to quality health care. Objective: The aim of this study was to design and test Beacon, a mobile phone--based tool for evaluating mHealth readiness in global health interventions. Here, we present the results of an application validation study designed to understand the mobile network landscape in and around Macha, Zambia, in 2019. Methods: Beacon was developed as an automated mobile phone app that continually collects spatiotemporal data and measures indicators of network performance. Beacon was used in and around Macha, Zambia, in 2019. Results were collected, even in the absence of network connectivity, and asynchronously uploaded to a database for further analysis. Results: Beacon was used to evaluate three mobile phone networks around Macha. Carriers A and B completed 6820/7034 (97.0\%) and 6701/7034 (95.3\%) downloads and 1349/1608 (83.9\%) and 1431/1608 (89.0\%) uploads, respectively, while Carrier C completed only 62/1373 (4.5\%) file downloads and 0/1373 (0.0\%) file uploads. File downloads generally occurred within 4 to 12 seconds, and their maximum download speeds occurred between 2 AM and 5 AM. A decrease in network performance, demonstrated by increases in upload and download durations, was observed beginning at 5 PM and continued throughout the evening. Conclusions: Beacon was able to compare the performance of different cellular networks, show times of day when cellular networks experience heavy loads and slow down, and identify geographic ``dead zones'' with limited or no cellular service. Beacon is a ready-to-use tool that could be used by organizations that are considering implementing mHealth interventions in low- and middle-income countries but are questioning the feasibility of the interventions, including infrastructure and cost. It could also be used by organizations that are looking to optimize the delivery of an existing mHealth intervention with improved logistics management. ",
doi="10.2196/18413",
url="http://mhealth.jmir.org/2020/7/e18413/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32720909"
}


@Article{info:doi/10.2196/17134,
author="Benjumea, Jaime
and Ropero, Jorge
and Rivera-Romero, Octavio
and Dorronzoro-Zubiete, Enrique
and Carrasco, Alejandro",
title="Assessment of the Fairness of Privacy Policies of Mobile Health Apps: Scale Development and Evaluation in Cancer Apps",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jul",
day="28",
volume="8",
number="7",
pages="e17134",
keywords="privacy",
keywords="mhealth apps",
keywords="fairness assessment scale",
keywords="cancer apps",
keywords="GDPR",
abstract="Background: Cancer patients are increasingly using mobile health (mHealth) apps to take control of their health. Many studies have explored their efficiency, content, usability, and adherence; however, these apps have created a new set of privacy challenges, as they store personal and sensitive data. Objective: The purpose of this study was to refine and evaluate a scale based on the General Data Protection Regulation and assess the fairness of privacy policies of mHealth apps. Methods: Based on the experience gained from our previous work, we redefined some of the items and scores of our privacy scale. Using the new version of our scale, we conducted a case study in which we analyzed the privacy policies of cancer Android apps. A systematic search of cancer mobile apps was performed in the Spanish version of the Google Play website. Results: The redefinition of certain items reduced discrepancies between reviewers. Thus, use of the scale was made easier, not only for the reviewers but also for any other potential users of our scale. Assessment of the privacy policies revealed that 29\% (9/31) of the apps included in the study did not have a privacy policy, 32\% (10/31) had a score over 50 out of a maximum of 100 points, and 39\% (12/31) scored fewer than 50 points. Conclusions: In this paper, we present a scale for the assessment of mHealth apps that is an improved version of our previous scale with adjusted scores. The results showed a lack of fairness in the mHealth app privacy policies that we examined, and the scale provides developers with a tool to evaluate their privacy policies. ",
doi="10.2196/17134",
url="http://mhealth.jmir.org/2020/7/e17134/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32720913"
}


@Article{info:doi/10.2196/18212,
author="Peng, Cheng
and He, Miao
and Cutrona, L. Sarah
and Kiefe, I. Catarina
and Liu, Feifan
and Wang, Zhongqing",
title="Theme Trends and Knowledge Structure on Mobile Health Apps: Bibliometric Analysis",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jul",
day="27",
volume="8",
number="7",
pages="e18212",
keywords="mobile app",
keywords="mobile health",
keywords="mhealth",
keywords="digital health",
keywords="digital medicine",
keywords="bibliometrics",
keywords="co-word analysis",
keywords="mobile phone",
keywords="VOSviewer",
abstract="Background: Due to the widespread and unprecedented popularity of mobile phones, the use of digital medicine and mobile health apps has seen significant growth. Mobile health apps have tremendous potential for monitoring and treating diseases, improving patient care, and promoting health. Objective: This paper aims to explore research trends, coauthorship networks, and the research hot spots of mobile health app research. Methods: Publications related to mobile health apps were retrieved and extracted from the Web of Science database with no language restrictions. Bibliographic Item Co-Occurrence Matrix Builder was employed to extract bibliographic information (publication year and journal source) and perform a descriptive analysis. We then used the VOSviewer (Leiden University) tool to construct and visualize the co-occurrence networks of researchers, research institutions, countries/regions, citations, and keywords. Results: We retrieved 2802 research papers on mobile health apps published from 2000 to 2019. The number of annual publications increased over the past 19 years. JMIR mHealth and uHealth (323/2802, 11.53\%), Journal of Medical Internet Research (106/2802, 3.78\%), and JMIR Research Protocols (82/2802, 2.93\%) were the most common journals for these publications. The United States (1186/2802, 42.33\%), England (235/2802, 8.39\%), Australia (215/2802, 7.67\%), and Canada (112/2802, 4.00\%) were the most productive countries of origin. The University of California San Francisco, the University of Washington, and the University of Toronto were the most productive institutions. As for the authors' contributions, Schnall R, Kuhn E, Lopez-Coronado M, and Kim J were the most active researchers. The co-occurrence cluster analysis of the top 100 keywords forms 5 clusters: (1) the technology and system development of mobile health apps; (2) mobile health apps for mental health; (3) mobile health apps in telemedicine, chronic disease, and medication adherence management; (4) mobile health apps in health behavior and health promotion; and (5) mobile health apps in disease prevention via the internet. Conclusions: We summarize the recent advances in mobile health app research and shed light on their research frontier, trends, and hot topics through bibliometric analysis and network visualization. These findings may provide valuable guidance on future research directions and perspectives in this rapidly developing field. ",
doi="10.2196/18212",
url="https://mhealth.jmir.org/2020/7/e18212",
url="http://www.ncbi.nlm.nih.gov/pubmed/32716312"
}


@Article{info:doi/10.2196/16899,
author="Robles, Noem{\'i}
and Puigdom{\`e}nech Puig, Elisa
and G{\'o}mez-Calder{\'o}n, Corpus
and Saig{\'i}-Rubi{\'o}, Francesc
and Cuatrecasas Cambra, Guillem
and Zamora, Alberto
and Moharra, Montse
and Paluzi{\'e}, Guillermo
and Balfeg{\'o}, Mariona
and Carrion, Carme",
title="Evaluation Criteria for Weight Management Apps: Validation Using a Modified Delphi Process",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jul",
day="22",
volume="8",
number="7",
pages="e16899",
keywords="mHealth",
keywords="technology assessment",
keywords="obesity",
keywords="overweight",
keywords="Delphi technique",
keywords="consensus",
abstract="Background: The use of apps for weight management has increased over recent years; however, there is a lack of evidence regarding the efficacy and safety of these apps. The EVALAPPS project will develop and validate an assessment instrument to specifically assess the safety and efficacy of weight management apps. Objective: The aim of this study was to reach a consensus among stakeholders on a comprehensive set of criteria to guide development of the EVALAPPS assessment instrument. A modified Delphi process was used in order to verify the robustness of the criteria that had been identified through a literature review and to prioritize a set of the identified criteria. Methods: Stakeholders (n=31) were invited to participate in a 2-round Delphi process with 114 initial criteria that had been identified from the literature. In round 1, participants rated criteria according to relevance on a scale from 0 (``I suggest this criterion is excluded'') to 5 (``This criterion is extremely relevant''). A criterion was accepted if the median rating was 4 or higher and if the relative intraquartile range was equal to 0.67 or lower. In round 2, participants were asked about criteria that had been discarded in round 1. A prioritization strategy was used to identify crucial criteria according to (1) the importance attributed by participants (criteria with a mean rating of 4.00 or higher), (2) the level of consensus (criteria with a score of 4 or 5 by at least 80\% of the participants). Results: The response rate was 83.9\% (26/31) in round 1 and 90.3\% (28/31) in round 2. A total of 107 out of 114 criteria (93.9\%) were accepted by consensus---105 criteria in round 1 and 2 criteria in round 2. After prioritization, 53 criteria were deemed crucial. These related mainly to the dimensions of security and privacy (13/53, 24.5\%) and usability (9/53, 17.0\%), followed by activity data (5/53, 9.4\%), clinical effectiveness (5/53, 9.4\%), and reliability (5/53, 9.4\%). Conclusions: Results confirmed the robustness of the criteria that were identified, with those relating to security and privacy being deemed most relevant by stakeholders. Additionally, a specific set of criteria based on health indicators (activity data, physical state data, and personal data) was also prioritized. ",
doi="10.2196/16899",
url="http://mhealth.jmir.org/2020/7/e16899/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32706689"
}


@Article{info:doi/10.2196/19364,
author="Huberty, Jennifer
and Eckert, Ryan
and Puzia, Megan
and Laird, Breanne
and Larkey, Linda
and Mesa, Ruben",
title="A Novel Educational Control Group Mobile App for Meditation Interventions: Single-Group Feasibility Trial",
journal="JMIR Form Res",
year="2020",
month="Jul",
day="21",
volume="4",
number="7",
pages="e19364",
keywords="feasibility",
keywords="smartphone",
keywords="mHealth",
keywords="digital health",
keywords="cancer",
keywords="beta test",
abstract="Background: Smartphone ownership is becoming ubiquitous among US adults, making the delivery of health interventions via a mobile app (ie, mobile health [mHealth]) attractive to many researchers and clinicians. Meditation interventions have become popular and have been delivered to study participants via mobile apps to improve a range of health outcomes in both healthy adults and those with chronic diseases. However, these meditation mHealth interventions have been limited by a lack of high-quality control groups. More specifically, these studies have lacked consistency in their use of active, time-matched, and attention-matched control groups. Objective: The purpose of this study is to beta test a novel health education podcast control condition delivered via a smartphone app that would be a strong comparator to be used in future studies of app-based meditation interventions. Methods: Patients with myeloproliferative neoplasm (MPN) cancer were recruited nationally. Upon enrollment, participants were informed to download the investigator-developed health education podcast app onto their mobile phone and listen to {\textasciitilde}60 min/week of cancer-related educational podcasts for 12 weeks. The benchmarks for feasibility included ?70\% of participants completing ?70\% of the prescribed 60 min/week of podcasts, ?70\% of participants reporting that they were satisfied with the intervention, and ?70\% of participants reporting that they enjoyed the health education podcasts. Results: A total of 96 patients with MPN were enrolled in the study; however, 19 never began the intervention. Of the 77 patients who participated in the intervention, 39 completed the entire study (ie, sustained participation through the follow-up period). Participation averaged 103.2 (SD 29.5) min/week. For 83.3\% (10/12) of the weeks, at least 70\% of participants completed at least 70\% of their total prescribed use. Almost half of participants reported that they enjoyed the health education podcasts (19/39, 48.7\%) and were satisfied with the intervention (17/39, 43.6\%). There were no significant changes in cancer-related outcomes from baseline to postintervention. Conclusions: A 12-week, health education podcast mobile app was demanded but not accepted in a sample of patients with cancer. Using the mobile app was not associated with significant changes in cancer-related symptoms. Based on findings from this study, a health education podcast mobile app may be a feasible option as a time- and attention-matched control group for efficacy trials with more extensive formative research for the content of the podcasts and its acceptability by the specific population. Trial Registration: ClinicalTrials.gov NCT03907774; https://clinicaltrials.gov/ct2/show/NCT03907774 ",
doi="10.2196/19364",
url="http://formative.jmir.org/2020/7/e19364/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32706719"
}


@Article{info:doi/10.2196/17703,
author="Cornet, Philip Victor
and Toscos, Tammy
and Bolchini, Davide
and Rohani Ghahari, Romisa
and Ahmed, Ryan
and Daley, Carly
and Mirro, J. Michael
and Holden, J. Richard",
title="Untold Stories in User-Centered Design of Mobile Health: Practical Challenges and Strategies Learned From the Design and Evaluation of an App for Older Adults With Heart Failure",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jul",
day="21",
volume="8",
number="7",
pages="e17703",
keywords="user-centered design",
keywords="research methods",
keywords="mobile health",
keywords="digital health",
keywords="mobile apps",
keywords="usability",
keywords="technology",
keywords="evaluation",
keywords="human-computer interaction",
keywords="mobile phone",
abstract="Background: User-centered design (UCD) is a powerful framework for creating useful, easy-to-use, and satisfying mobile health (mHealth) apps. However, the literature seldom reports the practical challenges of implementing UCD, particularly in the field of mHealth. Objective: This study aims to characterize the practical challenges encountered and propose strategies when implementing UCD for mHealth. Methods: Our multidisciplinary team implemented a UCD process to design and evaluate a mobile app for older adults with heart failure. During and after this process, we documented the challenges the team encountered and the strategies they used or considered using to address those challenges. Results: We identified 12 challenges, 3 about UCD as a whole and 9 across the UCD stages of formative research, design, and evaluation. Challenges included the timing of stakeholder involvement, overcoming designers' assumptions, adapting methods to end users, and managing heterogeneity among stakeholders. To address these challenges, practical recommendations are provided to UCD researchers and practitioners. Conclusions: UCD is a gold standard approach that is increasingly adopted for mHealth projects. Although UCD methods are well-described and easily accessible, practical challenges and strategies for implementing them are underreported. To improve the implementation of UCD for mHealth, we must tell and learn from these traditionally untold stories. ",
doi="10.2196/17703",
url="http://mhealth.jmir.org/2020/7/e17703/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32706745"
}


@Article{info:doi/10.2196/16844,
author="van Haasteren, Afua
and Vayena, Effy
and Powell, John",
title="The Mobile Health App Trustworthiness Checklist: Usability Assessment",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jul",
day="21",
volume="8",
number="7",
pages="e16844",
keywords="checklist",
keywords="trustworthiness",
keywords="trust",
keywords="mobile health apps",
keywords="validation",
keywords="survey",
abstract="Background: The mobile health (mHealth) app trustworthiness (mHAT) checklist was created to identify end users' opinions on the characteristics of trustworthy mHealth apps and to communicate this information to app developers. To ensure that the checklist is suited for all relevant stakeholders, it is necessary to validate its contents. Objective: The purpose of this study was to assess the feasibility of the mHAT checklist by modifying its contents according to ratings and suggestions from stakeholders familiar with the process of developing, managing, or curating mHealth apps. Methods: A 44-item online survey was administered to relevant stakeholders. The survey was largely comprised of the mHAT checklist items, which respondents rated on a 5-point Likert scale, ranging from completely disagree (1) to completely agree (5). Results: In total, seven professional backgrounds were represented in the survey: administrators (n=6), health professionals (n=7), information technology personnel (n=6), managers (n=2), marketing personnel (n=3), researchers (n=5), and user experience researchers (n=8). Aside from one checklist item---``the app can inform end users about errors in measurements''---the combined positive ratings (ie, completely agree and agree) of the checklist items overwhelmingly exceeded the combined negative ratings (ie, completely disagree and disagree). Meanwhile, two additional items were included in the checklist: (1) business or funding model of the app and (2) details on app uninstallation statistics. Conclusions: Our results indicate that the mHAT checklist is a valuable resource for a broad range of stakeholders to develop trustworthy mHealth apps. Future studies should examine if the checklist works best for certain mHealth apps or in specific settings. ",
doi="10.2196/16844",
url="http://mhealth.jmir.org/2020/7/e16844/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32706733"
}


@Article{info:doi/10.2196/18480,
author="Larbi, Dillys
and Randine, Pietro
and {\AA}rsand, Eirik
and Antypas, Konstantinos
and Bradway, Meghan
and Gabarron, Elia",
title="Methods and Evaluation Criteria for Apps and Digital Interventions for Diabetes Self-Management: Systematic Review",
journal="J Med Internet Res",
year="2020",
month="Jul",
day="6",
volume="22",
number="7",
pages="e18480",
keywords="self-management",
keywords="diabetes mellitus",
keywords="mobile applications",
keywords="computer communication networks",
keywords="mHealth",
keywords="eHealth",
keywords="health care evaluation mechanisms",
abstract="Background: There is growing evidence that apps and digital interventions have a positive impact on diabetes self-management. Standard self-management for patients with diabetes could therefore be supplemented by apps and digital interventions to increase patients' skills. Several initiatives, models, and frameworks suggest how health apps and digital interventions could be evaluated, but there are few standards for this. And although there are many methods for evaluating apps and digital interventions, a more specific approach might be needed for assessing digital diabetes self-management interventions. Objective: This review aims to identify which methods and criteria are used to evaluate apps and digital interventions for diabetes self-management, and to describe how patients were involved in these evaluations. Methods: We searched CINAHL, EMBASE, MEDLINE, and Web of Science for articles published from 2015 that referred to the evaluation of apps and digital interventions for diabetes self-management and involved patients in the evaluation. We then conducted a narrative qualitative synthesis of the findings, structured around the included studies' quality, methods of evaluation, and evaluation criteria. Results: Of 1681 articles identified, 31 fulfilled the inclusion criteria. A total of 7 articles were considered of high confidence in the evidence. Apps were the most commonly used platform for diabetes self-management (18/31, 58\%), and type 2 diabetes (T2D) was the targeted health condition most studies focused on (12/31, 38\%). Questionnaires, interviews, and user-group meetings were the most common methods of evaluation. Furthermore, the most evaluated criteria for apps and digital diabetes self-management interventions were cognitive impact, clinical impact, and usability. Feasibility and security and privacy were not evaluated by studies considered of high confidence in the evidence. Conclusions: There were few studies with high confidence in the evidence that involved patients in the evaluation of apps and digital interventions for diabetes self-management. Additional evaluation criteria, such as sustainability and interoperability, should be focused on more in future studies to provide a better understanding of the effects and potential of apps and digital interventions for diabetes self-management. ",
doi="10.2196/18480",
url="https://www.jmir.org/2020/7/e18480",
url="http://www.ncbi.nlm.nih.gov/pubmed/32628125"
}


@Article{info:doi/10.2196/15909,
author="Melin, Jeanette
and Bonn, Erika Stephanie
and Pendrill, Leslie
and Trolle Lagerros, Ylva",
title="A Questionnaire for Assessing User Satisfaction With Mobile Health Apps: Development Using Rasch Measurement Theory",
journal="JMIR Mhealth Uhealth",
year="2020",
month="May",
day="26",
volume="8",
number="5",
pages="e15909",
keywords="cell phone",
keywords="healthy lifestyle",
keywords="methods",
keywords="mobile applications",
keywords="psychometrics",
keywords="smartphone",
keywords="telemedicine",
keywords="mobile phone",
abstract="Background: Mobile health (mHealth) apps offer great opportunities to deliver large-scale, cost-efficient digital solutions for implementing lifestyle changes. Furthermore, many mHealth apps act as medical devices. Yet, there is little research on how to assess user satisfaction with an mHealth solution. Objective: This study presents the development of the mHealth Satisfaction Questionnaire and evaluates its measurement properties. Methods: Respondents who took part in the Health Integrator Study and were randomized to use the Health Integrator smartphone app for lifestyle changes (n=112), with and without additional telephone coaching, rated their satisfaction with the app using the new 14-item mHealth Satisfaction Questionnaire. The ratings were given on a 5-point Likert scale and measurement properties were evaluated using Rasch measurement theory (RMT). Results: Optimal scoring was reached when response options 2, 3, and 4 were collapsed, giving three response categories. After omitting two items that did not fit into the scale, fit residuals were within, or close to, the recommended range of {\textpm}2.5. There was no differential item functioning between intervention group, age group, or sex. The Person Separation Index was 0.79, indicating that the scale's ability to discriminate correctly between person leniency was acceptable for group comparisons but not for individual evaluations. The scale did not meet the criterion of unidimensionality; 16.1\% (18/112) of the respondents were outside the desired range of ?1.96 to 1.96. In addition, several items showed local dependency and three underlying dimensions emerged: negative experiences, positive experiences, and lifestyle consequences of using the mHealth solution. Conclusions: In times where mHealth apps and digital solutions are given more attention, the mHealth Satisfaction Questionnaire provides a new possibility to measure user satisfaction to ensure usability and improve development of new apps. Our study is one of only a few cases where RMT has been used to evaluate the usability of such an instrument. There is, though, a need for further development of the mHealth Satisfaction Questionnaire, including the addition of more items and consideration of further response options. The mHealth Satisfaction Questionnaire should also be evaluated in a larger sample and with other mHealth apps and in other contexts. Trial Registration: ClinicalTrials.gov NCT03579342; http://clinicaltrials.gov/ct2/show/NCT03579342. ",
doi="10.2196/15909",
url="http://mhealth.jmir.org/2020/5/e15909/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32452817"
}


@Article{info:doi/10.2196/14826,
author="Wang, Fuzhi
and Wang, Zhuoxin
and Sun, Weiwei
and Yang, Xiumu
and Bian, Zhiwei
and Shen, Lining
and Pan, Wei
and Liu, Peng
and Chen, Xingzhi
and Fu, Lianguo
and Zhang, Fan
and Luo, Dan",
title="Evaluating the Quality of Health-Related WeChat Public Accounts: Cross-Sectional Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="May",
day="8",
volume="8",
number="5",
pages="e14826",
keywords="health-related WeChat Public Account",
keywords="HONcode",
keywords="suitability assessment of material",
keywords="evaluation",
keywords="social media",
keywords="mHealth",
keywords="app",
keywords="health information",
keywords="internet",
abstract="Background: As representatives of health information communication platforms accessed through mobile phones and mobile terminals, health-related WeChat public accounts (HWPAs) have a large consumer base in the Chinese-speaking world. However, there is still a lack of general understanding of the status quo of HWPAs and the quality of the articles they release. Objective: The aims of this study were to assess the conformity of HWPAs to the Health on the Net Foundation Code of Conduct (HONcode) and to evaluate the suitability of articles disseminated by HWPAs. Methods: The survey was conducted from April 23 to May 5, 2019. Based on the monthly (March 1-31, 2019) WeChat Index provided by Qingbo Big Data, the top 100 HWPAs were examined to evaluate their HONcode compliance. The first four articles published by each HWPA on the survey dates were selected as samples to evaluate their suitability. All materials were assessed by three raters. The materials were assessed using the HONcode checklist and the Suitability Assessment of Materials (SAM) score sheet. Data analysis was performed with SPSS version 17.0 (SPSS Inc, Chicago, IL, USA) and Excel version 2013 (Microsoft Inc, Washington DC, USA). Results: A total of 93 HWPAs and 210 of their released articles were included in this study. For six of the eight principles, the 93 HWPAs nearly consistently did not meet the requirements of the HONcode. The HWPAs certified by Tencent Corporation (66/93, 71\%) were generally slightly superior to those without such certification (27/93, 29\%) in terms of compliance with HONcode principles. The mean SAM score for the 210 articles was 67.72 (SD 10.930), which indicated ``adequate'' suitability. There was no significant difference between the SAM scores of the articles published by certified and uncertified HWPAs (P=.07), except in the literacy requirements dimension (tdf=97=--2.418, P=.02). Conclusions: The HWPAs had low HONcode conformity. Although the suitability of health information released by HWPAs was at a moderate level, there were still problems identified, such as difficulty in tracing information sources, excessive implicit advertisements, and irregular usage of charts. In addition, the low approval requirements of HWPAs were not conducive to improvement of their service quality. ",
doi="10.2196/14826",
url="https://mhealth.jmir.org/2020/5/e14826",
url="http://www.ncbi.nlm.nih.gov/pubmed/32383684"
}


@Article{info:doi/10.2196/11567,
author="Kan, Wei-Chih
and Chou, Willy
and Chien, Tsair-Wei
and Yeh, Yu-Tsen
and Chou, Po-Hsin",
title="The Most-Cited Authors Who Published Papers in JMIR mHealth and uHealth Using the Authorship-Weighted Scheme: Bibliometric Analysis",
journal="JMIR Mhealth Uhealth",
year="2020",
month="May",
day="7",
volume="8",
number="5",
pages="e11567",
keywords="betweenness centrality",
keywords="authorship collaboration",
keywords="Google Maps",
keywords="social network analysis",
keywords="knowledge concept map",
keywords="the author-weighted scheme",
abstract="Background: Many previous papers have investigated most-cited articles or most productive authors in academics, but few have studied most-cited authors. Two challenges are faced in doing so, one of which is that some different authors will have the same name in the bibliometric data, and the second is that coauthors' contributions are different in the article byline. No study has dealt with the matter of duplicate names in bibliometric data. Although betweenness centrality (BC) is one of the most popular degrees of density in social network analysis (SNA), few have applied the BC algorithm to interpret a network's characteristics. A quantitative scheme must be used for calculating weighted author credits and then applying the metrics in comparison. Objective: This study aimed to apply the BC algorithm to examine possible identical names in a network and report the most-cited authors for a journal related to international mobile health (mHealth) research. Methods: We obtained 676 abstracts from Medline based on the keywords ``JMIR mHealth and uHealth'' (Journal) on June 30, 2018. The author names, countries/areas, and author-defined keywords were recorded. The BCs were then calculated for the following: (1) the most-cited authors displayed on Google Maps; (2) the geographical distribution of countries/areas for the first author; and (3) the keywords dispersed by BC and related to article topics in comparison on citation indices. Pajek software was used to yield the BC for each entity (or node). Bibliometric indices, including h-, g-, and x-indexes, the mean of core articles on g(Ag)=sum (citations on g-core/publications on g-core), and author impact factor (AIF), were applied. Results: We found that the most-cited author was Sherif M Badawy (from the United States), who had published six articles on JMIR mHealth and uHealth with high bibliometric indices (h=3; AIF=8.47; x=4.68; Ag=5.26). We also found that the two countries with the highest BC were the United States and the United Kingdom and that the two keyword clusters of mHealth and telemedicine earned the highest indices in comparison to other counterparts. All visual representations were successfully displayed on Google Maps. Conclusions: The most cited authors were selected using the authorship-weighted scheme (AWS), and the keywords of mHealth and telemedicine were more highly cited than other counterparts. The results on Google Maps are novel and unique as knowledge concept maps for understanding the feature of a journal. The research approaches used in this study (ie, BC and AWS) can be applied to other bibliometric analyses in the future. ",
doi="10.2196/11567",
url="https://mhealth.jmir.org/2020/5/e11567",
url="http://www.ncbi.nlm.nih.gov/pubmed/32379053"
}


@Article{info:doi/10.2196/16814,
author="Bradway, Meghan
and Gabarron, Elia
and Johansen, Monika
and Zanaboni, Paolo
and Jardim, Patricia
and Joakimsen, Ragnar
and Pape-Haugaard, Louise
and {\AA}rsand, Eirik",
title="Methods and Measures Used to Evaluate Patient-Operated Mobile Health Interventions: Scoping Literature Review",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Apr",
day="30",
volume="8",
number="4",
pages="e16814",
keywords="mobile health",
keywords="apps",
keywords="self-management",
keywords="chronic disease",
keywords="noncommunicable diseases",
keywords="interventions",
keywords="patient-centered approach",
keywords="patient-operated intervention",
abstract="Background: Despite the prevalence of mobile health (mHealth) technologies and observations of their impacts on patients' health, there is still no consensus on how best to evaluate these tools for patient self-management of chronic conditions. Researchers currently do not have guidelines on which qualitative or quantitative factors to measure or how to gather these reliable data. Objective: This study aimed to document the methods and both qualitative and quantitative measures used to assess mHealth apps and systems intended for use by patients for the self-management of chronic noncommunicable diseases. Methods: A scoping review was performed, and PubMed, MEDLINE, Google Scholar, and ProQuest Research Library were searched for literature published in English between January 1, 2015, and January 18, 2019. Search terms included combinations of the description of the intention of the intervention (eg, self-efficacy and self-management) and description of the intervention platform (eg, mobile app and sensor). Article selection was based on whether the intervention described a patient with a chronic noncommunicable disease as the primary user of a tool or system that would always be available for self-management. The extracted data included study design, health conditions, participants, intervention type (app or system), methods used, and measured qualitative and quantitative data. Results: A total of 31 studies met the eligibility criteria. Studies were classified as either those that evaluated mHealth apps (ie, single devices; n=15) or mHealth systems (ie, more than one tool; n=17), and one study evaluated both apps and systems. App interventions mainly targeted mental health conditions (including Post-Traumatic Stress Disorder), followed by diabetes and cardiovascular and heart diseases; among the 17 studies that described mHealth systems, most involved patients diagnosed with cardiovascular and heart disease, followed by diabetes, respiratory disease, mental health conditions, cancer, and multiple illnesses. The most common evaluation method was collection of usage logs (n=21), followed by standardized questionnaires (n=18) and ad-hoc questionnaires (n=13). The most common measure was app interaction (n=19), followed by usability/feasibility (n=17) and patient-reported health data via the app (n=15). Conclusions: This review demonstrates that health intervention studies are taking advantage of the additional resources that mHealth technologies provide. As mHealth technologies become more prevalent, the call for evidence includes the impacts on patients' self-efficacy and engagement, in addition to traditional measures. However, considering the unstructured data forms, diverse use, and various platforms of mHealth, it can be challenging to select the right methods and measures to evaluate mHealth technologies. The inclusion of app usage logs, patient-involved methods, and other approaches to determine the impact of mHealth is an important step forward in health intervention research. We hope that this overview will become a catalogue of the possible ways in which mHealth has been and can be integrated into research practice. ",
doi="10.2196/16814",
url="https://mhealth.jmir.org/2020/4/e16814",
url="http://www.ncbi.nlm.nih.gov/pubmed/32352394"
}


@Article{info:doi/10.2196/17258,
author="Guo, Xitong
and Chen, Shuqing
and Zhang, Xiaofei
and Ju, Xiaofeng
and Wang, Xifu",
title="Exploring Patients' Intentions for Continuous Usage of mHealth Services: Elaboration-Likelihood Perspective Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Apr",
day="6",
volume="8",
number="4",
pages="e17258",
keywords="mHealth services",
keywords="health consciousness",
keywords="elaboration-likelihood model",
keywords="health behavior",
keywords="patients' continuous usage",
abstract="Background: With the increasingly rapid development of Web 2.0 technologies, the application of mobile health (mHealth) care in the field of health management has become popular. Accordingly, patients are able to access consulting services and effective health information online without temporal and geographical constraints. The elaboration-likelihood model (ELM) is a dual-process persuasion theory that describes the change of attitudes and behavior. Objective: In this study, we drew on the ELM to investigate patients' continuous usage intentions regarding mHealth services. In addition, we further examined which route---central or peripheral---has a stronger impact on a patient's usage of health care management. Methods: To meet these objectives, five hypotheses were developed and empirically validated using a field survey to test the direct and indirect effects, via attitude, of the two routes on continuous usage intention. Results: We found that patients' perceived mHealth information quality and perceived mHealth system quality had a positive effect on their personal attitudes. The results revealed that social media influence had a positive effect on a patient's attitude toward mHealth services. In particular, our findings suggest that a patient's health consciousness has a positive effect on the relationship between social media influence and attitude. Conclusions: This study contributes to the mHealth services literature by introducing the ELM as a referent theory for research, as well as by specifying the moderating role of health consciousness. For practitioners, this study introduces influence processes as policy tools that managers can employ to motivate the uptake of mHealth services within their organizations. ",
doi="10.2196/17258",
url="https://mhealth.jmir.org/2020/4/e17258",
url="http://www.ncbi.nlm.nih.gov/pubmed/32250277"
}


@Article{info:doi/10.2196/14479,
author="Messner, Eva-Maria
and Terhorst, Yannik
and Barke, Antonia
and Baumeister, Harald
and Stoyanov, Stoyan
and Hides, Leanne
and Kavanagh, David
and Pryss, R{\"u}diger
and Sander, Lasse
and Probst, Thomas",
title="The German Version of the Mobile App Rating Scale (MARS-G): Development and Validation Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Mar",
day="27",
volume="8",
number="3",
pages="e14479",
keywords="mHealth",
keywords="Mobile App Rating Scale",
keywords="mobile app",
keywords="assessment",
keywords="rating",
keywords="scale development",
abstract="Background: The number of mobile health apps (MHAs), which are developed to promote healthy behaviors, prevent disease onset, manage and cure diseases, or assist with rehabilitation measures, has exploded. App store star ratings and descriptions usually provide insufficient or even false information about app quality, although they are popular among end users. A rigorous systematic approach to establish and evaluate the quality of MHAs is urgently needed. The Mobile App Rating Scale (MARS) is an assessment tool that facilitates the objective and systematic evaluation of the quality of MHAs. However, a German MARS is currently not available. Objective: The aim of this study was to translate and validate a German version of the MARS (MARS-G). Methods: The original 19-item MARS was forward and backward translated twice, and the MARS-G was created. App description items were extended, and 104 MHAs were rated twice by eight independent bilingual researchers, using the MARS-G and MARS. The internal consistency, validity, and reliability of both scales were assessed. Mokken scale analysis was used to investigate the scalability of the overall scores. Results: The retranslated scale showed excellent alignment with the original MARS. Additionally, the properties of the MARS-G were comparable to those of the original MARS. The internal consistency was good for all subscales (ie, omega ranged from 0.72 to 0.91). The correlation coefficients (r) between the dimensions of the MARS-G and MARS ranged from 0.93 to 0.98. The scalability of the MARS (H=0.50) and MARS-G (H=0.48) were good. Conclusions: The MARS-G is a reliable and valid tool for experts and stakeholders to assess the quality of health apps in German-speaking populations. The overall score is a reliable quality indicator. However, further studies are needed to assess the factorial structure of the MARS and MARS-G. ",
doi="10.2196/14479",
url="http://mhealth.jmir.org/2020/3/e14479/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32217504"
}


@Article{info:doi/10.2196/13561,
author="Gao, Ye
and Dai, Hongliang
and Jia, Guizhi
and Liang, Chunguang
and Tong, Tong
and Zhang, Zhiyu
and Song, Ruobing
and Wang, Qing
and Zhu, Yue",
title="Translation of the Chinese Version of the Nomophobia Questionnaire and Its Validation Among College Students: Factor Analysis",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Mar",
day="13",
volume="8",
number="3",
pages="e13561",
keywords="nomophobia",
keywords="reliability",
keywords="validity",
keywords="mobile phone",
abstract="Background: Nomophobia or phobia of no mobile phone is the fear of being without a mobile phone or being unable to contact others via a mobile phone. It is a newly emerging psychiatric disorder among mobile phone users. Objective: There are no psychometric scales available in China for examining nomophobia, although China has become the largest mobile phone handset consumer market in the world. Therefore, this study aimed to translate the original English version of a psychometric scale into Chinese and further examine its reliability and validity among Chinese college students. Methods: The original version of the Nomophobia Questionnaire (NMP-Q) was first translated into Chinese using the backward and forward translation procedure. An exploratory factor analysis (a principal component analysis plus varimax rotation) and a confirmatory factor analysis (CFA) were performed to examine the underlying factor structure of the translated questionnaire. The internal consistency reliability of the scale was determined by computing the Cronbach alpha coefficient, the test-retest reliability, and the corrected item-total correlation. A multivariate regression analysis was used for examining associations between nomophobia and independent variables among the college students. Results: A total of 2000 participants were included in the study. Their ages ranged from 16 to 25 years, with 51.95\% (1039/2000) being male participants. The Chinese version of NMP-Q retained 18 items. The eigenvalues, total variance explained, and scree plot jointly support a 4-factor structure of the translated questionnaire. The CFA reached the adaptive standard, and the discriminant validity of the scale was good. The Cronbach alpha coefficient of this scale was .925, and the Cronbach alpha coefficients of the subscales were .882, .843, .895, and .818. The test-retest reliability was 0.947. Corrected item-total correlation ranged from 0.539 to 0.663. The significant predictors for each of the dimensions of nomophobia and total score of the questionnaire were the average number of hours spent on a mobile phone daily and gender. Conclusions: The Chinese version of the NMP-Q exhibited satisfactory psychometric properties. ",
doi="10.2196/13561",
url="http://mhealth.jmir.org/2020/3/e13561/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32167480"
}


@Article{info:doi/10.2196/13057,
author="Llorens-Vernet, Pere
and Mir{\'o}, Jordi",
title="Standards for Mobile Health--Related Apps: Systematic Review and Development of a Guide",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Mar",
day="3",
volume="8",
number="3",
pages="e13057",
keywords="mHealth",
keywords="mobile apps",
keywords="review",
keywords="medical device",
keywords="standards",
abstract="Background: In recent years, the considerable increase in the number of mobile health (mHealth) apps has made health care more accessible and affordable for all. However, the exponential growth in mHealth solutions has occurred with almost no control or regulation of any kind. Despite some recent initiatives, there is still no specific regulation procedure, accreditation system, or standards to help the development of the apps, mitigate risks, or guarantee quality. Objective: The main aim of this study was to propose a set of criteria for mHealth-related apps on the basis of what is available from published studies, guidelines, and standards in the various areas that are related to health app development. Methods: We used three sources of information to identify the most important criteria. First, we conducted a systematic review of all the studies published on pain-related apps. Second, we searched for health app recommendations on the websites of professional organizations. Third, we looked for standards governing the development of software for medical devices on the specialized websites of regulatory organizations. Then, we grouped and subsumed the criteria we had identified on the basis of their shared characteristics. Finally, the comprehensibility and perceived importance of the resulting criteria were evaluated for face validity with a group of 18 stakeholders. Results: We identified a total of 503 criteria from all sources, which, after close analysis, were grouped into eight different categories, including 36 important criteria for health apps. The resulting categories were usability, privacy, security, appropriateness and suitability, transparency and content, safety, technical support and updates, and technology. The results of the preliminary analysis showed that the criteria were mostly understood by the group of stakeholders. In addition, they perceived all of them as important. Conclusions: This set of criteria can help health care providers, developers, patients, and other stakeholders to guide the development of mHealth-related apps and, potentially, to measure the quality of an mHealth app. ",
doi="10.2196/13057",
url="https://mhealth.jmir.org/2020/3/e13057",
url="http://www.ncbi.nlm.nih.gov/pubmed/32130169"
}


@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/10.2196/16316,
author="W{\aa}ngdahl, Josefin
and Jaensson, Maria
and Dahlberg, Karuna
and Nilsson, Ulrica",
title="The Swedish Version of the Electronic Health Literacy Scale: Prospective Psychometric Evaluation Study Including Thresholds Levels",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Feb",
day="24",
volume="8",
number="2",
pages="e16316",
keywords="eHealth",
keywords="literacy",
keywords="internet",
keywords="psychometrics",
abstract="Background: To enhance the efficacy of information and communication, health care has increasingly turned to digitalization. Electronic health (eHealth) is an important factor that influences the use and receipt of benefits from Web-based health resources. Consequently, the concept of eHealth literacy has emerged, and in 2006 Norman and Skinner developed an 8-item self-report instrument to measure these skills: the eHealth Literacy Scale (eHEALS). However, the eHEALS has not been tested for reliability and validity in the general Swedish population and no threshold values have been established. Objective: The aim of this study was to translate and adapt eHEALS into a Swedish version; evaluate convergent validity and psychometric properties; and determine threshold levels for inadequate, problematic, and sufficient eHealth literacy. Methods: Prospective psychometric evaluation study included 323 participants equally distributed between sexes with a mean age of 49 years recruited from 12 different arenas. Results: There were some difficulties translating the English concept health resources. This resulted in this concept being translated as health information (ie, H{\"a}lsoinformation in Swedish). The eHEALS total score was 29.3 (SD 6.2), Cronbach alpha .94, Spearman-Brown coefficient .96, and response rate 94.6\%. All a priori hypotheses were confirmed, supporting convergent validity. The test-retest reliability indicated an almost perfect agreement, .86 (P<.001). An exploratory factor analysis found one component explaining 64\% of the total variance. No floor or ceiling effect was noted. Thresholds levels were set at 8 to 20 = inadequate, 21 to 26 = problematic, and 27 to 40 = sufficient, and there were no significant differences in distribution of the three levels between the Swedish version of eHEALS and the HLS-EU-Q16. Conclusions: The Swedish version of eHEALS was assessed as being unidimensional with high internal consistency of the instrument, making the reliability adequate. Adapted threshold levels for inadequate, problematic, and sufficient levels of eHealth literacy seem to be relevant. However, there are some linguistic issues relating to the concept of health resources. ",
doi="10.2196/16316",
url="https://mhealth.jmir.org/2020/2/e16316",
url="http://www.ncbi.nlm.nih.gov/pubmed/32130168"
}


@Article{info:doi/10.2196/14661,
author="Wang, Jiani
and Rogge, A. Aliz{\'e}
and Armour, Mike
and Smith, A. Caroline
and D'Adamo, R. Christopher
and Pischke, R. Claudia
and Yen, Hung-Rong
and Wu, Mei-Yao
and Mor{\'e}, Ocampo Ari Ojeda
and Witt, M. Claudia
and Pach, Daniel",
title="International ResearchKit App for Women with Menstrual Pain: Development, Access, and Engagement",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Feb",
day="11",
volume="8",
number="2",
pages="e14661",
keywords="dysmenorrhea",
keywords="mHealth",
keywords="mobile applications",
keywords="acupressure",
keywords="pain",
keywords="behavior change techniques (BCTs)",
keywords="ResearchKit",
keywords="recruitment",
abstract="Background: Primary dysmenorrhea is a common condition in women of reproductive age. A previous app-based study undertaken by our group demonstrated that a smartphone app supporting self-acupressure introduced by a health care professional can reduce menstrual pain. Objective: This study aims to evaluate whether a specific smartphone app is effective in reducing menstrual pain in 18- to 34-year-old women with primary dysmenorrhea in a self-care setting. One group of women has access to the full-featured study app and will be compared with 2 control groups who have access to fewer app features. Here, we report the trial design, app development, user access, and engagement. Methods: On the basis of the practical implications of the previous app-based study, we revised and reengineered the study app and included the ResearchKit (Apple Inc) framework. Behavior change techniques (BCTs) were implemented in the app and validated by expert ratings. User access was estimated by assessing recruitment progress over time. User evolution and baseline survey respondent rate were assessed to evaluate user engagement. Results: The development of the study app for a 3-armed randomized controlled trial required a multidisciplinary team. The app is accessible for the target population free of charge via the Apple App Store. In Germany, within 9 months, the app was downloaded 1458 times and 328 study participants were recruited using it without external advertising. A total of 98.27\% (5157/5248) of the app-based baseline questions were answered. The correct classification of BCTs used in the app required psychological expertise. Conclusions: Conducting an innovative app study requires multidisciplinary effort. Easy access and engagement with such an app can be achieved by recruitment via the App Store. Future research is needed to investigate the determinants of user engagement, optimal BCT application, and potential clinical and self-care scenarios for app use. Trial Registration: ClinicalTrials.gov NCT03432611; https://clinicaltrials.gov/ct2/show/NCT03432611 (Archived by WebCite at http://www.webcitation.org/75LLAcnCQ). ",
doi="10.2196/14661",
url="https://mhealth.jmir.org/2020/2/e14661",
url="http://www.ncbi.nlm.nih.gov/pubmed/32058976"
}


@Article{info:doi/10.2196/15663,
author="Biviji, Rizwana
and Vest, R. Joshua
and Dixon, E. Brian
and Cullen, Theresa
and Harle, A. Christopher",
title="Factors Related to User Ratings and User Downloads of Mobile Apps for Maternal and Infant Health: Cross-Sectional Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jan",
day="24",
volume="8",
number="1",
pages="e15663",
keywords="mHealth",
keywords="mobile apps",
keywords="pregnancy",
keywords="parturition",
keywords="infant care",
keywords="smartphones",
abstract="Background: Mobile health apps related to maternal and infant health (MIH) are prevalent and frequently used. Some of these apps are extremely popular and have been downloaded over 5 million times. However, the understanding of user behavior and user adoption of these apps based on consumer preferences for different app features and categories is limited. Objective: This study aimed to examine the relationship between MIH app characteristics and users' perceived satisfaction and intent to use. Methods: The associations between app characteristics, ratings, and downloads were assessed in a sample of MIH apps designed to provide health education or decision-making support to pregnant women or parents and caregivers of infants. Multivariable linear regression was used to assess the relationship between app characteristics and user ratings, and ordinal logistic regression was used to assess the relationship between app characteristics and user downloads. Results: The analyses of user ratings and downloads included 421 and 213 apps, respectively. The average user rating was 3.79 out of 5. Compared with the Apple App Store, the Google Play Store was associated with high user ratings (beta=.33; P=.005). Apps with higher standardized user ratings (beta=.80; P<.001), in-app purchases (beta=1.12; P=.002), and in-app advertisements (beta=.64; P=.02) were more frequently downloaded. Having a health care organization developer as part of the development team was neither associated with user ratings (beta=?.20; P=.06) nor downloads (beta=?.14; P=.63). Conclusions: A majority of MIH apps are developed by non--health care organizations, which could raise concern about the accuracy and trustworthiness of in-app information. These findings could benefit app developers in designing better apps and could help inform marketing and development strategies. Further work is needed to evaluate the clinical accuracy of information provided within the apps. ",
doi="10.2196/15663",
url="http://mhealth.jmir.org/2020/1/e15663/",
url="http://www.ncbi.nlm.nih.gov/pubmed/32012107"
}


@Article{info:doi/10.2196/15329,
author="Abdolkhani, Robab
and Gray, Kathleen
and Borda, Ann
and DeSouza, Ruth",
title="Quality Assurance of Health Wearables Data: Participatory Workshop on Barriers, Solutions, and Expectations",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jan",
day="22",
volume="8",
number="1",
pages="e15329",
keywords="remote sensing technology",
keywords="data quality assurance",
keywords="patient-generated health data",
keywords="wearable devices",
keywords="participatory research",
abstract="Background: The ubiquity of health wearables and the consequent production of patient-generated health data (PGHD) are rapidly escalating. However, the utilization of PGHD in routine clinical practices is still low because of data quality issues. There is no agreed approach to PGHD quality assurance; therefore, realizing the promise of PGHD requires in-depth discussion among diverse stakeholders to identify the data quality assurance challenges they face and understand their needs for PGHD quality assurance. Objective: This paper reports findings from a workshop aimed to explore stakeholders' data quality challenges, identify their needs and expectations, and offer practical solutions. Methods: A qualitative multi-stakeholder workshop was conducted as a half-day event on the campus of an Australian University located in a major health care precinct, namely the Melbourne Parkville Precinct. The 18 participants had experience of PGHD use in clinical care, including people who identified as health care consumers, clinical care providers, wearables suppliers, and health information specialists. Data collection was done by facilitators capturing written notes of the proceedings as attendees engaged in participatory design activities in written and oral formats, using a range of whole-group and small-group interactive methods. The collected data were analyzed thematically, using deductive and inductive coding. Results: The participants' discussions revealed a range of technical, behavioral, operational, and organizational challenges surrounding PGHD, from the time when data are collected by patients to the time data are used by health care providers for clinical decision making. PGHD stakeholders found consensus on training and engagement needs, continuous collaboration among stakeholders, and development of technical and policy standards to assure PGHD quality. Conclusions: Assuring PGHD quality is a complex process that requires the contribution of all PGHD stakeholders. The variety and depth of inputs in our workshop highlighted the importance of co-designing guidance for PGHD quality guidance. ",
doi="10.2196/15329",
url="https://mhealth.jmir.org/2020/1/e15329",
url="http://www.ncbi.nlm.nih.gov/pubmed/32012090"
}


@Article{info:doi/10.2196/12424,
author="Dick, Samantha
and O'Connor, Yvonne
and Thompson, J. Matthew
and O'Donoghue, John
and Hardy, Victoria
and Wu, Joseph Tsung-Shu
and O'Sullivan, Timothy
and Chirambo, Baxter Griphin
and Heavin, Ciara",
title="Considerations for Improved Mobile Health Evaluation: Retrospective Qualitative Investigation",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jan",
day="22",
volume="8",
number="1",
pages="e12424",
keywords="telemedicine",
keywords="mHealth",
keywords="research design",
keywords="developing countries",
abstract="Background: Mobile phone use and, consequently, mobile health (mHealth) interventions have seen an exponential increase in the last decade. There is an excess of 318,000 health-related apps available free of cost for consumers to download. However, many of these interventions are not evaluated and are lacking appropriate regulations. Randomized controlled trials are often considered the gold standard study design in determining the effectiveness of interventions, but recent literature has identified limitations in the methodology when used to evaluate mHealth. Objective: The objective of this study was to investigate the system developers' experiences of evaluating mHealth interventions in the context of a developing country. Methods: We employed a qualitative exploratory approach, conducting semistructured interviews with multidisciplinary members of an mHealth project consortium. A conventional content analysis approach was used to allow codes and themes to be identified directly from the data. Results: The findings from this study identified the system developers' perceptions of mHealth evaluation, providing an insight into the requirements of an effective mHealth evaluation. This study identified social and technical factors which should be taken into account when evaluating an mHealth intervention. Conclusions: Contextual issues represented one of the most recurrent challenges of mHealth evaluation in the context of a developing country, highlighting the importance of a mixed method evaluation. There is a myriad of social, technical, and regulatory variables, which may impact the effectiveness of an mHealth intervention. Failure to account for these variables in an evaluation may limit the ability of the intervention to achieve long-term implementation and scale. ",
doi="10.2196/12424",
url="https://mhealth.jmir.org/2020/1/e12424",
url="http://www.ncbi.nlm.nih.gov/pubmed/32012085"
}


@Article{info:doi/10.2196/16362,
author="Bobe, R. Jason
and Buros, Jacqueline
and Golden, Eddye
and Johnson, Matthew
and Jones, Michael
and Percha, Bethany
and Viglizzo, Ryan
and Zimmerman, Noah",
title="Factors Associated With Trial Completion and Adherence in App-Based N-of-1 Trials: Protocol for a Randomized Trial Evaluating Study Duration, Notification Level, and Meaningful Engagement in the Brain Boost Study",
journal="JMIR Res Protoc",
year="2020",
month="Jan",
day="8",
volume="9",
number="1",
pages="e16362",
keywords="crossover trials",
keywords="mobile apps",
keywords="adherence",
keywords="nootropics",
keywords="N-of-1 trials",
keywords="attrition",
keywords="study duration",
keywords="usability",
keywords="motivation",
keywords="cognition",
keywords="mHealth",
keywords="randomized controlled trial",
abstract="Background: N-of-1 trials promise to help individuals make more informed decisions about treatment selection through structured experiments that compare treatment effectiveness by alternating treatments and measuring their impacts in a single individual. We created a digital platform that automates the design, administration, and analysis of N-of-1 trials. Our first N-of-1 trial, the app-based Brain Boost Study, invited individuals to compare the impacts of two commonly consumed substances (caffeine and L-theanine) on their cognitive performance. Objective: The purpose of this study is to evaluate critical factors that may impact the completion of N-of-1 trials to inform the design of future app-based N-of-1 trials. We will measure study completion rates for participants that begin the Brain Boost Study and assess their associations with study duration (5, 15, or 27 days) and notification level (light or moderate). Methods: Participants will be randomized into three study durations and two notification levels. To sufficiently power the study, a minimum of 640 individuals must begin the study, and 97 individuals must complete the study. We will use a multiple logistic regression model to discern whether the study length and notification level are associated with the rate of study completion. For each group, we will also compare participant adherence and the proportion of trials that yield statistically meaningful results. Results: We completed the beta testing of the N1 app on a convenience sample of users. The Brain Boost Study on the N1 app opened enrollment to the public in October 2019. More than 30 participants enrolled in the first month. Conclusions: To our knowledge, this will be the first study to rigorously evaluate critical factors associated with study completion in the context of app-based N-of-1 trials. Trial Registration: ClinicalTrials.gov NCT04056650; https://clinicaltrials.gov/ct2/show/NCT04056650 International Registered Report Identifier (IRRID): PRR1-10.2196/16362 ",
doi="10.2196/16362",
url="https://www.researchprotocols.org/2020/1/e16362",
url="http://www.ncbi.nlm.nih.gov/pubmed/31913135"
}


@Article{info:doi/10.2196/13244,
author="Holdener, Marianne
and Gut, Alain
and Angerer, Alfred",
title="Applicability of the User Engagement Scale to Mobile Health: A Survey-Based Quantitative Study",
journal="JMIR Mhealth Uhealth",
year="2020",
month="Jan",
day="3",
volume="8",
number="1",
pages="e13244",
keywords="mobile health",
keywords="mhealth",
keywords="mobile apps",
keywords="user engagement",
keywords="measurement",
keywords="user engagement scale",
keywords="chatbot",
abstract="Background: There has recently been exponential growth in the development and use of health apps on mobile phones. As with most mobile apps, however, the majority of users abandon them quickly and after minimal use. One of the most critical factors for the success of a health app is how to support users' commitment to their health. Despite increased interest from researchers in mobile health, few studies have examined the measurement of user engagement with health apps. Objective: User engagement is a multidimensional, complex phenomenon. The aim of this study was to understand the concept of user engagement and, in particular, to demonstrate the applicability of a user engagement scale (UES) to mobile health apps. Methods: To determine the measurability of user engagement in a mobile health context, a UES was employed, which is a psychometric tool to measure user engagement with a digital system. This was adapted to Ada, developed by Ada Health, an artificial intelligence--powered personalized health guide that helps people understand their health. A principal component analysis (PCA) with varimax rotation was conducted on 30 items. In addition, sum scores as means of each subscale were calculated. Results: Survey data from 73 Ada users were analyzed. PCA was determined to be suitable, as verified by the sampling adequacy of Kaiser-Meyer-Olkin=0.858, a significant Bartlett test of sphericity ($\chi$2300=1127.1; P<.001), and communalities mostly within the 0.7 range. Although 5 items had to be removed because of low factor loadings, the results of the remaining 25 items revealed 4 attributes: perceived usability, aesthetic appeal, reward, and focused attention. Ada users showed the highest engagement level with perceived usability, with a value of 294, followed by aesthetic appeal, reward, and focused attention. Conclusions: Although the UES was deployed in German and adapted to another digital domain, PCA yielded consistent subscales and a 4-factor structure. This indicates that user engagement with health apps can be assessed with the German version of the UES. These results can benefit related mobile health app engagement research and may be of importance to marketers and app developers. ",
doi="10.2196/13244",
url="https://mhealth.jmir.org/2020/1/e13244",
url="http://www.ncbi.nlm.nih.gov/pubmed/31899454"
}


@Article{info:doi/10.2196/13305,
author="L'Hommedieu, Michelle
and L'Hommedieu, Justin
and Begay, Cynthia
and Schenone, Alison
and Dimitropoulou, Lida
and Margolin, Gayla
and Falk, Tiago
and Ferrara, Emilio
and Lerman, Kristina
and Narayanan, Shrikanth",
title="Lessons Learned: Recommendations For Implementing a Longitudinal Study Using Wearable and Environmental Sensors in a Health Care Organization",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Dec",
day="10",
volume="7",
number="12",
pages="e13305",
keywords="research",
keywords="research techniques",
keywords="Ecological Momentary Assessment",
keywords="wearable electronic devices",
doi="10.2196/13305",
url="https://mhealth.jmir.org/2019/12/e13305",
url="http://www.ncbi.nlm.nih.gov/pubmed/31821155"
}


@Article{info:doi/10.2196/16442,
author="Albrecht, Urs-Vito
and Framke, Theodor
and von Jan, Ute",
title="Quality Awareness and Its Influence on the Evaluation of App Meta-Information by Physicians: Validation Study",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Nov",
day="18",
volume="7",
number="11",
pages="e16442",
keywords="mobile health",
keywords="evaluation studies",
keywords="mobile apps",
keywords="quality principles",
keywords="usage decisions",
abstract="Background: Meta-information provided about health apps on app stores is often the only readily available source of quality-related information before installation. Objective: The purpose of this study was to assess whether physicians deem a predefined set of quality principles as relevant for health apps; whether they are able to identify corresponding information in a given sample of app descriptions; and whether, and how, this facilitates their informed usage decisions. Methods: All members of the German Society for Internal Medicine were invited by email to participate in an anonymous online survey over a 6-week period. Participants were randomly assigned one app description focusing on cardiology or pulmonology. In the survey, participants were asked three times about whether the assigned description sufficed for a usage decision: they were asked (1) after giving an appraisal of the relevance of nine predefined app quality principles, (2) after determining whether the descriptions covered the quality principles, and (3) after they assessed the availability of detailed quality information by means of 25 additional key questions. Tests for significance of changes in their decisions between assessments 1 and 2, and between assessments 2 and 3, were conducted with the McNemar-Bowker test of symmetry. The effect size represents the discordant proportion ratio sum as a quotient of the test statistics of the Bowker test and the number of observation units. The significance level was set to alpha=.05 with a power of 1-beta=.95. Results: A total of 441 of 724 participants (60.9\%) who started the survey fully completed the questionnaires and were included in the evaluation. The participants predominantly rated the specified nine quality principles as important for their decision (approximately 80\%-99\% of ratings). However, apart from the practicality criterion, information provided in the app descriptions was lacking for both groups (approximately 51\%-92\%). Reassessment of the apps led to more critical assessments among both groups. After having familiarized themselves with the nine quality principles, approximately one-third of the participants (group A: 63/220, 28.6\%; group B: 62/221, 28.1\%) came to more critical usage decisions in a statistically significant manner (McNemar-Bowker test, groups A and B: P<.001). After a subsequent reassessment with 25 key questions, critical appraisals further increased, although not in a statistically significant manner (McNemar-Bowker, group A: P=.13; group B: P=.05). Conclusions: Sensitizing physicians to the topic of quality principles via questions about attitudes toward established quality principles, and letting them apply these principles to app descriptions, lead to more critical appraisals of the sufficiency of the information they provided. Even working with only nine generic criteria was sufficient to bring about the majority of decision changes. This may lay the foundation for aiding physicians in their app-related decision processes, without unduly taking up their valuable time. ",
doi="10.2196/16442",
url="http://mhealth.jmir.org/2019/11/e16442/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31738179"
}


@Article{info:doi/10.2196/14829,
author="Silva, G. Anabela
and Sim{\~o}es, Patr{\'i}cia
and Santos, Rita
and Queir{\'o}s, Alexandra
and Rocha, P. Nelson
and Rodrigues, M{\'a}rio",
title="A Scale to Assess the Methodological Quality of Studies Assessing Usability of Electronic Health Products and Services: Delphi Study Followed by Validity and Reliability Testing",
journal="J Med Internet Res",
year="2019",
month="Nov",
day="15",
volume="21",
number="11",
pages="e14829",
keywords="quality of health care",
keywords="eHealth",
keywords="mHealth",
keywords="efficiency",
abstract="Background: The usability of electronic health (eHealth) and mobile health apps is of paramount importance as it impacts the quality of care. Methodological quality assessment is a common practice in the field of health for different designs and types of studies. However, we were unable to find a scale to assess the methodological quality of studies on the usability of eHealth products or services. Objective: This study aimed to develop a scale to assess the methodological quality of studies assessing usability of mobile apps and to perform a preliminary analysis of of the scale's feasibility, reliability, and construct validity on studies assessing usability of mobile apps, measuring aspects of physical activity. Methods: A 3-round Delphi panel was used to generate a pool of items considered important when assessing the quality of studies on the usability of mobile apps. These items were used to write the scale and the guide to assist its use. The scale was then used to assess the quality of studies on usability of mobile apps for physical activity, and it assessed in terms of feasibility, interrater reliability, and construct validity. Results: A total of 25 experts participated in the Delphi panel, and a 15-item scale was developed. This scale was shown to be feasible (time of application mean 13.10 [SD 2.59] min), reliable (intraclass correlation coefficient=0.81; 95\% CI 0.55-0.93), and able to discriminate between low- and high-quality studies (high quality: mean 9.22 [SD 0.36]; low quality: mean 6.86 [SD 0.80]; P=.01). Conclusions: The scale that was developed can be used both to assess the methodological quality of usability studies and to inform its planning. ",
doi="10.2196/14829",
url="http://www.jmir.org/2019/11/e14829/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31730036"
}


@Article{info:doi/10.2196/14849,
author="Pham, Quynh
and Shaw, James
and Morita, P. Plinio
and Seto, Emily
and Stinson, N. Jennifer
and Cafazzo, A. Joseph",
title="The Service of Research Analytics to Optimize Digital Health Evidence Generation: Multilevel Case Study",
journal="J Med Internet Res",
year="2019",
month="Nov",
day="11",
volume="21",
number="11",
pages="e14849",
keywords="research analytics",
keywords="effective engagement",
keywords="digital health",
keywords="mobile health",
keywords="implementation",
keywords="log data",
keywords="service design",
keywords="chronic disease",
abstract="Background: The widespread adoption of digital health interventions for chronic disease self-management has catalyzed a paradigm shift in the selection of methodologies used to evidence them. Recently, the application of digital health research analytics has emerged as an efficient approach to evaluate these data-rich interventions. However, there is a growing mismatch between the promising evidence base emerging from analytics mediated trials and the complexity of introducing these novel research methods into evaluative practice. Objective: This study aimed to generate transferable insights into the process of implementing research analytics to evaluate digital health interventions. We sought to answer the following two research questions: (1) how should the service of research analytics be designed to optimize digital health evidence generation? and (2) what are the challenges and opportunities to scale, spread, and sustain this service in evaluative practice? Methods: We conducted a qualitative multilevel embedded single case study of implementing research analytics in evaluative practice that comprised a review of the policy and regulatory climate in Ontario (macro level), a field study of introducing a digital health analytics platform into evaluative practice (meso level), and interviews with digital health innovators on their perceptions of analytics and evaluation (microlevel). Results: The practice of research analytics is an efficient and effective means of supporting digital health evidence generation. The introduction of a research analytics platform to evaluate effective engagement with digital health interventions into a busy research lab was ultimately accepted by research staff, became routinized in their evaluative practice, and optimized their existing mechanisms of log data analysis and interpretation. The capacity for research analytics to optimize digital health evaluations is highest when there is (1) a collaborative working relationship between research client and analytics service provider, (2) a data-driven research agenda, (3) a robust data infrastructure with clear documentation of analytic tags, (4) in-house software development expertise, and (5) a collective tolerance for methodological change. Conclusions: Scientific methods and practices that can facilitate the agile trials needed to iterate and improve digital health interventions warrant continued implementation. The service of research analytics may help to accelerate the pace of digital health evidence generation and build a data-rich research infrastructure that enables continuous learning and evaluation. ",
doi="10.2196/14849",
url="http://www.jmir.org/2019/11/e14849/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31710296"
}


@Article{info:doi/10.2196/14203,
author="Maar, A. Marion
and Beaudin, Valerie
and Yeates, Karen
and Boesch, Lisa
and Liu, Peter
and Madjedi, Kian
and Perkins, Nancy
and Hua-Stewart, Diane
and Beaudin, Faith
and Wabano, Jo Mary
and Tobe, W. Sheldon",
title="Wise Practices for Cultural Safety in Electronic Health Research and Clinical Trials With Indigenous People: Secondary Analysis of a Randomized Clinical Trial",
journal="J Med Internet Res",
year="2019",
month="Nov",
day="4",
volume="21",
number="11",
pages="e14203",
keywords="mobile health",
keywords="process evaluation",
keywords="implementation science",
keywords="Indigenous peoples",
keywords="health care texting",
keywords="SMS",
keywords="hypertension",
keywords="task shifting",
keywords="community-based participatory research",
keywords="DREAM-GLOBAL",
abstract="Background: There is a paucity of controlled clinical trial data based on research with Indigenous peoples. A lack of data specific to Indigenous peoples means that new therapeutic methods, such as those involving electronic health (eHealth), will be extrapolated to these groups based on research with other populations. Rigorous, ethical research can be undertaken in collaboration with Indigenous communities but requires careful attention to culturally safe research practices. Literature on how to involve Indigenous peoples in the development and evaluation of eHealth or mobile health apps that responds to the needs of Indigenous patients, providers, and communities is still scarce; however, the need for community-based participatory research to develop culturally safe technologies is emerging as an essential focus in Indigenous eHealth research. To be effective, researchers must first gain an in-depth understanding of Indigenous determinants of health, including the harmful consequences of colonialism. Second, researchers need to learn how colonialism affects the research process. The challenge then for eHealth researchers is to braid Indigenous ethical values with the requirements of good research methodologies into a culturally safe research protocol. Objective: A recent systematic review showed that Indigenous peoples are underrepresented in randomized controlled trials (RCTs), primarily due to a lack of attention to providing space for Indigenous perspectives within the study frameworks of RCTs. Given the lack of guidelines for conducting RCTs with Indigenous communities, we conducted an analysis of our large evaluation data set collected in the Diagnosing Hypertension-Engaging Action and Management in Getting Lower Blood Pressure in Indigenous Peoples and Low- and Middle- Income Countries (DREAM-GLOBAL) trial over a period of five years. Our goal is to identify wise practices for culturally safe, collaborative eHealth and RCT research with Indigenous communities. Methods: We thematically analyzed survey responses and qualitative interview/focus group data that we collected over five years in six culturally diverse Indigenous communities in Canada during the evaluation of the clinical trial DREAM-GLOBAL. We established themes that reflect culturally safe approaches to research and then developed wise practices for culturally safe research in pragmatic eHealth research. Results: Based on our analysis, successful eHealth research in collaboration with Indigenous communities requires a focus on cultural safety that includes: (1) building a respectful relationship; (2) maintaining a respectful relationship; (3) good communication and support for the local team during the RCT; (4) commitment to co-designing the innovation; (5) supporting task shifting with the local team; and (6) reflecting on our mistakes and lessons learned or areas for improvement that support learning and cultural safety. Conclusions: Based on evaluation data collected in the DREAM-GLOBAL RCT, we found that there are important cultural safety considerations in Indigenous eHealth research. Building on the perspectives of Indigenous staff and patients, we gleaned wise practices for RCTs in Indigenous communities. Trial Registration: ClinicalTrials.gov NCT02111226; https://clinicaltrials.gov/ct2/show/NCT02111226 ",
doi="10.2196/14203",
url="https://www.jmir.org/2019/11/e14203",
url="http://www.ncbi.nlm.nih.gov/pubmed/31682574"
}


@Article{info:doi/10.2196/13408,
author="Neijenhuijs, Ilja Koen
and van der Hout, Anja
and Veldhuijzen, Evalien
and Scholten-Peeters, M. Gwendolijne G.
and van Uden-Kraan, F. Cornelia
and Cuijpers, Pim
and Verdonck-de Leeuw, M. Irma",
title="Translation of the eHealth Impact Questionnaire for a Population of Dutch Electronic Health Users: Validation Study",
journal="J Med Internet Res",
year="2019",
month="Aug",
day="26",
volume="21",
number="8",
pages="e13408",
keywords="eHealth",
keywords="evaluation",
keywords="e-Health Impact Questionnaire",
keywords="psychometrics",
abstract="Background: The eHealth Impact Questionnaire (eHIQ) provides a standardized method to measure attitudes of electronic health (eHealth) users toward eHealth. It has previously been validated in a population of eHealth users in the United Kingdom and consists of 2 parts and 5 subscales. Part 1 measures attitudes toward eHealth in general and consists of the subscales attitudes towards online health information (5 items) and attitudes towards sharing health experiences online (6 items). Part 2 measures the attitude toward a particular eHealth application and consists of the subscales confidence and identification (9 items), information and presentation (8 items), and understand and motivation (9 items). Objective: This study aimed to translate and validate the eHIQ in a Dutch population of eHealth users. Methods: The eHIQ was translated and validated in accordance with the COnsensus-based Standards for the selection of health status Measurement INstruments criteria. The validation comprised 3 study samples, with a total of 1287 participants. Structural validity was assessed using confirmatory factor analyses and exploratory factor analyses (EFAs; all 3 samples). Internal consistency was assessed using hierarchical omega (all 3 samples). Test-retest reliability was assessed after 2 weeks, using 2-way intraclass correlation coefficients (sample 1). Measurement error was assessed by calculating the smallest detectable change (sample 1). Convergent and divergent validity were assessed using correlations with the remaining measures (all 3 samples). A graded response model was fit, and item information curves were plotted to describe the information provided by items across item trait levels (all 3 samples). Results: The original factor structure showed a bad fit in all 3 study samples. EFAs showed a good fit for a modified factor structure in the first study sample. This factor structure was subsequently tested in samples 2 and 3 and showed acceptable to good fits. Internal consistency, test-retest reliability, convergent validity, and divergent validity were acceptable to good for both the original as the modified factor structure, except for test-retest reliability of one of the original subscales and the 2 derivative subscales in the modified factor structure. The graded response model showed that some items underperformed in both the original and modified factor structure. Conclusions: The Dutch version of the eHIQ (eHIQ-NL) shows a different factor structure compared with the original English version. Part 1 of the eHIQ-NL consists of 3 subscales: attitudes towards online health information (5 items), comfort with sharing health experiences online (3 items), and usefulness of sharing health experiences online (3 items). Part 2 of the eHIQ-NL consists of 3 subscales: motivation and confidence to act (10 items), information and presentation (13 items), and identification (3 items). ",
doi="10.2196/13408",
url="http://www.jmir.org/2019/8/e13408/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31452516"
}


@Article{info:doi/10.2196/12771,
author="Nelson, C. Elizabeth
and Verhagen, Tibert
and Vollenbroek-Hutten, Miriam
and Noordzij, L. Matthijs",
title="Is Wearable Technology Becoming Part of Us? Developing and Validating a Measurement Scale for Wearable Technology Embodiment",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Aug",
day="09",
volume="7",
number="8",
pages="e12771",
keywords="embodiment",
keywords="wearable technology",
keywords="measurement development",
keywords="human technology interaction",
keywords="eHealth",
keywords="mHealth",
keywords="wearable electronic devices",
keywords="self-help devices",
keywords="health information technology",
keywords="medical informatics",
abstract="Background: To experience external objects in such a way that they are perceived as an integral part of one's own body is called embodiment. Wearable technology is a category of objects, which, due to its intrinsic properties (eg, close to the body, inviting frequent interaction, and access to personal information), is likely to be embodied. This phenomenon, which is referred to in this paper as wearable technology embodiment, has led to extensive conceptual considerations in various research fields. These considerations and further possibilities with regard to quantifying wearable technology embodiment are of particular value to the mobile health (mHealth) field. For example, the ability to predict the effectiveness of mHealth interventions and knowing the extent to which people embody the technology might be crucial for improving mHealth adherence. To facilitate examining wearable technology embodiment, we developed a measurement scale for this construct. Objective: This study aimed to conceptualize wearable technology embodiment, create an instrument to measure it, and test the predictive validity of the scale using well-known constructs related to technology adoption. The introduced instrument has 3 dimensions and includes 9 measurement items. The items are distributed evenly between the 3 dimensions, which include body extension, cognitive extension, and self-extension. Methods: Data were collected through a vignette-based survey (n=182). Each respondent was given 3 different vignettes, describing a hypothetical situation using a different type of wearable technology (a smart phone, a smart wristband, or a smart watch) with the purpose of tracking daily activities. Scale dimensions and item reliability were tested for their validity and Goodness of Fit Index (GFI). Results: Convergent validity of the 3 dimensions and their reliability were established as confirmatory factor analysis factor loadings (>0.70), average variance extracted values (>0.50), and minimum item to total correlations (>0.40) exceeded established threshold values. The reliability of the dimensions was also confirmed as Cronbach alpha and composite reliability exceeded 0.70. GFI testing confirmed that the 3 dimensions function as intercorrelated first-order factors. Predictive validity testing showed that these dimensions significantly add to multiple constructs associated with predicting the adoption of new technologies (ie, trust, perceived usefulness, involvement, attitude, and continuous intention). Conclusions: The wearable technology embodiment measurement instrument has shown promise as a tool to measure the extension of an individual's body, cognition, and self, as well as predict certain aspects of technology adoption. This 3-dimensional instrument can be applied to mixed method research and used by wearable technology developers to improve future versions through such things as fit, improved accuracy of biofeedback data, and customizable features or fashion to connect to the users' personal identity. Further research is recommended to apply this measurement instrument to multiple scenarios and technologies, and more diverse user groups. ",
doi="10.2196/12771",
url="https://mhealth.jmir.org/2019/8/e12771/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31400106"
}


@Article{info:doi/10.2196/11656,
author="Alwashmi, F. Meshari
and Hawboldt, John
and Davis, Erin
and Fetters, D. Michael",
title="The Iterative Convergent Design for Mobile Health Usability Testing: Mixed Methods Approach",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Apr",
day="26",
volume="7",
number="4",
pages="e11656",
keywords="mHealth",
keywords="mixed methods",
keywords="usability",
keywords="eHealth",
keywords="methods",
doi="10.2196/11656",
url="http://mhealth.jmir.org/2019/4/e11656/",
url="http://www.ncbi.nlm.nih.gov/pubmed/31025951"
}


@Article{info:doi/10.2196/11500,
author="Zhou, Leming
and Bao, Jie
and Setiawan, Agus I. Made
and Saptono, Andi
and Parmanto, Bambang",
title="The mHealth App Usability Questionnaire (MAUQ): Development and Validation Study",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Apr",
day="11",
volume="7",
number="4",
pages="e11500",
keywords="questionnaire design",
keywords="reliability and validity",
keywords="mobile apps",
abstract="Background: After a mobile health (mHealth) app is created, an important step is to evaluate the usability of the app before it is released to the public. There are multiple ways of conducting a usability study, one of which is collecting target users' feedback with a usability questionnaire. Different groups have used different questionnaires for mHealth app usability evaluation: The commonly used questionnaires are the System Usability Scale (SUS) and Post-Study System Usability Questionnaire (PSSUQ). However, the SUS and PSSUQ were not designed to evaluate the usability of mHealth apps. Self-written questionnaires are also commonly used for evaluation of mHealth app usability but they have not been validated. Objective: The goal of this project was to develop and validate a new mHealth app usability questionnaire. Methods: An mHealth app usability questionnaire (MAUQ) was designed by the research team based on a number of existing questionnaires used in previous mobile app usability studies, especially the well-validated questionnaires. MAUQ, SUS, and PSSUQ were then used to evaluate the usability of two mHealth apps: an interactive mHealth app and a standalone mHealth app. The reliability and validity of the new questionnaire were evaluated. The correlation coefficients among MAUQ, SUS, and PSSUQ were calculated. Results: In this study, 128 study participants provided responses to the questionnaire statements. Psychometric analysis indicated that the MAUQ has three subscales and their internal consistency reliability is high. The relevant subscales correlated well with the subscales of the PSSUQ. The overall scale also strongly correlated with the PSSUQ and SUS. Four versions of the MAUQ were created in relation to the type of app (interactive or standalone) and target user of the app (patient or provider). A website has been created to make it convenient for mHealth app developers to use this new questionnaire in order to assess the usability of their mHealth apps. Conclusions: The newly created mHealth app usability questionnaire---MAUQ---has the reliability and validity required to assess mHealth app usability. ",
doi="10.2196/11500",
url="http://mhealth.jmir.org/2019/4/e11500/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30973342"
}


@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/10.2196/11969,
author="Jones, Helen Kerina
and Daniels, Helen
and Heys, Sharon
and Ford, Vincent David",
title="Toward an Ethically Founded Framework for the Use of Mobile Phone Call Detail Records in Health Research",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Mar",
day="22",
volume="7",
number="3",
pages="e11969",
keywords="mobile phone data",
keywords="ethical framework",
doi="10.2196/11969",
url="http://mhealth.jmir.org/2019/3/e11969/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30900996"
}


@Article{info:doi/10.2196/11973,
author="Birckhead, Brandon
and Khalil, Carine
and Liu, Xiaoyu
and Conovitz, Samuel
and Rizzo, Albert
and Danovitch, Itai
and Bullock, Kim
and Spiegel, Brennan",
title="Recommendations for Methodology of Virtual Reality Clinical Trials in Health Care by an International Working Group: Iterative Study",
journal="JMIR Ment Health",
year="2019",
month="Jan",
day="31",
volume="6",
number="1",
pages="e11973",
keywords="clinical trials",
keywords="consensus",
keywords="virtual reality",
abstract="Background: Therapeutic virtual reality (VR) has emerged as an efficacious treatment modality for a wide range of health conditions. However, despite encouraging outcomes from early stage research, a consensus for the best way to develop and evaluate VR treatments within a scientific framework is needed. Objective: We aimed to develop a methodological framework with input from an international working group in order to guide the design, implementation, analysis, interpretation, and communication of trials that develop and test VR treatments. Methods: A group of 21 international experts was recruited based on their contributions to the VR literature. The resulting Virtual Reality Clinical Outcomes Research Experts held iterative meetings to seek consensus on best practices for the development and testing of VR treatments. Results: The interactions were transcribed, and key themes were identified to develop a scientific framework in order to support best practices in methodology of clinical VR trials. Using the Food and Drug Administration Phase I-III pharmacotherapy model as guidance, a framework emerged to support three phases of VR clinical study designs---VR1, VR2, and VR3. VR1 studies focus on content development by working with patients and providers through the principles of human-centered design. VR2 trials conduct early testing with a focus on feasibility, acceptability, tolerability, and initial clinical efficacy. VR3 trials are randomized, controlled studies that evaluate efficacy against a control condition. Best practice recommendations for each trial were provided. Conclusions: Patients, providers, payers, and regulators should consider this best practice framework when assessing the validity of VR treatments. ",
doi="10.2196/11973",
url="https://mental.jmir.org/2019/1/e11973/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30702436"
}


@Article{info:doi/10.2196/11130,
author="McKay, H. Fiona
and Slykerman, Sarah
and Dunn, Matthew",
title="The App Behavior Change Scale: Creation of a Scale to Assess the Potential of Apps to Promote Behavior Change",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Jan",
day="25",
volume="7",
number="1",
pages="e11130",
keywords="apps",
keywords="smartphone",
keywords="mobile phone",
keywords="mobile app",
keywords="scale development",
keywords="rating",
abstract="Background: Using mobile phone apps to promote behavior change is becoming increasingly common. However, there is no clear way to rate apps against their behavior change potential. Objective: This study aimed to develop a reliable, theory-based scale that can be used to assess the behavior change potential of smartphone apps. Methods: A systematic review of all studies purporting to investigate app's behavior change potential was conducted. All scales and measures from the identified studies were collected to create an item pool. From this item pool, 3 health promotion exerts created the App Behavior Change Scale (ABACUS). To test the scale, 70 physical activity apps were rated to provide information on reliability. Results: The systematic review returned 593 papers, the abstracts and titles of all were reviewed, with the full text of 77 papers reviewed; 50 papers met the inclusion criteria. From these 50 papers, 1333 questions were identified. Removing duplicates and unnecessary questions left 130 individual questions, which were then refined into the 21-item scale. The ABACUS demonstrates high percentage agreement among reviewers (over 80\%), with 3 questions scoring a Krippendorff alpha that would indicate agreement and a further 7 came close with alphas >.5. The scale overall reported high interrater reliability (2-way mixed interclass coefficient=.92, 95\% CI 0.81-0.97) and high internal consistency (Cronbach alpha=.93). Conclusions: The ABACUS is a reliable tool that can be used to determine the behavior change potential of apps. This instrument fills a gap by allowing the evaluation of a large number of apps to be standardized across a range of health categories. ",
doi="10.2196/11130",
url="http://mhealth.jmir.org/2019/1/e11130/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30681967"
}


@Article{info:doi/10.2196/11941,
author="Pham, Quynh
and Graham, Gary
and Carrion, Carme
and Morita, P. Plinio
and Seto, Emily
and Stinson, N. Jennifer
and Cafazzo, A. Joseph",
title="A Library of Analytic Indicators to Evaluate Effective Engagement with Consumer mHealth Apps for Chronic Conditions: Scoping Review",
journal="JMIR Mhealth Uhealth",
year="2019",
month="Jan",
day="18",
volume="7",
number="1",
pages="e11941",
keywords="analytics",
keywords="effective engagement",
keywords="engagement",
keywords="adherence",
keywords="log data",
keywords="mobile health",
keywords="mobile applications",
keywords="chronic disease",
keywords="scoping review",
abstract="Background: There is mixed evidence to support current ambitions for mobile health (mHealth) apps to improve chronic health and well-being. One proposed explanation for this variable effect is that users do not engage with apps as intended. The application of analytics, defined as the use of data to generate new insights, is an emerging approach to study and interpret engagement with mHealth interventions. Objective: This study aimed to consolidate how analytic indicators of engagement have previously been applied across clinical and technological contexts, to inform how they might be optimally applied in future evaluations. Methods: We conducted a scoping review to catalog the range of analytic indicators being used in evaluations of consumer mHealth apps for chronic conditions. We categorized studies according to app structure and application of engagement data and calculated descriptive data for each category. Chi-square and Fisher exact tests of independence were applied to calculate differences between coded variables. Results: A total of 41 studies met our inclusion criteria. The average mHealth evaluation included for review was a two-group pretest-posttest randomized controlled trial of a hybrid-structured app for mental health self-management, had 103 participants, lasted 5 months, did not provide access to health care provider services, measured 3 analytic indicators of engagement, segmented users based on engagement data, applied engagement data for descriptive analyses, and did not report on attrition. Across the reviewed studies, engagement was measured using the following 7 analytic indicators: the number of measures recorded (76\%, 31/41), the frequency of interactions logged (73\%, 30/41), the number of features accessed (49\%, 20/41), the number of log-ins or sessions logged (46\%, 19/41), the number of modules or lessons started or completed (29\%, 12/41), time spent engaging with the app (27\%, 11/41), and the number or content of pages accessed (17\%, 7/41). Engagement with unstructured apps was mostly measured by the number of features accessed (8/10, P=.04), and engagement with hybrid apps was mostly measured by the number of measures recorded (21/24, P=.03). A total of 24 studies presented, described, or summarized the data generated from applying analytic indicators to measure engagement. The remaining 17 studies used or planned to use these data to infer a relationship between engagement patterns and intended outcomes. Conclusions: Although researchers measured on average 3 indicators in a single study, the majority reported findings descriptively and did not further investigate how engagement with an app contributed to its impact on health and well-being. Researchers are gaining nuanced insights into engagement but are not yet characterizing effective engagement for improved outcomes. Raising the standard of mHealth app efficacy through measuring analytic indicators of engagement may enable greater confidence in the causal impact of apps on improved chronic health and well-being. ",
doi="10.2196/11941",
url="http://mhealth.jmir.org/2019/1/e11941/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30664463"
}


@Article{info:doi/10.2196/10255,
author="Torbj{\o}rnsen, Astrid
and Sm{\aa}stuen, C. Milada
and Jenum, Karen Anne
and {\AA}rsand, Eirik
and Ribu, Lis",
title="The Service User Technology Acceptability Questionnaire: Psychometric Evaluation of the Norwegian Version",
journal="JMIR Hum Factors",
year="2018",
month="Dec",
day="21",
volume="5",
number="4",
pages="e10255",
keywords="acceptability",
keywords="factor analysis",
keywords="health care",
keywords="mHealth",
keywords="telemedicine",
abstract="Background: When developing a mobile health app, users' perception of the technology should preferably be evaluated. However, few standardized and validated questionnaires measuring acceptability are available. Objective: The aim of this study was to assess the validity of the Norwegian version of the Service User Technology Acceptability Questionnaire (SUTAQ). Methods: Persons with type 2 diabetes randomized to the intervention groups of the RENEWING HEALTH study used a diabetes diary app. At the one-year follow-up, participants in the intervention groups (n=75) completed the self-reported instrument SUTAQ to measure the acceptability of the equipment. We conducted confirmatory factor analysis for evaluating the fit of the original five-factor structure of the SUTAQ. Results: We confirmed only 2 of the original 5 factors of the SUTAQ, perceived benefit and care personnel concerns. Conclusions: The original five-factor structure of the SUTAQ was not confirmed in the Norwegian study, indicating that more research is needed to tailor the questionnaire to better reflect the Norwegian setting. However, a small sample size prevented us from drawing firm conclusions about the translated questionnaire. ",
doi="10.2196/10255",
url="http://humanfactors.jmir.org/2018/4/e10255/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30578191"
}


@Article{info:doi/10.2196/11447,
author="Pham, Quynh
and Graham, Gary
and Lalloo, Chitra
and Morita, P. Plinio
and Seto, Emily
and Stinson, N. Jennifer
and Cafazzo, A. Joseph",
title="An Analytics Platform to Evaluate Effective Engagement With Pediatric Mobile Health Apps: Design, Development, and Formative Evaluation",
journal="JMIR Mhealth Uhealth",
year="2018",
month="Dec",
day="21",
volume="6",
number="12",
pages="e11447",
keywords="analytics",
keywords="engagement",
keywords="log data",
keywords="mobile health",
keywords="mobile apps",
keywords="chronic disease",
abstract="Background: Mobile health (mHealth) apps for pediatric chronic conditions are growing in availability and challenge investigators to conduct rigorous evaluations that keep pace with mHealth innovation. Traditional research methods are poorly suited to operationalize the agile, iterative trials required to evidence and optimize these digitally mediated interventions. Objective: We sought to contribute a resource to support the quantification, analysis, and visualization of analytic indicators of effective engagement with mHealth apps for chronic conditions. Methods: We applied user-centered design methods to design and develop an Analytics Platform to Evaluate Effective Engagement (APEEE) with consumer mHealth apps for chronic conditions and implemented the platform to analyze both retrospective and prospective data generated from a smartphone-based pain self-management app called iCanCope for young people with chronic pain. Results: Through APEEE, we were able to automate the process of defining, operationalizing, and evaluating effective engagement with iCanCope. Configuring the platform to integrate with the app was feasible and provided investigators with a resource to consolidate, analyze, and visualize engagement data generated by participants in real time. Preliminary efforts to evaluate APEEE showed that investigators perceived the platform to be an acceptable evaluative resource and were satisfied with its design, functionality, and performance. Investigators saw potential in APEEE to accelerate and augment evidence generation and expressed enthusiasm for adopting the platform to support their evaluative practice once fully implemented. Conclusions: Dynamic, real-time analytic platforms may provide investigators with a powerful means to characterize the breadth and depth of mHealth app engagement required to achieve intended health outcomes. Successful implementation of APEEE into evaluative practice may contribute to the realization of effective and evidence-based mHealth care. ",
doi="10.2196/11447",
url="http://mhealth.jmir.org/2018/12/e11447/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30578179"
}


@Article{info:doi/10.2196/10123,
author="Bidargaddi, Niranjan
and Almirall, Daniel
and Murphy, Susan
and Nahum-Shani, Inbal
and Kovalcik, Michael
and Pituch, Timothy
and Maaieh, Haitham
and Strecher, Victor",
title="To Prompt or Not to Prompt? A Microrandomized Trial of Time-Varying Push Notifications to Increase Proximal Engagement With a Mobile Health App",
journal="JMIR Mhealth Uhealth",
year="2018",
month="Nov",
day="29",
volume="6",
number="11",
pages="e10123",
keywords="mobile applications",
keywords="smartphone",
keywords="self report",
keywords="health promotion",
keywords="lifestyle",
keywords="ubiquitous computing",
keywords="push notification",
abstract="Background: Mobile health (mHealth) apps provide an opportunity for easy, just-in-time access to health promotion and self-management support. However, poor user engagement with these apps remains a significant unresolved challenge. Objective: This study aimed to assess the effect of sending versus not sending a push notification containing a contextually tailored health message on proximal engagement, measured here as self-monitoring via the app. Secondary aims were to examine whether this effect varies by the number of weeks enrolled in the program or by weekday versus weekend. An exploratory aim was to describe how the effect on proximal engagement differs between weekday versus weekend by the time of day. Methods: The study analyzes the causal effects of push notifications on proximal engagement in 1255 users of a commercial workplace well-being intervention app over 89 days. The app employs a microrandomized trial (MRT) design to send push notifications. At 1 of 6 times per day (8:30 am, 12:30 pm, 5:30 pm, 6:30 pm, 7:30 pm, and 8:30 pm; selected randomly), available users were randomized with equal probability to be sent or not sent a push notification containing a tailored health message. The primary outcome of interest was whether the user self-monitored behaviors and feelings at some time during the next 24 hours via the app. A generalization of log-linear regression analysis, adapted for use with data arising from an MRT, was used to examine the effect of sending a push notification versus not sending a push notification on the probability of engagement over the next 24 hours. Results: Users were estimated to be 3.9\% more likely to engage with the app in the next 24 hours when a tailored health message was sent versus when it was not sent (risk ratio 1.039; 95\% CI 1.01 to 1.08; P<.05). The effect of sending the message attenuated over the course of the study, but this effect was not statistically significant (P=.84). The effect of sending the message was greater on weekends than on weekdays, but the difference between these effects was not statistically significant (P=.18). When sent a tailored health message on weekends, the users were 8.7\% more likely to engage with the app (95\% CI 1.01 to 1.17), whereas on weekdays, the users were 2.5\% more likely to engage with the app (95\% CI 0.98 to 1.07). The effect of sending a tailored health message was greatest at 12:30 pm on weekends, when the users were 11.8\% more likely to engage (90\% CI 1.02 to 1.13). Conclusions: Sending a push notification containing a tailored health message was associated with greater engagement in an mHealth app. Results suggested that users are more likely to engage with the app within 24 hours when push notifications are sent at mid-day on weekends. ",
doi="10.2196/10123",
url="http://mhealth.jmir.org/2018/11/e10123/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30497999"
}


@Article{info:doi/10.2196/11012,
author="Gower, D. Aubrey
and Moreno, A. Megan",
title="A Novel Approach to Evaluating Mobile Smartphone Screen Time for iPhones: Feasibility and Preliminary Findings",
journal="JMIR Mhealth Uhealth",
year="2018",
month="Nov",
day="19",
volume="6",
number="11",
pages="e11012",
keywords="smartphone",
keywords="youth",
keywords="mobile apps",
keywords="mobile phone",
keywords="screenshot",
abstract="Background: Increasingly high levels of smartphone ownership and use pose the potential risk for addictive behaviors and negative health outcomes, particularly among younger populations. Previous methodologies to understand mobile screen time have relied on self-report surveys or ecological momentary assessments (EMAs). Self-report is subject to bias and unreliability, while EMA can be burdensome to participants. Thus, a new methodology is needed to advance the understanding of mobile screen time. Objective: The objective of this study was to test the feasibility of a novel methodology to record and evaluate mobile smartphone screen time and use: battery use screenshot (BUS). Methods: The BUS approach, defined for this study as uploading a mobile phone screenshot of a specific page within a smartphone, was utilized within a Web-based cross-sectional survey of adolescents aged 12-15 years through the survey platform Qualtrics. Participants were asked to provide a screenshot of their battery use page, a feature within an iPhone, to upload within the Web-based survey. Feasibility was assessed by smartphone ownership and response rate to the BUS upload request. Data availability was evaluated as apps per BUS, completeness of data within the screenshot, and five most used apps based on battery use percentage. Results: Among those surveyed, 26.73\% (309/1156) indicated ownership of a smartphone. A total of 105 screenshots were evaluated. For data availability, screenshots contained an average of 10.2 (SD 2.0) apps per screenshot and over half (58/105, 55.2\%) had complete data available. The most common apps or functions included Safari and Home and Lock Screen. Conclusions: Study findings describe the BUS as a novel approach for real-time data collection focused on iPhone screen time and use among young adolescents. Although feasibility showed some challenges in the upload capacity of young teens, data availability was generally strong across this large dataset. These data from screenshots have the potential to provide key insights into precise mobile smartphone screen use and time spent per mobile app. Future studies could explore the use of the BUS methodology on other mobile smartphones such as Android phones to correlate mobile smartphone screen time with health outcomes. ",
doi="10.2196/11012",
url="http://mhealth.jmir.org/2018/11/e11012/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30455163"
}


@Article{info:doi/10.2196/mental.9684,
author="Laird, A. Elizabeth
and Ryan, Assumpta
and McCauley, Claire
and Bond, B. Raymond
and Mulvenna, D. Maurice
and Curran, J. Kevin
and Bunting, Brendan
and Ferry, Finola
and Gibson, Aideen",
title="Using Mobile Technology to Provide Personalized Reminiscence for People Living With Dementia and Their Carers: Appraisal of Outcomes From a Quasi-Experimental Study",
journal="JMIR Ment Health",
year="2018",
month="Sep",
day="11",
volume="5",
number="3",
pages="e57",
keywords="dementia",
keywords="evaluation",
keywords="mobile apps",
keywords="reminiscence",
keywords="research",
keywords="technology",
keywords="mobile phone",
abstract="Background: Dementia is an international research priority. Reminiscence is an intervention that prompts memories and has been widely used as a therapeutic approach for people living with dementia. We developed a novel iPad app to support home-based personalized reminiscence. It is crucial that technology-enabled reminiscence interventions are appraised. Objective: We sought to measure the effect of technology-enabled reminiscence on mutuality (defined as the level of ``closeness'' between an adult living with dementia and their carer), quality of carer and patient relationship, and subjective well-being. Methods: A 19-week personalized reminiscence intervention facilitated by a program of training and a bespoke iPad app was delivered to people living with dementia and their family carers at their own homes. Participants (N=60) were recruited in dyads from a cognitive rehabilitation team affiliated with a large UK health care organization. Each dyad comprised a person living with early to moderate dementia and his or her family carer. Outcome measurement data were collected at baseline, midpoint, and intervention closure. Results: Participants living with dementia attained statistically significant increases in mutuality, quality of carer and patient relationship, and subjective well-being (P<.001 for all 3) from baseline to endpoint. Carers attained nonsignificant increases in mutuality and quality of carer and patient relationship and a nonsignificant decrease in subjective well-being. Conclusions: Our results indicate that individual-specific reminiscence supported by an iPad app may be efficient in the context of early to moderate dementia. A robust randomized controlled trial of technology-enabled personalized reminiscence is warranted. ",
doi="10.2196/mental.9684",
url="http://mental.jmir.org/2018/3/e57/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30206053"
}


@Article{info:doi/10.2196/10414,
author="Larson, S. Richard",
title="A Path to Better-Quality mHealth Apps",
journal="JMIR Mhealth Uhealth",
year="2018",
month="Jul",
day="30",
volume="6",
number="7",
pages="e10414",
keywords="mobile apps",
keywords="smartphone",
keywords="software validation",
keywords="medical device legislation",
keywords="United States Food and Drug Administration",
doi="10.2196/10414",
url="http://mhealth.jmir.org/2018/7/e10414/",
url="http://www.ncbi.nlm.nih.gov/pubmed/30061091"
}


@Article{info:doi/10.2196/10016,
author="Zelmer, Jennifer
and van Hoof, Krystle
and Notarianni, MaryAnn
and van Mierlo, Trevor
and Schellenberg, Megan
and Tannenbaum, Cara",
title="An Assessment Framework for e-Mental Health Apps in Canada: Results of a Modified Delphi Process",
journal="JMIR Mhealth Uhealth",
year="2018",
month="Jul",
day="09",
volume="6",
number="7",
pages="e10016",
keywords="mental health",
keywords="mobile phone apps",
keywords="consensus",
keywords="Delphi process",
keywords="evaluation framework",
keywords="telemedicine",
abstract="Background: The number of e-mental health apps is increasing rapidly. Studies have shown that the use of some apps is beneficial, whereas others are ineffective or do not meet users' privacy expectations. Individuals and organizations that curate, recommend, host, use, or pay for apps have an interest in categorizing apps according to the consensus criteria of usability and effectiveness. Others have previously published recommendations for assessing health-related apps; however, the extent to which these recommendations can be generalized across different population groups (eg, culture, gender, and language) remains unclear. This study describes an attempt by Canadian stakeholders to develop an e-mental health assessment framework that responds to the unique needs of people living in Canada in an evidence-based manner. Objective: The objective of our study was to achieve consensus from a broad group of Canadian stakeholders on guiding principles and criteria for a framework to assess e-mental health apps in Canada. Methods: We developed an initial set of guiding principles and criteria from a rapid review and environmental scan of pre-existing app assessment frameworks. The initial list was refined through a two-round modified Delphi process. Participants (N=25) included app developers and users, health care providers, mental health advocates, people with lived experience of a mental health problem or mental illness, policy makers, and researchers. Consensus on each guideline or criterion was defined a priori as at least 70\% agreement. The first round of voting was conducted electronically. Prior to Round 2 voting, in-person presentations from experts and a persona empathy mapping process were used to explore the perspectives of diverse stakeholders. Results: Of all respondents, 68\% (17/25) in Round 1 and 100\% (13/13) in Round 2 agreed that a framework for evaluating health apps is needed to help Canadian consumers identify high-quality apps. Consensus was reached on 9 guiding principles: evidence based, gender responsive, culturally appropriate, user centered, risk based, internationally aligned, enabling innovation, transparent and fair, and based on ethical norms. In addition, 15 informative and evaluative criteria were defined to assess the effectiveness, functionality, clinical applicability, interoperability, usability, transparency regarding security and privacy, security or privacy standards, supported platforms, targeted users, developers' transparency, funding transparency, price, user desirability, user inclusion, and meaningful inclusion of a diverse range of communities. Conclusions: Canadian mental health stakeholders reached the consensus on a framework of 9 guiding principles and 15 criteria important in assessing e-mental health apps. What differentiates the Canadian framework from other scales is explicit attention to user inclusion at all stages of the development, gender responsiveness, and cultural appropriateness. Furthermore, an empathy mapping process markedly influenced the development of the framework. This framework may be used to inform future mental health policies and programs. ",
doi="10.2196/10016",
url="http://mhealth.jmir.org/2018/7/e10016/",
url="http://www.ncbi.nlm.nih.gov/pubmed/29986846"
}


@Article{info:doi/10.2196/10202,
author="Zanaboni, Paolo
and Ngangue, Patrice
and Mbemba, Claudine Gisele Ir{\`e}ne
and Schopf, Roger Thomas
and Bergmo, Strand Trine
and Gagnon, Marie-Pierre",
title="Methods to Evaluate the Effects of Internet-Based Digital Health Interventions for Citizens: Systematic Review of Reviews",
journal="J Med Internet Res",
year="2018",
month="Jun",
day="07",
volume="20",
number="6",
pages="e10202",
keywords="review",
keywords="electronic health records",
keywords="patient access to records",
keywords="patient portals",
keywords="epidemiological methods",
keywords="evaluation studies as topic",
abstract="Background: Digital health can empower citizens to manage their health and address health care system problems including poor access, uncoordinated care and increasing costs. Digital health interventions are typically complex interventions. Therefore, evaluations present methodological challenges. Objective: The objective of this study was to provide a systematic overview of the methods used to evaluate the effects of internet-based digital health interventions for citizens. Three research questions were addressed to explore methods regarding approaches (study design), effects and indicators. Methods: We conducted a systematic review of reviews of the methods used to measure the effects of internet-based digital health interventions for citizens. The protocol was developed a priori according to Preferred Reporting Items for Systematic review and Meta-Analysis Protocols and the Cochrane Collaboration methodology for overviews of reviews. Qualitative, mixed-method, and quantitative reviews published in English or French from January 2010 to October 2016 were included. We searched for published reviews in PubMed, EMBASE, The Cochrane Database of Systematic Reviews, CINHAL and Epistemonikos. We categorized the findings based on a thematic analysis of the reviews structured around study designs, indicators, types of interventions, effects and perspectives. Results: A total of 20 unique reviews were included. The most common digital health interventions for citizens were patient portals and patients' access to electronic health records, covered by 10/20 (50\%) and 6/20 (30\%) reviews, respectively. Quantitative approaches to study design included observational study (15/20 reviews, 75\%), randomized controlled trial (13/20 reviews, 65\%), quasi-experimental design (9/20 reviews, 45\%), and pre-post studies (6/20 reviews, 30\%). Qualitative studies or mixed methods were reported in 13/20 (65\%) reviews. Five main categories of effects were identified: (1) health and clinical outcomes, (2) psychological and behavioral outcomes, (3) health care utilization, (4) system adoption and use, and (5) system attributes. Health and clinical outcomes were measured with both general indicators and disease-specific indicators and reported in 11/20 (55\%) reviews. Patient-provider communication and patient satisfaction were the most investigated psychological and behavioral outcomes, reported in 13/20 (65\%) and 12/20 (60\%) reviews, respectively. Evaluation of health care utilization was included in 8/20 (40\%) reviews, most of which focused on the economic effects on the health care system. Conclusions: Although observational studies and surveys have provided evidence of benefits and satisfaction for patients, there is still little reliable evidence from randomized controlled trials of improved health outcomes. Future evaluations of digital health interventions for citizens should focus on specific populations or chronic conditions which are more likely to achieve clinically meaningful benefits and use high-quality approaches such as randomized controlled trials. Implementation research methods should also be considered. We identified a wide range of effects and indicators, most of which focused on patients as main end users. Implications for providers and the health system should also be included in evaluations or monitoring of digital health interventions. ",
doi="10.2196/10202",
url="http://www.jmir.org/2018/6/e10202/"
}


@Article{info:doi/10.2196/mhealth.9581,
author="Shen, Lining
and Xiong, Bing
and Li, Wei
and Lan, Fuqiang
and Evans, Richard
and Zhang, Wei",
title="Visualizing Collaboration Characteristics and Topic Burst on International Mobile Health Research: Bibliometric Analysis",
journal="JMIR Mhealth Uhealth",
year="2018",
month="Jun",
day="05",
volume="6",
number="6",
pages="e135",
keywords="collaboration characteristics",
keywords="topic bursts",
keywords="international mobile health",
keywords="mHealth",
keywords="telemedicine",
keywords="bibliometric analysis",
keywords="bibliometrics",
keywords="research trends",
abstract="Background: In the last few decades, mobile technologies have been widely adopted in the field of health care services to improve the accessibility to and the quality of health services received. Mobile health (mHealth) has emerged as a field of research with increasing attention being paid to it by scientific researchers and a rapid increase in related literature being reported. Objective: The purpose of this study was to analyze the current state of research, including publication outputs, in the field of mHealth to uncover in-depth collaboration characteristics and topic burst of international mHealth research. Methods: The authors collected literature that has been published in the last 20 years and indexed by Thomson Reuters Web of Science Core Collection (WoSCC). Various statistical techniques and bibliometric measures were employed, including publication growth analysis; journal distribution; and collaboration network analysis at the author, institution, and country collaboration level. The temporal visualization map of burst terms was drawn, and the co-occurrence matrix of these burst terms was analyzed by hierarchical cluster analysis and social network analysis. Results: A total of 2704 bibliographic records on mHealth were collected. The earliest paper centered on mHealth was published in 1997, with the number of papers rising continuously since then. A total of 21.28\% (2318/10,895) of authors publishing mHealth research were first author, whereas only 1.29\% (141/10,895) of authors had published one paper. The total degree of author collaboration was 4.42 (11,958/2704) and there are 266 core authors who have collectively published 53.07\% (1435/2704) of the total number of publications, which means that the core group of authors has fundamentally been formed based on the Law of Price. The University of Michigan published the highest number of mHealth-related publications, but less collaboration among institutions exits. The United States is the most productive country in the field and plays a leading role in collaborative research on mHealth. There are 5543 different identified keywords in the cleaned records. The temporal bar graph clearly presents overall topic evolutionary process over time. There are 12 important research directions identified, which are in the imbalanced development. Moreover, the density of the network was 0.007, a relatively low level. These 12 topics can be categorized into 4 areas: (1) patient engagement and patient intervention, (2) health monitoring and self-care, (3) mobile device and mobile computing, and (4) security and privacy. Conclusions: The collaboration of core authors on mHealth research is not tight and stable. Furthermore, collaboration between institutions mainly occurs in the United States, although country collaboration is seen as relatively scarce. The focus of research topics on mHealth is decentralized. Our study might provide a potential guide for future research in mHealth. ",
doi="10.2196/mhealth.9581",
url="http://mhealth.jmir.org/2018/6/e135/"
}


@Article{info:doi/10.2196/mhealth.9661,
author="Shattuck, Dominick
and Haile, T. Liya
and Simmons, G. Rebecca",
title="Lessons From the Dot Contraceptive Efficacy Study: Analysis of the Use of Agile Development to Improve Recruitment and Enrollment for mHealth Research",
journal="JMIR Mhealth Uhealth",
year="2018",
month="Apr",
day="20",
volume="6",
number="4",
pages="e99",
keywords="mobile apps",
keywords="mHealth",
keywords="higher mobile research",
keywords="fertility tracker",
keywords="contraceptive",
keywords="family planning",
keywords="fertility awareness method",
keywords="Dot",
keywords="contraceptive efficacy",
abstract="Background: Smartphone apps that provide women with information about their daily fertility status during their menstrual cycles can contribute to the contraceptive method mix. However, if these apps claim to help a user prevent pregnancy, they must undergo similar rigorous research required for other contraceptive methods. Georgetown University's Institute for Reproductive Health is conducting a prospective longitudinal efficacy trial on Dot (Dynamic Optimal Timing), an algorithm-based fertility app designed to help women prevent pregnancy. Objective: The aim of this paper was to highlight decision points during the recruitment-enrollment process and the effect of modifications on enrollment numbers and demographics. Recruiting eligible research participants for a contraceptive efficacy study and enrolling an adequate number to statistically assess the effectiveness of Dot is critical. Recruiting and enrolling participants for the Dot study involved making decisions based on research and analytic data, constant process modification, and close monitoring and evaluation of the effect of these modifications. Methods: Originally, the only option for women to enroll in the study was to do so over the phone with a study representative. On noticing low enrollment numbers, we examined the 7 steps from the time a woman received the recruitment message until she completed enrollment and made modifications accordingly. In modification 1, we added call-back and voicemail procedures to increase the number of completed calls. Modification 2 involved using a chat and instant message (IM) features to facilitate study enrollment. In modification 3, the process was fully automated to allow participants to enroll in the study without the aid of study representatives. Results: After these modifications were implemented, 719 women were enrolled in the study over a 6-month period. The majority of participants (494/719, 68.7\%) were enrolled during modification 3, in which they had the option to enroll via phone, chat, or the fully automated process. Overall, 29.2\% (210/719) of the participants were enrolled via a phone call, 19.9\% (143/719) via chat/IM, and 50.9\% (366/719) directly through the fully automated process. With respect to the demographic profile of our study sample, we found a significant statistical difference in education level across all modifications (P<.05) but not in age or race or ethnicity (P>.05). Conclusions: Our findings show that agile and consistent modifications to the recruitment and enrollment process were necessary to yield an appropriate sample size. An automated process resulted in significantly higher enrollment rates than one that required phone interaction with study representatives. Although there were some differences in demographic characteristics of enrollees as the process was modified, in general, our study population is diverse and reflects the overall United States population in terms of race/ethnicity, age, and education. Additional research is proposed to identify how differences in mode of enrollment and demographic characteristics may affect participants' performance in the study. Trial Registration: ClinicalTrials.gov NCT02833922; http://clinicaltrials.gov/ct2/show/NCT02833922 (Archived by WebCite at http://www.webcitation.org/6yj5FHrBh) ",
doi="10.2196/mhealth.9661",
url="http://mhealth.jmir.org/2018/4/e99/",
url="http://www.ncbi.nlm.nih.gov/pubmed/29678802"
}


@Article{info:doi/10.2196/mhealth.8851,
author="Schnall, Rebecca
and Cho, Hwayoung
and Liu, Jianfang",
title="Health Information Technology Usability Evaluation Scale (Health-ITUES) for Usability Assessment of Mobile Health Technology: Validation Study",
journal="JMIR Mhealth Uhealth",
year="2018",
month="Jan",
day="05",
volume="6",
number="1",
pages="e4",
keywords="mobile technology",
keywords="usability",
keywords="mobile health apps",
keywords="psychometric evaluation",
abstract="Background: Mobile technology has become a ubiquitous technology and can be particularly useful in the delivery of health interventions. This technology can allow us to deliver interventions to scale, cover broad geographic areas, and deliver technologies in highly tailored ways based on the preferences or characteristics of users. The broad use of mobile technologies supports the need for usability assessments of these tools. Although there have been a number of usability assessment instruments developed, none have been validated for use with mobile technologies. Objective: The goal of this work was to validate the Health Information Technology Usability Evaluation Scale (Health-ITUES), a customizable usability assessment instrument in a sample of community-dwelling adults who were testing the use of a new mobile health (mHealth) technology. Methods: A sample of 92 community-dwelling adults living with HIV used a new mobile app for symptom self-management and completed the Health-ITUES to assess the usability of the app. They also completed the Post-Study System Usability Questionnaire (PSSUQ), a widely used and well-validated usability assessment tool. Correlations between these scales and each of the subscales were assessed. Results: The subscales of the Health-ITUES showed high internal consistency reliability (Cronbach alpha=.85-.92). Each of the Health-ITUES subscales and the overall scale was moderately to strongly correlated with the PSSUQ scales (r=.46-.70), demonstrating the criterion validity of the Health-ITUES. Conclusions: The Health-ITUES has demonstrated reliability and validity for use in assessing the usability of mHealth technologies in community-dwelling adults living with a chronic illness. ",
doi="10.2196/mhealth.8851",
url="http://mhealth.jmir.org/2018/1/e4/",
url="http://www.ncbi.nlm.nih.gov/pubmed/29305343"
}


@Article{info:doi/10.2196/mhealth.8758,
author="Jake-Schoffman, E. Danielle
and Silfee, J. Valerie
and Waring, E. Molly
and Boudreaux, D. Edwin
and Sadasivam, S. Rajani
and Mullen, P. Sean
and Carey, L. Jennifer
and Hayes, B. Rashelle
and Ding, Y. Eric
and Bennett, G. Gary
and Pagoto, L. Sherry",
title="Methods for Evaluating the Content, Usability, and Efficacy of Commercial Mobile Health Apps",
journal="JMIR Mhealth Uhealth",
year="2017",
month="Dec",
day="18",
volume="5",
number="12",
pages="e190",
keywords="mHealth",
keywords="mobile health",
keywords="mobile applications",
keywords="telemedicine/methods ",
keywords="treatment efficacy",
keywords="behavioral medicine",
keywords="chronic disease",
doi="10.2196/mhealth.8758",
url="http://mhealth.jmir.org/2017/12/e190/",
url="http://www.ncbi.nlm.nih.gov/pubmed/29254914"
}


@Article{info:doi/10.2196/mhealth.9061,
author="Nilsson, Ulrica
and Dahlberg, Karuna
and Jaensson, Maria",
title="The Swedish Web Version of the Quality of Recovery Scale Adapted for Use in a Mobile App: Prospective Psychometric Evaluation Study",
journal="JMIR Mhealth Uhealth",
year="2017",
month="Dec",
day="3",
volume="5",
number="12",
pages="e188",
keywords="psychometric evaluation",
keywords="postoperative recovery",
keywords="Web version",
keywords="evaluation studies",
keywords="mobile application",
keywords="Quality of Recovery scale",
abstract="Background: The 40-item Quality of Recovery (QoR-40) questionnaire is well validated for measuring self-assessed postoperative recovery. The Swedish version of the 40-item Quality of Recovery (QoR-40) has been developed into a Web-based questionnaire, the Swedish Web version of the Quality of Recovery (SwQoR) questionnaire, adapted for use in a mobile app, Recovery Assessment by Phone Points, or RAPP. Objective: The aim of this study was to test the validity, reliability, responsiveness, and clinical acceptability and feasibility of SwQoR. Methods: We conducted a prospective psychometric evaluation study including 494 patients aged ?18 years undergoing day surgery at 4 different day-surgery departments in Sweden. SwQoR was completed daily on postoperative days 1 to 14. Results: All a priori hypotheses were confirmed, supporting convergent validity. There was excellent internal consistency (Cronbach alpha range .91-.93), split-half reliability (coefficient range .87-.93), and stability (ri=.99, 95\% CI .96-.99; P<.001). Cohen d effect size was 1.00, with a standardized response mean of 1.2 and a percentage change from baseline of 59.1\%. An exploratory factor analysis found 5 components explaining 57.8\% of the total variance. We noted a floor effect only on postoperative day 14; we found no ceiling effect. Conclusions: SwQoR is valid, has excellent reliability and high responsiveness, and is clinically feasible for the systematic follow-up of patients' postoperative recovery. ",
doi="10.2196/mhealth.9061",
url="http://mhealth.jmir.org/2017/12/e188/",
url="http://www.ncbi.nlm.nih.gov/pubmed/29229590"
}


@Article{info:doi/10.2196/mhealth.7827,
author="Maduka, Omosivie
and Akpan, Godwin
and Maleghemi, Sylvester",
title="Using Android and Open Data Kit Technology in Data Management for Research in Resource-Limited Settings in the Niger Delta Region of Nigeria: Cross-Sectional Household Survey",
journal="JMIR Mhealth Uhealth",
year="2017",
month="Nov",
day="30",
volume="5",
number="11",
pages="e171",
keywords="mobile phones",
keywords="technology",
keywords="Africa",
abstract="Background: Data collection in Sub-Saharan Africa has traditionally been paper-based. However, the popularization of Android mobile devices and data capture software has brought paperless data management within reach. We used Open Data Kit (ODK) technology on Android mobile devices during a household survey in the Niger Delta region of Nigeria. Objective: The aim of this study was to describe the pros and cons of deploying ODK for data management. Methods: A descriptive cross-sectional household survey was carried out by 6 data collectors between April and May 2016. Data were obtained from 1706 persons in 601 households across 6 communities in 3 states in the Niger Delta. The use of Android mobile devices and ODK technology involved form building, testing, collection, aggregation, and download for data analysis. The median duration for data collection per household and per individual was 25.7 and 9.3 min, respectively. Results: Data entries per device ranged from 33 (33/1706, 1.93\%) to 482 (482/1706, 28.25\%) individuals between 9 (9/601, 1.5\%) and 122 (122/601, 20.3\%) households. The most entries (470) were made by data collector 5. Only 2 respondents had data entry errors (2/1706, 0.12\%). However, 73 (73/601, 12.1\%) households had inaccurate date and time entries for when data collection started and ended. The cost of deploying ODK was estimated at US \$206.7 in comparison with the estimated cost of US \$466.7 for paper-based data management. Conclusions: We found the use of mobile data capture technology to be efficient and cost-effective. As Internet services improve in Africa, we advocate their use as effective tools for health information management. ",
doi="10.2196/mhealth.7827",
url="http://mhealth.jmir.org/2017/11/e171/",
url="http://www.ncbi.nlm.nih.gov/pubmed/29191798"
}


@Article{info:doi/10.2196/mhealth.7441,
author="DiFilippo, Nicole Kristen
and Huang, Wenhao
and Chapman-Novakofski, M. Karen",
title="A New Tool for Nutrition App Quality Evaluation (AQEL): Development, Validation, and Reliability Testing",
journal="JMIR Mhealth Uhealth",
year="2017",
month="Oct",
day="27",
volume="5",
number="10",
pages="e163",
keywords="evaluation",
keywords="mobile apps",
keywords="dietitians",
keywords="health education",
keywords="diet, food, and nutrition",
abstract="Background: The extensive availability and increasing use of mobile apps for nutrition-based health interventions makes evaluation of the quality of these apps crucial for integration of apps into nutritional counseling. Objective: The goal of this research was the development, validation, and reliability testing of the app quality evaluation (AQEL) tool, an instrument for evaluating apps' educational quality and technical functionality. Methods: Items for evaluating app quality were adapted from website evaluations, with additional items added to evaluate the specific characteristics of apps, resulting in 79 initial items. Expert panels of nutrition and technology professionals and app users reviewed items for face and content validation. After recommended revisions, nutrition experts completed a second AQEL review to ensure clarity. On the basis of 150 sets of responses using the revised AQEL, principal component analysis was completed, reducing AQEL into 5 factors that underwent reliability testing, including internal consistency, split-half reliability, test-retest reliability, and interrater reliability (IRR). Two additional modifiable constructs for evaluating apps based on the age and needs of the target audience as selected by the evaluator were also tested for construct reliability. IRR testing using intraclass correlations (ICC) with all 7 constructs was conducted, with 15 dietitians evaluating one app. Results: Development and validation resulted in the 51-item AQEL. These were reduced to 25 items in 5 factors after principal component analysis, plus 9 modifiable items in two constructs that were not included in principal component analysis. Internal consistency and split-half reliability of the following constructs derived from principal components analysis was good (Cronbach alpha >.80, Spearman-Brown coefficient >.80): behavior change potential, support of knowledge acquisition, app function, and skill development. App purpose split half-reliability was .65. Test-retest reliability showed no significant change over time (P>.05) for all but skill development (P=.001). Construct reliability was good for items assessing age appropriateness of apps for children, teens, and a general audience. In addition, construct reliability was acceptable for assessing app appropriateness for various target audiences (Cronbach alpha >.70). For the 5 main factors, ICC (1,k) was >.80, with a P value of <.05. When 15 nutrition professionals evaluated one app, ICC (2,15) was .98, with a P value of <.001 for all 7 constructs when the modifiable items were specified for adults seeking weight loss support. Conclusions: Our preliminary effort shows that AQEL is a valid, reliable instrument for evaluating nutrition apps' qualities for clinical interventions by nutrition clinicians, educators, and researchers. Further efforts in validating AQEL in various contexts are needed. ",
doi="10.2196/mhealth.7441",
url="http://mhealth.jmir.org/2017/10/e163/",
url="http://www.ncbi.nlm.nih.gov/pubmed/29079554"
}


@Article{info:doi/10.2196/mhealth.7236,
author="Taki, Sarah
and Lymer, Sharyn
and Russell, Georgina Catherine
and Campbell, Karen
and Laws, Rachel
and Ong, Kok-Leong
and Elliott, Rosalind
and Denney-Wilson, Elizabeth",
title="Assessing User Engagement of an mHealth Intervention: Development and Implementation of the Growing Healthy App Engagement Index",
journal="JMIR Mhealth Uhealth",
year="2017",
month="Jun",
day="29",
volume="5",
number="6",
pages="e89",
keywords="mHealth",
keywords="social medium",
keywords="infant obesity",
keywords="infant development",
keywords="children",
keywords="infants",
keywords="practitioners",
keywords="primary healthcare",
abstract="Background: Childhood obesity is an ongoing problem in developed countries that needs targeted prevention in the youngest age groups. Children in socioeconomically disadvantaged families are most at risk. Mobile health (mHealth) interventions offer a potential route to target these families because of its relatively low cost and high reach. The Growing healthy program was developed to provide evidence-based information on infant feeding from birth to 9 months via app or website. Understanding user engagement with these media is vital to developing successful interventions. Engagement is a complex, multifactorial concept that needs to move beyond simple metrics. Objective: The aim of our study was to describe the development of an engagement index (EI) to monitor participant interaction with the Growing healthy app. The index included a number of subindices and cut-points to categorize engagement. Methods: The Growing program was a feasibility study in which 300 mother-infant dyads were provided with an app which included 3 push notifications that was sent each week. Growing healthy participants completed surveys at 3 time points: baseline (T1) (infant age ?3 months), infant aged 6 months (T2), and infant aged 9 months (T3). In addition, app usage data were captured from the app. The EI was adapted from the Web Analytics Demystified visitor EI. Our EI included 5 subindices: (1) click depth, (2) loyalty, (3) interaction, (4) recency, and (5) feedback. The overall EI summarized the subindices from date of registration through to 39 weeks (9 months) from the infant's date of birth. Basic descriptive data analysis was performed on the metrics and components of the EI as well as the final EI score. Group comparisons used t tests, analysis of variance (ANOVA), Mann-Whitney, Kruskal-Wallis, and Spearman correlation tests as appropriate. Consideration of independent variables associated with the EI score were modeled using linear regression models. Results: The overall EI mean score was 30.0\% (SD 11.5\%) with a range of 1.8\% - 57.6\%. The cut-points used for high engagement were scores greater than 37.1\% and for poor engagement were scores less than 21.1\%. Significant explanatory variables of the EI score included: parity (P=.005), system type including ``app only'' users or ``both'' app and email users (P<.001), recruitment method (P=.02), and baby age at recruitment (P=.005). Conclusions: The EI provided a comprehensive understanding of participant behavior with the app over the 9-month period of the Growing healthy program. The use of the EI in this study demonstrates that rich and useful data can be collected and used to inform assessments of the strengths and weaknesses of the app and in turn inform future interventions. ",
doi="10.2196/mhealth.7236",
url="http://mhealth.jmir.org/2017/6/e89/",
url="http://www.ncbi.nlm.nih.gov/pubmed/28663164"
}


@Article{info:doi/10.2196/mhealth.7291,
author="Bradway, Meghan
and Carrion, Carme
and Vallespin, B{\'a}rbara
and Saadatfard, Omid
and Puigdom{\`e}nech, Elisa
and Espallargues, Mireia
and Kotzeva, Anna",
title="mHealth Assessment: Conceptualization of a Global Framework",
journal="JMIR Mhealth Uhealth",
year="2017",
month="May",
day="02",
volume="5",
number="5",
pages="e60",
keywords="mhealth",
keywords="evaluation",
keywords="assessment",
keywords="checklist",
keywords="framework",
abstract="Background: The mass availability and use of mobile health (mHealth) technologies offers the potential for these technologies to support or substitute medical advice. However, it is worrisome that most assessment initiatives are still not able to successfully evaluate all aspects of mHealth solutions. As a result, multiple strategies to assess mHealth solutions are being proposed by medical regulatory bodies and similar organizations. Objective: We aim to offer a collective description of a universally applicable description of mHealth assessment initiatives, given their current and, as we see it, potential impact. In doing so, we recommend a common foundation for the development or update of assessment initiatives by addressing the multistakeholder issues that mHealth technology adds to the traditional medical environment. Methods: Organized by the Mobile World Capital Barcelona Foundation, we represent a workgroup consisting of patient associations, developers, and health authority representatives, including medical practitioners, within Europe. Contributions from each group's diverse competencies has allowed us to create an overview of the complex yet similar approaches to mHealth evaluation that are being developed today, including common gaps in concepts and perspectives. In response, we summarize commonalities of existing initiatives and exemplify additional characteristics that we believe will strengthen and unify these efforts. Results: As opposed to a universal standard or protocol in evaluating mHealth solutions, assessment frameworks should respect the needs and capacity of each medical system or country. Therefore, we expect that the medical system will specify the content, resources, and workflow of assessment protocols in order to ensure a sustainable plan for mHealth solutions within their respective countries. Conclusions: A common framework for all mHealth initiatives around the world will be useful in order to assess whatever mHealth solution is desirable in different areas, adapting it to the specifics of each context, to bridge the gap between health authorities, patients, and mHealth developers. We aim to foster a more trusting and collaborative environment to safeguard the well-being of patients and citizens while encouraging innovation of technology and policy. ",
doi="10.2196/mhealth.7291",
url="http://mhealth.jmir.org/2017/5/e60/",
url="http://www.ncbi.nlm.nih.gov/pubmed/28465282"
}


@Article{info:doi/10.2196/mhealth.7044,
author="Maar, A. Marion
and Yeates, Karen
and Perkins, Nancy
and Boesch, Lisa
and Hua-Stewart, Diane
and Liu, Peter
and Sleeth, Jessica
and Tobe, W. Sheldon",
title="A Framework for the Study of Complex mHealth Interventions in Diverse Cultural Settings",
journal="JMIR Mhealth Uhealth",
year="2017",
month="Apr",
day="20",
volume="5",
number="4",
pages="e47",
keywords="mobile health",
keywords="health care texting",
keywords="SMS",
keywords="protocol",
keywords="process evaluation",
keywords="process assessment (health care)",
keywords="health services, Indigenous",
keywords="Tanzania",
keywords="community-based participatory research",
keywords="DREAM-GLOBAL",
abstract="Background: To facilitate decision-making capacity between options of care under real-life service conditions, clinical trials must be pragmatic to evaluate mobile health (mHealth) interventions under the variable conditions of health care settings with a wide range of participants. The mHealth interventions require changes in the behavior of patients and providers, creating considerable complexity and ambiguity related to causal chains. Process evaluations of the implementation are necessary to shed light on the range of unanticipated effects an intervention may have, what the active ingredients in everyday practice are, how they exert their effect, and how these may vary among recipients or between sites. Objective: Building on the CONSORT-EHEALTH (Consolidated Standards of Reporting Trials of Electronic and Mobile HEalth Applications and onLine TeleHealth) statement and participatory evaluation theory, we present a framework for the process evaluations for mHealth interventions in multiple cultural settings. We also describe the application of this evaluation framework to the implementation of DREAM-GLOBAL (Diagnosing hypertension---Engaging Action and Management in Getting Lower BP in Indigenous and LMIC [low- and middle-income countries]), a pragmatic randomized controlled trial (RCT), and mHealth intervention designed to improve hypertension management in low-resource environments. We describe the evaluation questions and the data collection processes developed by us. Methods: Our literature review revealed that there is a significant knowledge gap related to the development of a process evaluation framework for mHealth interventions. We used community-based participatory research (CBPR) methods and formative research data to develop a process evaluation framework nested within a pragmatic RCT. Results: Four human organizational levels of participants impacted by the mHealth intervention were identified that included patients, providers, community and organizations actors, and health systems and settings. These four levels represent evaluation domains and became the core focus of the evaluation. In addition, primary implementation themes to explore in each of the domains were identified as follows: (1) the major active components of the intervention, (2) technology of the intervention, (3) cultural congruence, (4) task shifting, and (5) unintended consequences. Using the four organizational domains and their interaction with primary implementation themes, we developed detailed evaluation research questions and identified the data or information sources to best answer our questions. Conclusions: Using DREAM-GLOBAL to illustrate our approach, we succeeded in developing an uncomplicated process evaluation framework for mHealth interventions that provide key information to stakeholders, which can optimize implementation of a pragmatic trial as well as inform scale up. The human organizational level domains used to focus the primary implementation themes in the DREAM-GLOBAL process evaluation framework are sufficiently supported in our research, and the literature and can serve as a valuable tool for other mHealth process evaluations. Trial Registration: ClinicalTrials.gov NCT02111226; https://clinicaltrials.gov/ct2/show/NCT02111226 (Archived by WebCite at http://www.webcitation.org/6oxfHXege) ",
doi="10.2196/mhealth.7044",
url="http://mhealth.jmir.org/2017/4/e47/",
url="http://www.ncbi.nlm.nih.gov/pubmed/28428165"
}


@Article{info:doi/10.2196/jmir.7270,
author="Baumel, Amit
and Faber, Keren
and Mathur, Nandita
and Kane, M. John
and Muench, Fred",
title="Enlight: A Comprehensive Quality and Therapeutic Potential Evaluation Tool for Mobile and Web-Based eHealth Interventions",
journal="J Med Internet Res",
year="2017",
month="Mar",
day="21",
volume="19",
number="3",
pages="e82",
keywords="eHealth",
keywords="mHealth",
keywords="assessment",
keywords="evaluation",
keywords="quality",
keywords="persuasive design",
keywords="behavior change",
keywords="therapeutic alliance",
abstract="Background: Studies of criteria-based assessment tools have demonstrated the feasibility of objectively evaluating eHealth interventions independent of empirical testing. However, current tools have not included some quality constructs associated with intervention outcome, such as persuasive design, behavior change, or therapeutic alliance. In addition, the generalizability of such tools has not been explicitly examined. Objective: The aim is to introduce the development and further analysis of the Enlight suite of measures, developed to incorporate the aforementioned concepts and address generalizability aspects. Methods: As a first step, a comprehensive systematic review was performed to identify relevant quality rating criteria in line with the PRISMA statement. These criteria were then categorized to create Enlight. The second step involved testing Enlight on 42 mobile apps and 42 Web-based programs (delivery mediums) targeting modifiable behaviors related to medical illness or mental health (clinical aims). Results: A total of 476 criteria from 99 identified sources were used to build Enlight. The rating measures were divided into two sections: quality assessments and checklists. Quality assessments included usability, visual design, user engagement, content, therapeutic persuasiveness, therapeutic alliance, and general subjective evaluation. The checklists included credibility, privacy explanation, basic security, and evidence-based program ranking. The quality constructs exhibited excellent interrater reliability (intraclass correlations=.77-.98, median .91) and internal consistency (Cronbach alphas=.83-.90, median .88), with similar results when separated into delivery mediums or clinical aims. Conditional probability analysis revealed that 100\% of the programs that received a score of fair or above (?3.0) in therapeutic persuasiveness or therapeutic alliance received the same range of scores in user engagement and content---a pattern that did not appear in the opposite direction. Preliminary concurrent validity analysis pointed to positive correlations of combined quality scores with selected variables. The combined score that did not include therapeutic persuasiveness and therapeutic alliance descriptively underperformed the other combined scores. Conclusions: This paper provides empirical evidence supporting the importance of persuasive design and therapeutic alliance within the context of a program's evaluation. Reliability metrics and preliminary concurrent validity analysis indicate the potential of Enlight in examining eHealth programs regardless of delivery mediums and clinical aims. ",
doi="10.2196/jmir.7270",
url="http://www.jmir.org/2017/3/e82/",
url="http://www.ncbi.nlm.nih.gov/pubmed/28325712"
}


@Article{info:doi/10.2196/mhealth.6474,
author="Scherer, A. Emily
and Ben-Zeev, Dror
and Li, Zhigang
and Kane, M. John",
title="Analyzing mHealth Engagement: Joint Models for Intensively Collected User Engagement Data",
journal="JMIR Mhealth Uhealth",
year="2017",
month="Jan",
day="12",
volume="5",
number="1",
pages="e1",
keywords="joint models",
keywords="engagement",
keywords="informative missingness",
abstract="Background: Evaluating engagement with an intervention is a key component of understanding its efficacy. With an increasing interest in developing behavioral interventions in the mobile health (mHealth) space, appropriate methods for evaluating engagement in this context are necessary. Data collected to evaluate mHealth interventions are often collected much more frequently than those for clinic-based interventions. Additionally, missing data on engagement is closely linked to level of engagement resulting in the potential for informative missingness. Thus, models that can accommodate intensively collected data and can account for informative missingness are required for unbiased inference when analyzing engagement with an mHealth intervention. Objective: The objectives of this paper are to discuss the utility of the joint modeling approach in the analysis of longitudinal engagement data in mHealth research and to illustrate the application of this approach using data from an mHealth intervention designed to support illness management among people with schizophrenia. Methods: Engagement data from an evaluation of an mHealth intervention designed to support illness management among people with schizophrenia is analyzed. A joint model is applied to the longitudinal engagement outcome and time-to-dropout to allow unbiased inference on the engagement outcome. Results are compared to a na{\"i}ve model that does not account for the relationship between dropout and engagement. Results: The joint model shows a strong relationship between engagement and reduced risk of dropout. Using the mHealth app 1 day more per week was associated with a 23\% decreased risk of dropout (P<.001). The decline in engagement over time was steeper when the joint model was used in comparison with the na{\"i}ve model. Conclusions: Na{\"i}ve longitudinal models that do not account for informative missingness in mHealth data may produce biased results. Joint models provide a way to model intensively collected engagement outcomes while simultaneously accounting for the relationship between engagement and missing data in mHealth intervention research. ",
doi="10.2196/mhealth.6474",
url="http://mhealth.jmir.org/2017/1/e1/",
url="http://www.ncbi.nlm.nih.gov/pubmed/28082257"
}


@Article{info:doi/10.2196/resprot.6194,
author="Anderson, Kevin
and Burford, Oksana
and Emmerton, Lynne",
title="App Chronic Disease Checklist: Protocol to Evaluate Mobile Apps for Chronic Disease Self-Management",
journal="JMIR Res Protoc",
year="2016",
month="Nov",
day="04",
volume="5",
number="4",
pages="e204",
keywords="health",
keywords="mobile applications",
keywords="app",
keywords="smartphones",
keywords="self-management",
keywords="protocol",
keywords="usability checklist",
keywords="self-care",
keywords="chronic disease",
abstract="Background: The availability of mobile health apps for self-care continues to increase. While little evidence of their clinical impact has been published, there is general agreement among health authorities and authors that consumers' use of health apps assist in self-management and potentially clinical decision making. A consumer's sustained engagement with a health app is dependent on the usability and functionality of the app. While numerous studies have attempted to evaluate health apps, there is a paucity of published methods that adequately recognize client experiences in the academic evaluation of apps for chronic conditions. Objective: This paper reports (1) a protocol to shortlist health apps for academic evaluation, (2) synthesis of a checklist to screen health apps for quality and reliability, and (3) a proposed method to theoretically evaluate usability of health apps, with a view towards identifying one or more apps suitable for clinical assessment. Methods: A Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) flow diagram was developed to guide the selection of the apps to be assessed. The screening checklist was thematically synthesized with reference to recurring constructs in published checklists and related materials for the assessment of health apps. The checklist was evaluated by the authors for face and construct validity. The proposed method for evaluation of health apps required the design of procedures for raters of apps, dummy data entry to test the apps, and analysis of raters' scores. Results: The PRISMA flow diagram comprises 5 steps: filtering of duplicate apps; eliminating non-English apps; removing apps requiring purchase, filtering apps not updated within the past year; and separation of apps into their core functionality. The screening checklist to evaluate the selected apps was named the App Chronic Disease Checklist, and comprises 4 sections with 6 questions in each section. The validity check verified classification of, and ambiguity in, wording of questions within constructs. The proposed method to evaluate shortlisted and downloaded apps comprises instructions to attempt set-up of a dummy user profile, and dummy data entry to represent in-range and out-of-range clinical measures simulating a range of user behaviors. A minimum score of 80\% by consensus (using the Intraclass Correlation Coefficient) between raters is proposed to identify apps suitable for clinical trials. Conclusions: The flow diagram allows researchers to shortlist health apps that are potentially suitable for formal evaluation. The evaluation checklist enables quantitative comparison of shortlisted apps based on constructs reported in the literature. The use of multiple raters, and comparison of their scores, is proposed to manage inherent subjectivity in assessing user experiences. Initial trial of the combined protocol is planned for apps pertaining to the self-monitoring of asthma; these results will be reported elsewhere. ",
doi="10.2196/resprot.6194",
url="http://www.researchprotocols.org/2016/4/e204/",
url="http://www.ncbi.nlm.nih.gov/pubmed/27815233"
}


@Article{info:doi/10.2196/mhealth.5720,
author="Pham, Quynh
and Wiljer, David
and Cafazzo, A. Joseph",
title="Beyond the Randomized Controlled Trial: A Review of Alternatives in mHealth Clinical Trial Methods",
journal="JMIR Mhealth Uhealth",
year="2016",
month="Sep",
day="09",
volume="4",
number="3",
pages="e107",
keywords="mobile health",
keywords="mobile applications",
keywords="smartphones",
keywords="medical informatics",
keywords="research design",
keywords="clinical trials",
abstract="Background: Randomized controlled trials (RCTs) have long been considered the primary research study design capable of eliciting causal relationships between health interventions and consequent outcomes. However, with a prolonged duration from recruitment to publication, high-cost trial implementation, and a rigid trial protocol, RCTs are perceived as an impractical evaluation methodology for most mHealth apps. Objective: Given the recent development of alternative evaluation methodologies and tools to automate mHealth research, we sought to determine the breadth of these methods and the extent that they were being used in clinical trials. Methods: We conducted a review of the ClinicalTrials.gov registry to identify and examine current clinical trials involving mHealth apps and retrieved relevant trials registered between November 2014 and November 2015. Results: Of the 137 trials identified, 71 were found to meet inclusion criteria. The majority used a randomized controlled trial design (80\%, 57/71). Study designs included 36 two-group pretest-posttest control group comparisons (51\%, 36/71), 16 posttest-only control group comparisons (23\%, 16/71), 7 one-group pretest-posttest designs (10\%, 7/71), 2 one-shot case study designs (3\%, 2/71), and 2 static-group comparisons (3\%, 2/71). A total of 17 trials included a qualitative component to their methodology (24\%, 17/71). Complete trial data collection required 20 months on average to complete (mean 21, SD 12). For trials with a total duration of 2 years or more (31\%, 22/71), the average time from recruitment to complete data collection (mean 35 months, SD 10) was 2 years longer than the average time required to collect primary data (mean 11, SD 8). Trials had a moderate sample size of 112 participants. Two trials were conducted online (3\%, 2/71) and 7 trials collected data continuously (10\%, 7/68). Onsite study implementation was heavily favored (97\%, 69/71). Trials with four data collection points had a longer study duration than trials with two data collection points: F4,56=3.2, P=.021, $\eta$2=0.18. Single-blinded trials had a longer data collection period compared to open trials: F2,58=3.8, P=.028, $\eta$2=0.12. Academic sponsorship was the most common form of trial funding (73\%, 52/71). Trials with academic sponsorship had a longer study duration compared to industry sponsorship: F2,61=3.7, P=.030, $\eta$2=0.11. Combined, data collection frequency, study masking, sample size, and study sponsorship accounted for 32.6\% of the variance in study duration: F4,55=6.6, P<.01, adjusted r2=.33. Only 7 trials had been completed at the time this retrospective review was conducted (10\%, 7/71). Conclusions: mHealth evaluation methodology has not deviated from common methods, despite the need for more relevant and timely evaluations. There is a need for clinical evaluation to keep pace with the level of innovation of mHealth if it is to have meaningful impact in informing payers, providers, policy makers, and patients. ",
doi="10.2196/mhealth.5720",
url="http://mhealth.jmir.org/2016/3/e107/",
url="http://www.ncbi.nlm.nih.gov/pubmed/27613084"
}


@Article{info:doi/10.2196/mhealth.5738,
author="Pereira-Azevedo, Nuno
and Os{\'o}rio, Lu{\'i}s
and Cavadas, Vitor
and Fraga, Avelino
and Carrasquinho, Eduardo
and Cardoso de Oliveira, Eduardo
and Castelo-Branco, Miguel
and Roobol, J. Monique",
title="Expert Involvement Predicts mHealth App Downloads: Multivariate Regression Analysis of Urology Apps",
journal="JMIR Mhealth Uhealth",
year="2016",
month="Jul",
day="15",
volume="4",
number="3",
pages="e86",
keywords="eHealth",
keywords="mHealth",
keywords="urology",
keywords="mobile apps",
keywords="new technologies",
abstract="Background: Urological mobile medical (mHealth) apps are gaining popularity with both clinicians and patients. mHealth is a rapidly evolving and heterogeneous field, with some urology apps being downloaded over 10,000 times and others not at all. The factors that contribute to medical app downloads have yet to be identified, including the hypothetical influence of expert involvement in app development. Objective: The objective of our study was to identify predictors of the number of urology app downloads. Methods: We reviewed urology apps available in the Google Play Store and collected publicly available data. Multivariate ordinal logistic regression evaluated the effect of publicly available app variables on the number of apps being downloaded. Results: Of 129 urology apps eligible for study, only 2 (1.6\%) had >10,000 downloads, with half having ?100 downloads and 4 (3.1\%) having none at all. Apps developed with expert urologist involvement (P=.003), optional in-app purchases (P=.01), higher user rating (P<.001), and more user reviews (P<.001) were more likely to be installed. App cost was inversely related to the number of downloads (P<.001). Only data from the Google Play Store and the developers' websites, but not other platforms, were publicly available for analysis, and the level and nature of expert involvement was not documented. Conclusions: The explicit participation of urologists in app development is likely to enhance its chances to have a higher number of downloads. This finding should help in the design of better apps and further promote urologist involvement in mHealth. Official certification processes are required to ensure app quality and user safety. ",
doi="10.2196/mhealth.5738",
url="http://mhealth.jmir.org/2016/3/e86/",
url="http://www.ncbi.nlm.nih.gov/pubmed/27421338"
}


@Article{info:doi/10.2196/mhealth.5849,
author="Stoyanov, R. Stoyan
and Hides, Leanne
and Kavanagh, J. David
and Wilson, Hollie",
title="Development and Validation of the User Version of the Mobile Application Rating Scale (uMARS)",
journal="JMIR Mhealth Uhealth",
year="2016",
month="Jun",
day="10",
volume="4",
number="2",
pages="e72",
keywords="MARS",
keywords="mHealth",
keywords="eHealth",
keywords="app evaluation",
keywords="end user",
keywords="app trial",
keywords="mhealth trial",
keywords="user testing",
keywords="mobile application",
keywords="app rating",
keywords="reliability",
keywords="mobile health",
keywords="well being",
keywords="mental health",
keywords="smartphone",
keywords="cellphone",
keywords="telemedicine",
keywords="emental health",
keywords="e-therapy",
keywords="Internet",
keywords="online",
keywords="cognitive behavioral therapy",
keywords="anxiety",
keywords="anxiety disorders",
keywords="depression",
keywords="depressive disorder",
keywords="Australia",
keywords="research translation",
keywords="evidence-informed",
keywords="mHealth implementation",
keywords="mHealth evaluation",
keywords="randomized controlled trial",
keywords="RCT",
abstract="Background: The Mobile Application Rating Scale (MARS) provides a reliable method to assess the quality of mobile health (mHealth) apps. However, training and expertise in mHealth and the relevant health field is required to administer it. Objective: This study describes the development and reliability testing of an end-user version of the MARS (uMARS). Methods: The MARS was simplified and piloted with 13 young people to create the uMARS. The internal consistency and test-retest reliability of the uMARS was then examined in a second sample of 164 young people participating in a randomized controlled trial of a mHealth app. App ratings were collected using the uMARS at 1-, 3,- and 6-month follow up. Results: The uMARS had excellent internal consistency (alpha = .90), with high individual alphas for all subscales. The total score and subscales had good test-retest reliability over both 1-2 months and 3 months. Conclusions: The uMARS is a simple tool that can be reliably used by end-users to assess the quality of mHealth apps. ",
doi="10.2196/mhealth.5849",
url="http://mhealth.jmir.org/2016/2/e72/",
url="http://www.ncbi.nlm.nih.gov/pubmed/27287964"
}


@Article{info:doi/10.2196/resprot.4838,
author="Wilhide III, C. Calvin
and Peeples, M. Malinda
and Anthony Kouyat{\'e}, C. Robin",
title="Evidence-Based mHealth Chronic Disease Mobile App Intervention Design: Development of a Framework",
journal="JMIR Res Protoc",
year="2016",
month="Feb",
day="16",
volume="5",
number="1",
pages="e25",
keywords="mHealth",
keywords="mobile applications",
keywords="mobile app design",
keywords="chronic disease",
keywords="diabetes",
keywords="mHealth framework",
keywords="behavioral intervention",
keywords="intervention design",
keywords="mHealth implementation",
keywords="telemedicine",
abstract="Background: Mobile technology offers new capabilities that can help to drive important aspects of chronic disease management at both an individual and population level, including the ability to deliver real-time interventions that can be connected to a health care team. A framework that supports both development and evaluation is needed to understand the aspects of mHealth that work for specific diseases, populations, and in the achievement of specific outcomes in real-world settings. This framework should incorporate design structure and process, which are important to translate clinical and behavioral evidence, user interface, experience design and technical capabilities into scalable, replicable, and evidence-based mobile health (mHealth) solutions to drive outcomes. Objective: The purpose of this paper is to discuss the identification and development of an app intervention design framework, and its subsequent refinement through development of various types of mHealth apps for chronic disease. Methods: The process of developing the framework was conducted between June 2012 and June 2014. Informed by clinical guidelines, standards of care, clinical practice recommendations, evidence-based research, best practices, and translated by subject matter experts, a framework for mobile app design was developed and the refinement of the framework across seven chronic disease states and three different product types is described. Results: The result was the development of the Chronic Disease mHealth App Intervention Design Framework. This framework allowed for the integration of clinical and behavioral evidence for intervention and feature design. The application to different diseases and implementation models guided the design of mHealth solutions for varying levels of chronic disease management. Conclusions: The framework and its design elements enable replicable product development for mHealth apps and may provide a foundation for the digital health industry to systematically expand mobile health interventions and validate their effectiveness across multiple implementation settings and chronic diseases. ",
doi="10.2196/resprot.4838",
url="http://www.researchprotocols.org/2016/1/e25/",
url="http://www.ncbi.nlm.nih.gov/pubmed/26883135"
}


@Article{info:doi/10.2196/mhealth.5176,
author="Powell, C. Adam
and Torous, John
and Chan, Steven
and Raynor, Stephen Geoffrey
and Shwarts, Erik
and Shanahan, Meghan
and Landman, B. Adam",
title="Interrater Reliability of mHealth App Rating Measures: Analysis of Top Depression and Smoking Cessation Apps",
journal="JMIR mHealth uHealth",
year="2016",
month="Feb",
day="10",
volume="4",
number="1",
pages="e15",
keywords="mobile applications",
keywords="mental health",
keywords="evaluation studies",
keywords="health apps",
keywords="ratings",
abstract="Background: There are over 165,000 mHealth apps currently available to patients, but few have undergone an external quality review. Furthermore, no standardized review method exists, and little has been done to examine the consistency of the evaluation systems themselves. Objective: We sought to determine which measures for evaluating the quality of mHealth apps have the greatest interrater reliability. Methods: We identified 22 measures for evaluating the quality of apps from the literature. A panel of 6 reviewers reviewed the top 10 depression apps and 10 smoking cessation apps from the Apple iTunes App Store on these measures. Krippendorff's alpha was calculated for each of the measures and reported by app category and in aggregate. Results: The measure for interactiveness and feedback was found to have the greatest overall interrater reliability (alpha=.69). Presence of password protection (alpha=.65), whether the app was uploaded by a health care agency (alpha=.63), the number of consumer ratings (alpha=.59), and several other measures had moderate interrater reliability (alphas>.5). There was the least agreement over whether apps had errors or performance issues (alpha=.15), stated advertising policies (alpha=.16), and were easy to use (alpha=.18). There were substantial differences in the interrater reliabilities of a number of measures when they were applied to depression versus smoking apps. Conclusions: We found wide variation in the interrater reliability of measures used to evaluate apps, and some measures are more robust across categories of apps than others. The measures with the highest degree of interrater reliability tended to be those that involved the least rater discretion. Clinical quality measures such as effectiveness, ease of use, and performance had relatively poor interrater reliability. Subsequent research is needed to determine consistent means for evaluating the performance of apps. Patients and clinicians should consider conducting their own assessments of apps, in conjunction with evaluating information from reviews. ",
doi="10.2196/mhealth.5176",
url="http://mhealth.jmir.org/2016/1/e15/",
url="http://www.ncbi.nlm.nih.gov/pubmed/26863986"
}


@Article{info:doi/10.2196/jmir.4284,
author="Lewis, Lorchan Thomas
and Wyatt, C. Jeremy",
title="App Usage Factor: A Simple Metric to Compare the Population Impact of Mobile Medical Apps",
journal="J Med Internet Res",
year="2015",
month="Aug",
day="19",
volume="17",
number="8",
pages="e200",
keywords="mHealth",
keywords="medical app",
keywords="mobile phone",
keywords="metric",
keywords="risk assessment",
keywords="medical informatics apps",
keywords="population impact",
keywords="mobile health",
keywords="patient safety",
keywords="mobile app",
abstract="Background: One factor when assessing the quality of mobile apps is quantifying the impact of a given app on a population. There is currently no metric which can be used to compare the population impact of a mobile app across different health care disciplines. Objective: The objective of this study is to create a novel metric to characterize the impact of a mobile app on a population. Methods: We developed the simple novel metric, app usage factor (AUF), defined as the logarithm of the product of the number of active users of a mobile app with the median number of daily uses of the app. The behavior of this metric was modeled using simulated modeling in Python, a general-purpose programming language. Three simulations were conducted to explore the temporal and numerical stability of our metric and a simulated app ecosystem model using a simulated dataset of 20,000 apps. Results: Simulations confirmed the metric was stable between predicted usage limits and remained stable at extremes of these limits. Analysis of a simulated dataset of 20,000 apps calculated an average value for the app usage factor of 4.90 (SD 0.78). A temporal simulation showed that the metric remained stable over time and suitable limits for its use were identified. Conclusions: A key component when assessing app risk and potential harm is understanding the potential population impact of each mobile app. Our metric has many potential uses for a wide range of stakeholders in the app ecosystem, including users, regulators, developers, and health care professionals. Furthermore, this metric forms part of the overall estimate of risk and potential for harm or benefit posed by a mobile medical app. We identify the merits and limitations of this metric, as well as potential avenues for future validation and research. ",
doi="10.2196/jmir.4284",
url="http://www.jmir.org/2015/8/e200/",
url="http://www.ncbi.nlm.nih.gov/pubmed/26290093"
}


@Article{info:doi/10.2196/jmir.4359,
author="Lane, S. Taylor
and Armin, Julie
and Gordon, S. Judith",
title="Online Recruitment Methods for Web-Based and Mobile Health Studies: A Review of the Literature",
journal="J Med Internet Res",
year="2015",
month="Jul",
day="22",
volume="17",
number="7",
pages="e183",
keywords="mHealth",
keywords="Internet health",
keywords="online recruitment",
keywords="apps",
keywords="social media",
keywords="review",
abstract="Background: Internet and mobile health (mHealth) apps hold promise for expanding the reach of evidence-based health interventions. Research in this area is rapidly expanding. However, these studies may experience problems with recruitment and retention. Web-based and mHealth studies are in need of a wide-reaching and low-cost method of recruitment that will also effectively retain participants for the duration of the study. Online recruitment may be a low-cost and wide-reaching tool in comparison to traditional recruitment methods, although empirical evidence is limited. Objective: This study aims to review the literature on online recruitment for, and retention in, mHealth studies. Methods: We conducted a review of the literature of studies examining online recruitment methods as a viable means of obtaining mHealth research participants. The data sources used were PubMed, CINAHL, EbscoHost, PyscINFO, and MEDLINE. Studies reporting at least one method of online recruitment were included. A narrative approach enabled the authors to discuss the variability in recruitment results, as well as in recruitment duration and study design. Results: From 550 initial publications, 12 studies were included in this review. The studies reported multiple uses and outcomes for online recruitment methods. Web-based recruitment was the only type of recruitment used in 67\% (8/12) of the studies. Online recruitment was used for studies with a variety of health domains: smoking cessation (58\%; 7/12) and mental health (17\%; 2/12) being the most common. Recruitment duration lasted under a year in 67\% (8/12) of the studies, with an average of 5 months spent on recruiting. In those studies that spent over a year (33\%; 4/12), an average of 17 months was spent on recruiting. A little less than half (42\%; 5/12) of the studies found Facebook ads or newsfeed posts to be an effective method of recruitment, a quarter (25\%; 3/12) of the studies found Google ads to be the most effective way to reach participants, and one study showed better outcomes with traditional (eg in-person) methods of recruitment. Only one study recorded retention rates in their results, and half (50\%; 6/12) of the studies recorded survey completion rates. Conclusions: Although online methods of recruitment may be promising in experimental research, more empirical evidence is needed to make specific recommendations. Several barriers to using online recruitment were identified, including participant retention. These unique challenges of virtual interventions can affect the generalizability and validity of findings from Web-based and mHealth studies. There is a need for additional research to evaluate the effectiveness of online recruitment methods and participant retention in experimental mHealth studies. ",
doi="10.2196/jmir.4359",
url="http://www.jmir.org/2015/7/e183/",
url="http://www.ncbi.nlm.nih.gov/pubmed/26202991"
}


@Article{info:doi/10.2196/mhealth.3941,
author="Brown III, William
and Ibitoye, Mobolaji
and Bakken, Suzanne
and Schnall, Rebecca
and Bal{\'a}n, Iv{\'a}n
and Frasca, Timothy
and Carballo-Di{\'e}guez, Alex",
title="Cartographic Analysis of Antennas and Towers: A Novel Approach to Improving the Implementation and Data Transmission of mHealth Tools on Mobile Networks",
journal="JMIR mHealth uHealth",
year="2015",
month="Jun",
day="04",
volume="3",
number="2",
pages="e63",
keywords="cartographic analysis",
keywords="mHealth",
keywords="mobile health",
keywords="antenna",
keywords="short message service",
keywords="text messaging",
keywords="SMS",
keywords="wireless",
keywords="HIV",
abstract="Background: Most mHealth tools such as short message service (SMS), mobile apps, wireless pill counters, and ingestible wireless monitors use mobile antennas to communicate. Limited signal availability, often due to poor antenna infrastructure, negatively impacts the implementation of mHealth tools and remote data collection. Assessing the antenna infrastructure prior to starting a study can help mitigate this problem. Currently, there are no studies that detail whether and how the antenna infrastructure of a study site or area is assessed. Objective: To address this literature gap, we analyze and discuss the use of a cartographic analysis of antennas and towers (CAAT) for mobile communications for geographically assessing mobile antenna and tower infrastructure and identifying signal availability for mobile devices prior to the implementation of an SMS-based mHealth pilot study. Methods: An alpha test of the SMS system was performed using 11 site staff. A CAAT for the study area's mobile network was performed after the alpha test and pre-implementation of the pilot study. The pilot study used a convenience sample of 11 high-risk men who have sex with men who were given human immunodeficiency virus test kits for testing nonmonogamous sexual partners before intercourse. Product use and sexual behavior were tracked through SMS. Message frequency analyses were performed on the SMS text messages, and SMS sent/received frequencies of 11 staff and 11 pilot study participants were compared. Results: The CAAT helped us to successfully identify strengths and weaknesses in mobile service capacity within a 3-mile radius from the epicenters of four New York City boroughs. During the alpha test, before CAAT, 1176/1202 (97.84\%) text messages were sent to staff, of which 26/1176 (2.21\%) failed. After the CAAT, 2934 messages were sent to pilot study participants and none failed. Conclusions: The CAAT effectively illustrated the research area's mobile infrastructure and signal availability, which allowed us to improve study setup and sent message success rates. The SMS messages were sent and received with a lower fail rate than those reported in previous studies. ",
doi="10.2196/mhealth.3941",
url="http://mhealth.jmir.org/2015/2/e63/",
url="http://www.ncbi.nlm.nih.gov/pubmed/26043766"
}


@Article{info:doi/10.2196/mhealth.3928,
author="Fukuoka, Yoshimi
and Gay, Caryl
and Haskell, William
and Arai, Shoshana
and Vittinghoff, Eric",
title="Identifying Factors Associated With Dropout During Prerandomization Run-in Period From an mHealth Physical Activity Education Study: The mPED Trial",
journal="JMIR mHealth uHealth",
year="2015",
month="Apr",
day="13",
volume="3",
number="2",
pages="e34",
keywords="run-in period",
keywords="eligibility",
keywords="randomized controlled trial",
keywords="pedometer",
keywords="mobile phone",
keywords="mHealth",
abstract="Background: The mobile phone-based physical activity education (mPED) trial is a randomized controlled trial (RCT) evaluating a mobile phone-delivered physical activity intervention for women. The study includes a run-in period to maximize the internal validity of the intervention trial, but little is known about factors related to successful run-in completion, and thus about potential threats to external validity. Objective: Objectives of this study are (1) to determine the timing of dropout during the run-in period, reasons for dropout, optimum run-in duration, and relevant run-in components, and (2) to identify predictors of failure to complete the run-in period. Methods: A total of 318 physically inactive women met preliminary eligibility criteria and were enrolled in the study between May 2011 and April 2014. A 3-week run-in period was required prior to randomization and included using a mobile phone app and wearing a pedometer. Cross-sectional analysis identified predictors of dropout. Results: Out of 318 participants, 108 (34.0\%) dropped out prior to randomization, with poor adherence using the study equipment being the most common reason. Median failure time was 17 days into the run-in period. In univariate analyses, nonrandomized participants were younger, had lower income, were less likely to drive regularly, were less likely to have used a pedometer prior to the study, were generally less healthy, had less self-efficacy for physical activity, and reported more depressive symptoms than randomized participants. In multivariate competing risks models, not driving regularly in the past month and not having used a pedometer prior to the study were significantly associated with failure to be randomized (P=.04 and .006, respectively), controlling for age, race/ethnicity, education, shift work, and use of a study-provided mobile phone. Conclusions: Regular driving and past pedometer use were associated with reduced dropout during the prerandomization run-in period.  Understanding these characteristics is important for identifying higher-risk participants, and implementing additional help strategies may be useful for reducing dropout. Trial Registration: ClinicalTrials.gov NCT01280812; https://clinicaltrials.gov/ct2/show/NCT01280812 (Archived by WebCite at http://www.webcitation.org/6XFC5wvrP). ",
doi="10.2196/mhealth.3928",
url="http://mhealth.jmir.org/2015/2/e34/",
url="http://www.ncbi.nlm.nih.gov/pubmed/25872754"
}