Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.
Who will be affected?
Readers: No access to all 28 journals. We recommend accessing our articles via PubMed Central
Authors: No access to the submission form or your user account.
Reviewers: No access to your user account. Please download manuscripts you are reviewing for offline reading before Wednesday, July 01, 2020 at 7:00 PM.
Editors: No access to your user account to assign reviewers or make decisions.
Copyeditors: No access to user account. Please download manuscripts you are copyediting before Wednesday, July 01, 2020 at 7:00 PM.
Background: Accurate objective pain assessment is required in the healthcare domain and clinical settings for appropriate pain management. Automated objective pain detection from physiological data in patients provides valuable information to hospital staff and caregivers to better manage pain, in particular for those patients who are unable to self-report. Galvanic Skin Response (GSR) is one of the physiologic signals that refers to the changes in sweat gland activity, which can identify the features of emotional states and anxiety induced by varying pain levels. In this study, we used different statistical features extracted from GSR data collected from postoperative patients to detect their pain intensity. To the best of our knowledge, we are the first work building pain models using postoperative adult patients instead of healthy subjects. Objective: The goal of this paper is to present an automatic pain assessment tool using GSR signals to predict different pain intensities in non-communicative postoperative patients. Methods: The study was designed to collect biomedical data from post-operative patients reporting moderate to high pain levels. 25 subjects were recruited with the age range of 23 to 89. First, a Transcutaneous Electrical Nerve Stimulation (TENS) unit was employed to obtain patients' baselines. In the second part, the Empatica E4 wristband was attached to patients while they were performing low intensity activities. Patient self-report based on the NRS was used to record pain intensities used to correlate with the objective measured data. The labels were downsampled from 11 pain levels to 5 different pain intensities including the baseline. Two different machine learning algorithms were used to construct the models. The mean decrease impurity method was used to find the top important features for pain prediction and improve the accuracy. We compared our results with a previously published research study to estimate the true performance of our models. Results: Four different binary classification models were constructed using each machine learning algorithm to classify the baseline and other pain intensities (Baseline (BL) vs. Pain Level (PL) 1, BL vs. PL2, BL vs. PL3, and BL vs. PL4). Our models achieved the higher accuracy for the first three pain models in comparison with BioVid paper approach despite the challenges in analyzing real patient data. For BL vs. PL1, BL vs. PL2, and BL vs. PL4, the highest prediction accuracies were achieved when using a Random Forest classifier (86.0, 70.0, and 61.5, respectively). For BL vs. PL3, we achieved the accuracy of 72.1 using a K-nearest neighbors classifier. Conclusions: We are the first to propose and validate the pain assessment tool to predict different pain levels in real postoperative adult patients using GSR signals. We also exploited feature selection algorithms to find the top important features related to different pain intensities.
(Toronto, Sep 22, 2020) We are happy to announce that JMIR mHealth and uHealth, which published its first article in 2013, has been accepted for coverage in American Psychological Association’s (APA) PsycINFO.
JMIR Publications is pleased to have the following journals covered in PsycINFO:
Journal of Medical Internet Research
JMIR Human Factors (approved September 22, 2020)
JMIR Mental Health (approved September 22, 2020)
JMIR Serious Games (approved September 22, 2020)
APA is the leading scientific and professional organization representing psychology in the United States, with more than 121,000 researchers, educators, clinicians, consultants and students as its members worldwide. APA’s PsycINFO is a world-class resource for abstracts and citations of behavioral and social science research and JMIR Publications is glad to be a part of it.
The citations will be searchable once APA does the next quarterly update for PsycINFO.
JMIR mHealth and uHealth (JMU, ISSN 2291-5222; Impact Factor 4.31) is a sister journal of JMIR, the leading eHealth journal. JMIR mHealth and uHealth is indexed in PubMed, PubMed Central, Scopus, MEDLINE and Science Citation Index Expanded (SCIE), and in June 2020 received an Impact Factor of 4.31, ranking the journal Q1 in the medical informatics category indexed by the Science Citation Index Expanded (SCIE) by Thomson Reuters/Clarivate.
The journal focusses on health and biomedical applications in mobile and tablet computing, pervasive and ubiquitous computing, wearable computing and domotics.
JMIR mHealth and uHealth publishes since 2013 and was the first mhealth journal in Pubmed. It publishes even faster and has a broader scope with including papers which are more technical or more formative/developmental than what would be published in the Journal of Medical Internet Research.
JMIR mHealth and uHealth features a rapid and thorough peer-review process, professional copyediting, professional production of PDF, XHTML, and XML proofs.
JMIR mHealth and uHealth adheres to the same quality standards as JMIR and all articles published here are also cross-listed in the Table of Contents of JMIR, the worlds' leading medical journal in health sciences / health services research and health informatics.
Background: Effective contact tracing is labor intensive and time sensitive during the COVID-19 pandemic, but also essential in the absence of effective treatment and vaccines. Singapore launched the first Bluetooth-based contact tracing app—TraceTogether—in March 2020 to augment Singapore’s contact tracing capabilities.
Objective: This study aims to compare the performance of the contact tracing app—TraceTogether—with that of a wearable tag-based real-time locating system (RTLS) and to validate them against the electronic medical records at the National Centre for Infectious Diseases (NCID), the national referral center for COVID-19 screening.
Methods: All patients and physicians in the NCID screening center were issued RTLS tags (CADI Scientific) for contact tracing. In total, 18 physicians were deployed to the NCID screening center from May 10 to May 20, 2020. The physicians activated the TraceTogether app (version 1.6; GovTech) on their smartphones during shifts and urged their patients to use the app. We compared patient contacts identified by TraceTogether and those identified by RTLS tags within the NCID vicinity during physicians’ 10-day posting. We also validated both digital contact tracing tools by verifying the physician-patient contacts with the electronic medical records of 156 patients who attended the NCID screening center over a 24-hour time frame within the study period.
Results: RTLS tags had a high sensitivity of 95.3% for detecting patient contacts identified either by the system or TraceTogether while TraceTogether had an overall sensitivity of 6.5% and performed significantly better on Android phones than iPhones (Android: 9.7%, iPhone: 2.7%; P<.001). When validated against the electronic medical records, RTLS tags had a sensitivity of 96.9% and specificity of 83.1%, while TraceTogether only detected 2 patient contacts with physicians who did not attend to them.
Conclusions: TraceTogether had a much lower sensitivity than RTLS tags for identifying patient contacts in a clinical setting. Although the tag-based RTLS performed well for contact tracing in a clinical setting, its implementation in the community would be more challenging than TraceTogether. Given the uncertainty of the adoption and capabilities of contact tracing apps, policy makers should be cautioned against overreliance on such apps for contact tracing. Nonetheless, leveraging technology to augment conventional manual contact tracing is a necessary move for returning some normalcy to life during the long haul of the COVID-19 pandemic.
Background: Associations between higher levels of patient engagement and better health outcomes have been found in face-to-face interventions; studies on such associations with mobile health (mHealth) interventions have been limited and the results are inconclusive.
Objective: The objective of this study is to investigate the relationship between patient engagement in an mHealth intervention and depressive symptoms using repeated measures of both patient engagement and patient outcomes at 4 time points.
Methods: Data were drawn from a randomized controlled trial (RCT) of an mHealth intervention aimed at reducing depressive symptoms among people living with HIV and elevated depressive symptoms. We examined the association between patient engagement and depressive symptoms in the intervention group (n=150) where participants received an adapted cognitive-behavioral stress management (CBSM) course and physical activity promotion on their WeChat social media app. Depressive symptoms were repeatedly measured using the Patient Health Questionnaire (PHQ-9) at baseline and 1 month, 2 months, and 3 months. Patient engagement was correspondingly measured by the completion rate, frequency of items completed, and time spent on the program at 1 month, 2 months, and 3 months. Latent growth curve models (LGCMs) were used to explore the relationship between patient engagement and depressive symptoms at multiple time points in the intervention.
Results: The mean PHQ-9 scores were 10.2 (SD 4.5), 7.7 (SD 4.8), 6.5 (SD 4.7), and 6.7 (SD 4.1) at baseline, 1 month, 2 months, and 3 months, respectively. The mean completion rates were 50.6% (SD 31.8%), 51.5% (SD 32.2%), and 50.8% (SD 33.7%) at 1, 2, and 3 months, respectively; the average frequencies of items completed were 18.0 (SD 14.6), 32.6 (SD 24.8), and 47.5 (SD 37.2) at 1, 2, and 3 months, respectively, and the mean times spent on the program were 32.7 (SD 66.7), 65.4 (SD 120.8), and 96.4 (SD 180.4) minutes at 1, 2, and 3 months, respectively. LGCMs showed good model fit and indicated that a higher completion rate (β at 3 months=–2.184, P=.048) and a greater frequency of items completed (β at 3 months=–0.018, P=.04) were associated with fewer depressive symptoms at 3 months. Although not significant, similar trends were found in the abovementioned relationships at 1 and 2 months. There was no significant relationship between time spent on the program and depressive symptoms.
Conclusions: This study revealed a positive association between patient engagement and health outcomes at 3 months of an mHealth intervention using LGCMs and repeated measures data. The results underscore the importance of improving patient engagement in mHealth interventions to improve patient-centered health outcomes.
Trial Registration: Chinese Clinical Trial Registry ChiCTR-IPR-17012606; https://tinyurl.com/yxb64mef
Background: Worldwide, more than 75% of people with acquired brain injury (ABI) experience communication disorders. Communication disorders are impairments in the ability to communicate effectively, that is, sending, receiving, processing, and comprehending verbal and nonverbal concepts and symbols. Such disorders may have enduring impacts on employment, social participation, and quality of life. Technology-enabled interventions such as mobile apps have the potential to increase the reach of speech-language therapy to treat communication disorders. However, ensuring that apps are evidence-based and of high quality is critical for facilitating safe and effective treatment for adults with communication disorders.
Objective: The aim of this review is to identify mobile apps that are currently widely available to adults with communication disorders for speech-language therapy and to assess their content and quality using the validated Mobile App Rating Scale (MARS).
Methods: Google Play Store, Apple App Store, and webpages were searched to identify mobile apps for speech-language therapy. Apps were included in the review if they were designed for the treatment of adult communication disorders after ABI, were in English, and were either free or for purchase. Certified speech-language pathologists used the MARS to assess the quality of the apps.
Results: From a total of 2680 apps identified from Google Play Store, Apple App Store, and web searches, 2.61% (70/2680) apps met the eligibility criteria for inclusion. Overall, 61% (43/70) were available for download on the iPhone Operating System (iOS) platform, 20% (14/70) on the Android platform, and 19% (13/70) on both iOS and Android platforms. A content analysis of the apps revealed 43 apps for language, 17 apps for speech, 8 apps for cognitive communication, 6 apps for voice, and 5 apps for oromotor function or numeracy. The overall MARS mean score was 3.7 out of 5, SD 0.6, ranging between 2.1 and 4.5, with functionality being the highest-scored subscale (4.3, SD 0.6), followed by aesthetics (3.8, SD 0.8), information (3.4, SD 0.6), and engagement (3.3, SD 0.6). The top 5 apps were Naming Therapy (4.6/5), Speech Flipbook Standard (4.6/5), Number Therapy (4.5/5), Answering Therapy, and Constant Therapy (4.4/5).
Conclusions: To our knowledge, this is the first study to systematically identify and evaluate a broad range of mobile apps for speech-language therapy for adults with communication disorders after sustaining ABI. We found a lack of interactive and engaging elements in the apps, a critical factor in sustaining self-managed speech-language therapy. More evidence-based apps with a focus on human factors, user experience, and a patient-led design approach are required to enhance effectiveness and long-term use.
Background: Although healthy aging can be stimulated by the reduction of sedentary behavior, few interventions are available for older adults. Previous studies suggest that self-monitoring might be a promising behavior change technique to reduce older adults’ sedentary behavior. However, little is known about older adults’ experiences with a self-monitoring–based intervention aimed at the reduction of sedentary behavior.
Objective: The aim of this study is to evaluate engagement, acceptability, usability, and preliminary efficacy of a self-monitoring–based mHealth intervention developed to reduce older adults’ sedentary behavior.
Methods: A mixed methods study was performed among 28 community-dwelling older adults living in Flanders, Belgium. The 3-week intervention consisted of general sedentary behavior information as well as visual and tactile feedback on participants’ sedentary behavior. Semistructured interviews were conducted to explore engagement with, and acceptability and usability of, the intervention. Sitting time was measured using the thigh-worn activPAL (PAL Technologies) accelerometer before and after the intervention. System usage data of the app were recorded. Quantitative data were analyzed using descriptive statistics and paired-samples t tests; qualitative data were thematically analyzed and presented using pen profiles.
Results: Participants mainly reported positive feelings regarding the intervention, referring to it as motivating, surprising, and interesting. They commonly reported that the intervention changed their thinking (ie, they became more aware of their sedentary behavior) but not their actual behavior. There were mixed opinions on the kind of feedback (ie, tactile vs visual) that they preferred. The intervention was considered easy to use, and the design was described as clear. Some problems were noticed regarding attaching and wearing the self-monitoring device. System usage data showed that the median frequency of consulting the app widely differed among participants, ranging from 0 to 20 times a day. No significant reductions were found in objectively measured sitting time.
Conclusions: Although the intervention was well perceived by the majority of older adults, no reductions in sitting time were found. Possible explanations for the lack of reductions might be the short intervention duration or the fact that only bringing the habitual sedentary behavior into conscious awareness might not be sufficient to achieve behavior change.
Trial Registration: ClinicalTrials.gov NCT04003324; https://tinyurl.com/y2p4g8hx
Background: Mobile electronic platforms provide exciting possibilities for health behavior promotion. For instance, they can promote smoking cessation, moderate alcohol consumption, healthy eating, and physical activity. Young adults in Sweden are proficient in the use of technology, having been exposed to computers, smartphones, and the internet from an early age. However, with the high availability of mobile health (mHealth) interventions of varying quality, it is critical to optimize the usability of mHealth interventions to ensure long-term use of these health promotion interventions.
Objective: This study aims to investigate the usability of an mHealth intervention (LIFE4YOUth) targeting health behaviors among high school students through heuristic evaluation and usability testing.
Methods: A preliminary version of the LIFE4YOUth mHealth intervention, which was aimed at promoting healthy eating, physical activity, smoking cessation, and nonrisky drinking among high school students, was developed in early 2019. We completed a total of 15 heuristic evaluations and 5 usability tests to evaluate the usability of the mHealth intervention prototype to improve its functioning, content, and design.
Results: Heuristic evaluation from a total of 15 experts (10 employees and 5 university students, both women and men, aged 18-25 years) revealed that the major usability problems and the worst ratings, a total of 17 problems termed usability catastrophes, concerned shortcomings in displaying easy-to-understand information to the users or technical errors. The results of the usability testing including 5 high school students (both girls and boys, aged 15-18 years) showed that the design, quality, and quantity of content in the intervention may impact the users’ level of engagement. Poor functionality was considered a major barrier to usability. Of the 5 participants, one rated the LIFE4YOUth intervention as poor, 2 rated as average, and 2 assessed it as good, according to the System Usability Scale.
Conclusions: High school students have high expectations of digital products. If an mHealth intervention does not offer optimal functions, they may cease to use it. Optimizing the usability of mHealth interventions is a critical step in the development process. Heuristic evaluation and usability testing in this study provided valuable knowledge about the prototype from a user’s perspective. The findings may lead to the development of similar interventions targeting the high school population.
Background: Smartphone apps could support patients and caregivers in disease self-management. However, as patients’ experiences and needs might not always align with clinical judgments, the eliciting and engaging of perspectives of all stakeholders in the smartphone app design process is of paramount importance.
Objective: The aims of this study are to better understand the needs of and challenges facing caregivers and health care professionals (HCPs) who care for children with atopic dermatitis (AD) and to explore the desirable features and content of a smartphone app that would support AD self-management.
Methods: This study adopted a qualitative participatory co-design methodology involving 3 focus group discussions: workshop one focused on caregivers; workshop two engaged with HCPs; and in the last workshop, caregivers and digital health experts were asked to design the wireframe prototype. The participants completed a sociodemographic questionnaire, a technology acceptance questionnaire, and a workshop evaluation form.
Results: Twelve caregivers participated in the first workshop, and 10 HCPs participated in the second workshop. Eight caregivers and 4 digital health experts attended the third workshop. Three superordinate themes that reflected caregivers’ and HCPs’ challenges and needs were identified: empowerment by education, confusion over treatment, and emotional impact. Workshop participants also raised a series of suggestions on the features and contents of the AD self-management app, which informed the last co-design workshop, and described their needs and challenges. In the last workshop, the participants developed a wireframe prototype of the app following the identified requirements and recommendations.
Conclusions: The co-design approach was found to be a successful way of engaging with the participants, as it allowed them to express their creativity and helped us to articulate the root of the clinical problems. The co-design workshop was successful in creating and generating new ideas and solutions for smartphone app development.
Background: The development and use of mobile health (mHealth) apps for asthma management have risen dramatically over the past two decades. Asthma apps vary widely in their content and features; however, prior research has rarely examined preferences of users of publicly available apps.
Objective: The goals of this study were to provide a descriptive overview of asthma mobile apps that are publicly available and to assess the usability of asthma apps currently available on the market to identify content and features of apps associated with positive and negative user ratings.
Methods: Reviews were collected on June 23, 2020, and included publicly posted reviews until June 21, 2020. To characterize features associated with high or low app ratings, we first dichotomized the average user rating of the asthma app into 2 categories: a high average rating and a low average rating. Asthma apps with average ratings of 4 and above were categorized as having a high average rating. Asthma apps with average ratings of less than 4 were categorized as having a low average rating. For the sentiment analysis, we modeled both 2-word (bi-gram) and 3-word (tri-gram) phrases which commonly appeared across highly rated and lowly rated apps.
Results: Of the 10 apps that met the inclusion criteria, a total of 373 reviews were examined across all apps. Among apps reviewed, 53.4% (199/373) received high ratings (average ratings of 4 or 5) and 47.2% (176/373) received low ratings (average ratings of 3 or less). The number of ratings across all apps ranged from 188 (AsthmaMD) to 10 (My Asthma App); 30% (3/10) of apps were available on both Android and iOS. From the sentiment analysis, key features of asthma management that were common among highly rated apps included the tracking of peak flow readings (n=48), asthma symptom monitoring (n=11), and action plans (n=10). Key features related to functionality that were common among highly rated apps included ease of use (n=5). Users most commonly reported loss of data (n=14) and crashing of app (n=12) as functionality issues among poorly rated asthma apps.
Conclusions: Our study results demonstrate that asthma app quality, maintenance, and updates vary widely across apps and platforms. These findings may call into question the long-term engagement with asthma apps, a crucial factor for determining their potential to improve asthma self-management and asthma clinical outcomes.
Background: In the palliative care setting, infection control measures implemented due to COVID-19 have become barriers to end-of-life care discussions (eg, discharge planning and withdrawal of life-sustaining treatments) between patients, their families, and multidisciplinary medical teams. Strict restrictions in terms of visiting hours and the number of visitors have made it difficult to arrange in-person family conferences. Phone-based telehealth consultations may be a solution, but the lack of nonverbal cues may diminish the clinician-patient relationship. In this context, video-based, smartphone-enabled family conferences have become important.
Objective: We aimed to establish a smartphone-enabled telehealth model for palliative care family conferences. Our model integrates principles from the concept of shared decision making (SDM) and the value, acknowledge, listen, understand, and elicit (VALUE) approach.
Methods: Family conferences comprised three phases designed according to telehealth implementation guidelines—the previsit, during-visit, and postvisit phases. We incorporated the following SDM elements into the model: “team talk,” “option talk,” and “decision talk.” The model has been implemented at a national cancer treatment center in Taiwan since February 2020.
Results: From February to April 2020, 14 telehealth family conferences in the palliative care unit were analyzed. The patients’ mean age was 73 (SD 10.1) years; 6 out of 14 patients (43%) were female and 12 (86%) were married. The primary caregiver joining the conference virtually comprised mostly of spouses and children (n=10, 71%). The majority of participants were terminally ill patients with cancer (n=13, 93%), with the exception of 1 patient with stroke. Consensus on care goals related to discharge planning and withdrawal of life-sustaining treatments was reached in 93% (n=13) of cases during the family conferences. In total, 5 families rated the family conferences as good or very good (36%), whereas 9 were neutral (64%).
Conclusions: Smartphone-enabled telehealth for palliative care family conferences with SDM and VALUE integration demonstrated high satisfaction for families. In most cases, it was effective in reaching consensus on care decisions. The model may be applied to other countries to promote quality in end-of-life care in the midst of the COVID-19 pandemic.
Background: Daily monitoring of fetal and maternal conditions in complicated pregnancies leads to recurrent outpatient visits or (prolonged) hospitalization. Alternatives for hospital admissions include home-based monitoring with home visits by professionals or telemonitoring with self-measurements performed by pregnant women and uploaded for in-clinic assessment. For both alternatives, cardiotocography and blood pressure measurement can be performed at home. It is unknown to what extent, for which reasons, and for which pregnancy complications these strategies are used.
Objective: This study aims to assess the current practice and attitudes concerning home-based monitoring (with daily home visits by professionals) and telemonitoring (using devices and the internet for daily self-recorded measurements) in high-risk pregnancies requiring maternal and fetal monitoring in the Netherlands.
Methods: This nationwide cross-sectional study involved sending a web-based survey to the obstetrics departments of all 73 hospitals in the Netherlands to be answered by 1 representative dedicated to pregnancy monitoring per hospital. The primary outcome was the provision of home-based monitoring or telemonitoring using cardiotocography between 1995 and 2018. The survey further addressed perspectives regarding the use of home-based monitoring and telemonitoring, including (contra)indications, advantages, and disadvantages for pregnant women and clinicians.
Results: The response rate for the provision of either home-based monitoring or telemonitoring was 100%. In 2018, 38% (28/73) of centers in the Netherlands offered either home-based monitoring or telemonitoring or both to pregnant women with complications. Home-based monitoring was offered in 26% (19/73) of the centers; telemonitoring, in 23% (17/73); and both in 11% (8/73). Telemonitoring was first offered in 2009, increasing from 4% (3/73) of hospitals in 2014 to 23% (17/73) in 2018. Responses were received from 78% (57/73) of the invited hospitals and analyzed. Of all 17 centers using telemonitoring, 59% (10/17) did not investigate perinatal outcomes, safety, and patient satisfaction prior to implementation. Other (6/17, 35%) telemonitoring centers are participating in an ongoing multicenter randomized clinical trial comparing patient safety, satisfaction, and costs of telemonitoring with standard hospital admission. Home-based monitoring and telemonitoring are provided for a wide range of complications, such as fetal growth restriction, pre-eclampsia, and preterm rupture of membranes. The respondents reported advantages of monitoring from home, such as reduced stress and increased rest for patients, and reduction of admission and possible reduction of costs. The stated barriers included lack of insurance reimbursement and possible technical issues.
Conclusions: Home-based monitoring is provided in 26% (19/73) and telemonitoring, in 23% (17/73) of hospitals in the Netherlands to women with pregnancy complications. Altogether, 38% (28/73) of hospitals offer either home-based monitoring or telemonitoring or both as an alternative to hospital admission. Future research is warranted to assess safety and reimbursement issues before more widespread implementation of this practice.
Background: Diabetes is one of the leading causes of death in developing countries. Existing mobile health (mHealth) app design guidelines lack a description of the support of continuous self-monitoring of health status, behavior change to improve and adopt a healthy lifestyle, and communication with health educators and health care professionals in case of any need.
Objective: This paper presents the development of a specialized set of heuristics called heuristic evaluation for mHealth apps (HE4EH) as an all-in-one tool and its applicability by performing a heuristic evaluation of an mHealth app.
Methods: An extensive review of heuristics and checklists was used to develop the HE4EH. The HE4EH was evaluated by domain experts for heuristics, checklist items, severity ratings, and overall satisfaction. The OneTouch app, which helps individuals with diabetes manage their blood glucose levels, was evaluated using HE4EH to identify usability problems that need to be fixed in the app.
Results: The expert evaluation of HE4EH revealed that the heuristics were important, relevant, and clear. The checklist items across the heuristics were clear, relevant, and acceptably grouped. In terms of evaluating the OneTouch app using the HE4EH, the most frequently violated heuristics included Content, Visibility, Match, and Self-monitoring. Most of the usability problems found were minor. The system usability scale score indicated that the OneTouch app is marginally acceptable.
Conclusions: This heuristic evaluation using the OneTouch app shows that the HE4EH can play a vital role for designers, researchers, and practitioners to use HE4EH heuristics and checklist items as a tool to design a new or evaluate and improve an existing mHealth app.
Background: Carbohydrate counting is an important component of diabetes management, but it is challenging, often performed inaccurately, and can be a barrier to optimal diabetes management. iSpy is a novel mobile app that leverages machine learning to allow food identification through images and that was designed to assist youth with type 1 diabetes in counting carbohydrates.
Objective: Our objective was to test the app's usability and potential impact on carbohydrate counting accuracy.
Methods: Iterative usability testing (3 cycles) was conducted involving a total of 16 individuals aged 8.5-17.0 years with type 1 diabetes. Participants were provided a mobile device and asked to complete tasks using iSpy app features while thinking aloud. Errors were noted, acceptability was assessed, and refinement and retesting were performed across cycles. Subsequently, iSpy was evaluated in a pilot randomized controlled trial with 22 iSpy users and 22 usual care controls aged 10-17 years. Primary outcome was change in carbohydrate counting ability over 3 months. Secondary outcomes included levels of engagement and acceptability. Change in HbA1c level was also assessed.
Results: Use of iSpy was associated with improved carbohydrate counting accuracy (total grams per meal, P=.008), reduced frequency of individual counting errors greater than 10 g (P=.047), and lower HbA1c levels (P=.03). Qualitative interviews and acceptability scale scores were positive. No major technical challenges were identified. Moreover, 43% (9/21) of iSpy participants were still engaged, with usage at least once every 2 weeks, at the end of the study.
Conclusions: Our results provide evidence of efficacy and high acceptability of a novel carbohydrate counting app, supporting the advancement of digital health apps for diabetes care among youth with type 1 diabetes. Further testing is needed, but iSpy may be a useful adjunct to traditional diabetes management.
Trial Registration: ClinicalTrials.gov NCT04354142; https://clinicaltrials.gov/ct2/show/NCT04354142
Background: The use of mobile health (mHealth) apps is becoming increasingly widespread. However, little is known about the attitudes, expectations, and basic acceptance of health care professionals toward such treatment options. As physical activity and behavior modification are crucial in osteoarthritis management, app-based therapy could be particularly useful for the self-management of this condition.
Objective: The objective of the study was to determine the expectations and attitudes of medical professionals toward app-based therapy for osteoarthritis of the hip or knee.
Methods: Health care professionals attending a rehabilitation congress and employees of a university hospital were asked to fill out a questionnaire consisting of 16 items. A total of 240 questionnaires were distributed.
Results: A total of 127 participants completed the questionnaire. At 95.3% (121/127), the approval rate for app-based therapy for patients with osteoarthritis of the hip or knee was very high. Regarding possible concerns, aspects related to data protection and privacy were primarily mentioned (41/127, 32.3%). Regarding potential content, educational units, physiotherapeutic exercise modules, and practices based on motivation psychology were all met with broad approval.
Conclusions: The study showed a high acceptance of app-based therapy for osteoarthritis, indicating a huge potential of this form of treatment to be applied, prescribed, and recommended by medical professionals. It was widely accepted that the content should reflect a multimodal therapy approach.
Background: Accurate objective pain assessment is required in the healthcare domain and clinical settings for appropriate pain management. Automated objective pain detection from physiological data in...
Background: Accurate objective pain assessment is required in the healthcare domain and clinical settings for appropriate pain management. Automated objective pain detection from physiological data in patients provides valuable information to hospital staff and caregivers to better manage pain, in particular for those patients who are unable to self-report. Galvanic Skin Response (GSR) is one of the physiologic signals that refers to the changes in sweat gland activity, which can identify the features of emotional states and anxiety induced by varying pain levels. In this study, we used different statistical features extracted from GSR data collected from postoperative patients to detect their pain intensity. To the best of our knowledge, we are the first work building pain models using postoperative adult patients instead of healthy subjects. Objective: The goal of this paper is to present an automatic pain assessment tool using GSR signals to predict different pain intensities in non-communicative postoperative patients. Methods: The study was designed to collect biomedical data from post-operative patients reporting moderate to high pain levels. 25 subjects were recruited with the age range of 23 to 89. First, a Transcutaneous Electrical Nerve Stimulation (TENS) unit was employed to obtain patients' baselines. In the second part, the Empatica E4 wristband was attached to patients while they were performing low intensity activities. Patient self-report based on the NRS was used to record pain intensities used to correlate with the objective measured data. The labels were downsampled from 11 pain levels to 5 different pain intensities including the baseline. Two different machine learning algorithms were used to construct the models. The mean decrease impurity method was used to find the top important features for pain prediction and improve the accuracy. We compared our results with a previously published research study to estimate the true performance of our models. Results: Four different binary classification models were constructed using each machine learning algorithm to classify the baseline and other pain intensities (Baseline (BL) vs. Pain Level (PL) 1, BL vs. PL2, BL vs. PL3, and BL vs. PL4). Our models achieved the higher accuracy for the first three pain models in comparison with BioVid paper approach despite the challenges in analyzing real patient data. For BL vs. PL1, BL vs. PL2, and BL vs. PL4, the highest prediction accuracies were achieved when using a Random Forest classifier (86.0, 70.0, and 61.5, respectively). For BL vs. PL3, we achieved the accuracy of 72.1 using a K-nearest neighbors classifier. Conclusions: We are the first to propose and validate the pain assessment tool to predict different pain levels in real postoperative adult patients using GSR signals. We also exploited feature selection algorithms to find the top important features related to different pain intensities.
Background: Mobile technologies can offer a high potential solution to increase the rigorousness and reliability of data collected within clinical studies. However, the development process of mHealth...
Background: Mobile technologies can offer a high potential solution to increase the rigorousness and reliability of data collected within clinical studies. However, the development process of mHealth apps is often inadequate and not sufficiently participatory, affecting the potential to meet intended purposes. Objective: The aim of this study was to design and validate a mHealth app for physical activities and electronic patient-reported outcomes (ePRO) collection in the POWER observational study currently enrolling patients with haemophilia A. Methods: We adopted a user-design process grounded in design science engaging several stakeholders in the development and usability testing of this mobile application, measured through the mHealth app usability questionnaire (MAUQ). During an initial need-assessment focus group we elicited the specific design requirements of the end-users. We then conducted 2 Exploratory Focus Groups to seek additional inputs for improvement and 2 Confirmatory Focus Groups to validate the proposed artifact and test its usability in the field. Results: Findings from thematic analysis of the need-assessment FG revealed a demand for sense making, simplification of app functionalities, maximized integration, and minimized feeling of external control. Participants involved in the later stages of the design refinement contributed to improve the design further by refining the app layout and adding aspects such as a chatbot function and a visual feedback on the number of hours the wearable device has been worn, to make sure the minimum is reached and observed data are actually registered. The end-users rated the app highly during the quantitative assessment, with an average MAUQ score of 5.32 (range 4.44-6.23) and 6.20 (5.72-6.88) out of seven in the two iterative usability testing cycles. Conclusions: The results of the usability test indicated high and growing satisfaction with the app. The adoption of a thorough user-centered design process can maximize the likelihood of sustained retention of the POWER mHealth app and make it fit for data collection of relevant outcomes in the observational study. Findings from our work support the use of different types of focus groups in the design process of a mHealth app. Continuous use of this tool and the actual level of engagement will be properly evaluated during the on-going study.
