mHealth app using machine learning to increase physical activity in diabetes and depression: clinical trial protocol for the DIAMANTE Study

How to design equitable digital health tools: A narrative review of design tactics, case studies, and opportunities

With a renewed focus on health equity in the United States driven by national crises and legislation to improve digital healthcare innovation, there is a need for the designers of digital health tools to take deliberate steps to design for equity in their work. A concrete toolkit of methods to design for health equity is needed to support digital health practitioners in this aim. This narrative review summarizes several health equity frameworks to help digital health practitioners conceptualize the equity dimensions of importance for their work, and then provides design approaches that accommodate an equity focus. Specifically, the Double Diamond Model, the IDEAS framework and toolkit, and community collaboration techniques such as participatory design are explored as mechanisms for practitioners to solicit input from members of underserved groups and better design digital health tools that serve their needs. Each of these design methods requires a deliberate effort by practitioners to infuse health equity into the approach. A series of case studies that use different methods to build in equity considerations are offered to provide examples of how this can be accomplished and demonstrate the range of applications available depending on resources, budget, product maturity, and other factors. We conclude with a call for shared rigor around designing digital health tools that deliver equitable outcomes for members of underserved populations.

Transforming the cardiometabolic disease landscape: Multimodal AI-powered approaches in prevention and management

The rise of artificial intelligence (AI) has revolutionized various scientific fields, particularly in medicine, where it has enabled the modeling of complex relationships from massive datasets. Initially, AI algorithms focused on improved interpretation of diagnostic studies such as chest X-rays and electrocardiograms in addition to predicting patient outcomes and future disease onset. However, AI has evolved with the introduction of transformer models, allowing analysis of the diverse, multimodal data sources existing in medicine today. Multimodal AI holds great promise in more accurate disease risk assessment and stratification as well as optimizing the key driving factors in cardiometabolic disease: blood pressure, sleep, stress, glucose control, weight, nutrition, and physical activity. In this article we outline the current state of medical AI in cardiometabolic disease, highlighting the potential of multimodal AI to augment personalized prevention and treatment strategies in cardiometabolic disease.

Participatory development of an mHealth intervention delivered in general practice to increase physical activity and reduce sedentary behaviour of patients with prediabetes and type 2 diabetes (ENERGISED)

BACKGROUND

The escalating global prevalence of type 2 diabetes and prediabetes presents a major public health challenge. Physical activity plays a critical role in managing (pre)diabetes; however, adherence to physical activity recommendations remains low. The ENERGISED trial was designed to address these challenges by integrating mHealth tools into the routine practice of general practitioners, aiming for a significant, scalable impact in (pre)diabetes patient care through increased physical activity and reduced sedentary behaviour.

METHODS

The mHealth intervention for the ENERGISED trial was developed according to the mHealth development and evaluation framework, which includes the active participation of (pre)diabetes patients. This iterative process encompasses four sequential phases: (a) conceptualisation to identify key aspects of the intervention; (b) formative research including two focus groups with (pre)diabetes patients (n = 14) to tailor the intervention to the needs and preferences of the target population; (c) pre-testing using think-aloud patient interviews (n = 7) to optimise the intervention components; and (d) piloting (n = 10) to refine the intervention to its final form.

RESULTS

The final intervention comprises six types of text messages, each embodying different behaviour change techniques. Some of the messages, such as those providing interim reviews of the patients' weekly step goal or feedback on their weekly performance, are delivered at fixed times of the week. Others are triggered just in time by specific physical behaviour events as detected by the Fitbit activity tracker: for example, prompts to increase walking pace are triggered after 5 min of continuous walking; and prompts to interrupt sitting following 30 min of uninterrupted sitting. For patients without a smartphone or reliable internet connection, the intervention is adapted to ensure inclusivity. Patients receive on average three to six messages per week for 12 months. During the first six months, the text messaging is supplemented with monthly phone counselling to enable personalisation of the intervention, assistance with technical issues, and enhancement of adherence.

CONCLUSIONS

The participatory development of the ENERGISED mHealth intervention, incorporating just-in-time prompts, has the potential to significantly enhance the capacity of general practitioners for personalised behavioural counselling on physical activity in (pre)diabetes patients, with implications for broader applications in primary care.

Lessons and Untapped Potential of Smartphone-Based Physical Activity Interventions for Mental Health: Narrative Review

BACKGROUND

Physical activity has well-known and broad health benefits, including antidepressive and anxiolytic effects. However, only approximately half of Americans meet even the minimum exercise recommendations. Individuals with anxiety, depression, or related conditions are even less likely to do so. With the advent of mobile sensors and phones, experts have quickly noted the utility of technology for the enhanced measurement of and intervention for physical activity. In addition to being more accessible than in-person approaches, technology-driven interventions may uniquely engage key mechanisms of behavior change such as self-awareness.

OBJECTIVE

This study aims to provide a narrative overview and specific recommendations for future research on smartphone-based physical activity interventions for psychological disorders or concerns.

METHODS

In this paper, we summarized early efforts to adapt and test smartphone-based or smartphone-supported physical activity interventions for mental health. The included articles described or reported smartphone-delivered or smartphone-supported interventions intended to increase physical activity or reduce sedentary behavior and included an emotional disorder, concern, or symptom as an outcome measure. We attempted to extract details regarding the intervention designs, trial designs, study populations, outcome measures, and inclusion of adaptations specifically for mental health. In taking a narrative lens, we drew attention to the type of work that has been done and used these exemplars to discuss key directions to build on.

RESULTS

To date, most studies have examined mental health outcomes as secondary or exploratory variables largely in the context of managing medical concerns (eg, cancer and diabetes). Few trials have recruited psychiatric populations or explicitly aimed to target psychiatric concerns. Consequently, although there are encouraging signals that smartphone-based physical activity interventions could be feasible, acceptable, and efficacious for individuals with mental illnesses, this remains an underexplored area.

CONCLUSIONS

Promising avenues for tailoring validated smartphone-based interventions include adding psychoeducation (eg, the relationship between depression, physical activity, and inactivity), offering psychosocial treatment in parallel (eg, cognitive restructuring), and adding personalized coaching. To conclude, we offer specific recommendations for future research, treatment development, and implementation in this area, which remains open and promising for flexible, highly scalable support.

Empowering patients with comorbid diabetes and hypertension through a multi-component intervention of mobile app, health coaching and shared decision-making: Protocol for an effectiveness-implementation of randomised controlled trial

INTRODUCTION

Diabetes and hypertension are prevalent and costly to the health system. We have developed a mobile app (EMPOWER app) which enables remote monitoring and education through personalised nudges. We aim to study the effectiveness of a multi-component intervention comprising the EMPOWER mobile app with health coaching and shared decision-making for diabetes and hypertension.

METHODS

We will conduct a two-arm, open-label, pragmatic randomised controlled trial (RCT). Participants with comorbid diabetes and hypertension enrolled from public primary care clinics will be randomised to either intervention or control in a 1:1 ratio. The intervention group participants will have access to health coaching with shared decision-making interventions in addition to the EMPOWER app and their usual primary care. The control group participants will continue to receive usual primary care and will neither receive the EMPOWER app nor health coaching and shared decision-making interventions. Our primary outcome is change in HbA1c level over 9 months. Secondary outcomes include change in systolic blood pressure, quality of life, patient activation, medication adherence, physical activity level, diet, and healthcare cost (direct and indirect) over 9 months.

DISCUSSION

Our trial will provide key insights into clinical- and cost-effectiveness of a multi-component intervention comprising EMPOWER mobile app, health coaching and shared decision-making in diabetes and hypertension management. This trial will also offer evidence on cost-effective and sustainable methods for promoting behavioural changes among patients with comorbid diabetes and hypertension.

TRIAL REGISTRATION

This study was registered on clintrials.gov on August 3, 2022, with the trial registration number: NCT05486390.

Automatic recognition of depression based on audio and video: A review

Depression is a common mental health disorder. With current depression detection methods, specialized physicians often engage in conversations and physiological examinations based on standardized scales as auxiliary measures for depression assessment. Non-biological markers-typically classified as verbal or non-verbal and deemed crucial evaluation criteria for depression-have not been effectively utilized. Specialized physicians usually require extensive training and experience to capture changes in these features. Advancements in deep learning technology have provided technical support for capturing non-biological markers. Several researchers have proposed automatic depression estimation (ADE) systems based on sounds and videos to assist physicians in capturing these features and conducting depression screening. This article summarizes commonly used public datasets and recent research on audio- and video-based ADE based on three perspectives: Datasets, deficiencies in existing research, and future development directions.

The impact of using reinforcement learning to personalize communication on medication adherence: findings from the REINFORCE trial

Text messaging can promote healthy behaviors, like adherence to medication, yet its effectiveness remains modest, in part because message content is rarely personalized. Reinforcement learning has been used in consumer technology to personalize content but with limited application in healthcare. We tested a reinforcement learning program that identifies individual responsiveness ("adherence") to text message content and personalizes messaging accordingly. We randomized 60 individuals with diabetes and glycated hemoglobin A1c [HbA1c] ≥ 7.5% to reinforcement learning intervention or control (no messages). Both arms received electronic pill bottles to measure adherence. The intervention improved absolute adjusted adherence by 13.6% (95%CI: 1.7%-27.1%) versus control and was more effective in patients with HbA1c 7.5- < 9.0% (36.6%, 95%CI: 25.1%-48.2%, interaction p < 0.001). We also explored whether individual patient characteristics were associated with differential response to tested behavioral factors and unique clusters of responsiveness. Reinforcement learning may be a promising approach to improve adherence and personalize communication at scale.

mHealth Intervention to Promote Physical Activity Among Employees Using a Deep Learning Model for Passive Monitoring of Depression and Anxiety: Single-Arm Feasibility Trial

BACKGROUND

Physical activity effectively prevents depression and anxiety. Although mobile health (mHealth) technologies offer promising results in promoting physical activity and improving mental health, conflicting evidence exists on their effectiveness, and employees face barriers to using mHealth services. To address these problems, we recently developed a smartphone app named ASHARE to prevent depression and anxiety in the working population; it uses a deep learning model for passive monitoring of depression and anxiety from information about physical activity.

OBJECTIVE

This study aimed to preliminarily investigate (1) the effectiveness of the developed app in improving physical activity and reducing depression and anxiety and (2) the app's implementation outcomes (ie, its acceptability, appropriateness, feasibility, satisfaction, and potential harm).

METHODS

We conducted a single-arm interventional study. From March to April 2023, employees aged ≥18 years who were not absent were recruited. The participants were asked to install and use the app for 1 month. The ideal usage of the app was for the participants to take about 5 minutes every day to open the app, check the physical activity patterns and results of an estimated score of psychological distress, and increase their physical activity. Self-reported physical activity (using the Global Physical Activity Questionnaire, version 2) and psychological distress (using the 6-item Kessler Psychological Distress Scale) were measured at baseline and after 1 month. The duration of physical activity was also recorded digitally. Paired t tests (two-tailed) and chi-square tests were performed to evaluate changes in these variables. Implementation Outcome Scales for Digital Mental Health were also measured for acceptability, appropriateness, feasibility, satisfaction, and harm. These average scores were assessed by comparing them with those reported in previous studies.

RESULTS

This study included 24 employees. On average, the app was used for 12.54 days (44.8% of this study's period). After using the app, no significant change was observed in physical activity (-12.59 metabolic equivalent hours per week, P=.31) or psychological distress (-0.43 metabolic equivalent hours per week, P=.93). However, the number of participants with severe psychological distress decreased significantly (P=.01). The digitally recorded duration of physical activity increased during the intervention period (+0.60 minutes per day, P=.08). The scores for acceptability, appropriateness, and satisfaction were lower than those in previous mHealth studies, whereas those for feasibility and harm were better.

CONCLUSIONS

The ASHARE app was insufficient in promoting physical activity or improving psychological distress. At this stage, the app has many issues that are to be addressed in terms of both implementation and effectiveness. The main reason for this low effectiveness might be the poor evaluation of the implementation outcomes by app users. Improving acceptability, appropriateness, and satisfaction are identified as key issues to be addressed in future implementation.

TRIAL REGISTRATION

University Hospital Medical Information Network Clinical Trials Registry UMIN000050430; https://tinyurl.com/mrx5ntcmrecptno=R000057438.

Cultural Responsivity in Technology-Enabled Services: Integrating Culture Into Technology and Service Components

Technology-enabled services (TESs) are clinical interventions that combine technological and human components to provide health services. TESs for mental health are efficacious in the treatment of anxiety and depression and are currently being offered as frontline treatments around the world. It is hoped that these interventions will be able to reach diverse populations across a range of identities and ultimately decrease disparities in mental health treatment. However, this hope is largely unrealized. TESs include both technology and human service components, and we argue that cultural responsivity must be considered in each of these components to help address existing treatment disparities. To date, there is limited guidance on how to consider cultural responsivity within these interventions, including specific targets for the development, tailoring, or design of the technologies and services within TESs. In response, we propose a framework that provides specific recommendations for targets based on existing models, both at the technological component level (informed by the Behavioral Intervention Technology Model) and the human support level (informed by the Efficiency Model of Support). We hope that integrating culturally responsive considerations into these existing models will facilitate increased attention to cultural responsivity within TESs to ensure they are ethical and responsive for everyone.

Testing the Effects of App-Based Motivational Messages on Physical Activity and Resting Heart Rate Through Smartphone App Compliance in Patients With Vulnerable Coronary Artery Plaques: Protocol for a Microrandomized Trial

BACKGROUND

Achieving the weekly physical activity recommendations of at least 150-300 minutes of moderate-intensity or 75-150 minutes of vigorous-intensity aerobic exercise is important for reducing cardiometabolic risk, but evidence shows that most people struggle to meet these goals, particularly in the mid to long term.

OBJECTIVE

The Messages Improving Resting Heart Health (MIRTH) study aims to determine if (1) sending daily motivational messages through a research app is effective in improving motivation and in promoting adherence to physical activity recommendations in men and women with coronary heart disease randomized to a 12-month intensive lifestyle intervention, and (2) the time of the day when the message is delivered impacts compliance with exercise training.

METHODS

We will conduct a single-center, microrandomized trial. Participants will be randomized daily to either receive or not receive motivational messages over two 90-day periods at the beginning (phase 1: months 4-6) and at the end (phase 2: months 10-12) of the Lifestyle Vulnerable Plaque Study. Wrist-worn devices (Fitbit Inspire 2) and Bluetooth pairing with smartphones will be used to passively collect data for proximal (ie, physical activity duration, steps walked, and heart rate within 180 minutes of receiving messages) and distal (ie, change values for resting heart rate and total steps walked within and across both phases 1 and 2 of the trial) outcomes. Participants will be recruited from a large academic cardiology office practice (Central Sydney Cardiology) and the Royal Prince Alfred Hospital Departments of Cardiology and Radiology. All clinical investigations will be undertaken at the Charles Perkins Centre Royal Prince Alfred clinic. Individuals aged 18-80 years (n=58) with stable coronary heart disease who have low attenuation plaques based on a coronary computed tomography angiography within the past 3 months and have been randomized to an intensive lifestyle intervention program will be included in MIRTH.

RESULTS

The Lifestyle Vulnerable Plaque Study was funded in 2020 and started enrolling participants in February 2022. Recruitment for MIRTH commenced in November 2022. As of September 2023, 2 participants were enrolled in the MIRTH study and provided baseline data.

CONCLUSIONS

This MIRTH microrandomized trial will represent the single most detailed and integrated analysis of the effects of a comprehensive lifestyle intervention delivered through a customized mobile health app on smart devices on time-based motivational messaging for patients with coronary heart disease. This study will also help inform future studies optimizing for just-in-time adaptive interventions.

TRIAL REGISTRATION

Australian New Zealand Clinical Trials Registry ACTRN12622000731796; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=382861.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/46082.

Current evidence for designing self-management support for underserved populations: an integrative review using the example of diabetes

AIMS

With numerous and continuing attempts at adapting diabetes self-management support programmes to better account for underserved populations, its important that the lessons being learned are understood and shared. The work we present here reviews the latest evidence and best practice in designing and embedding culturally and socially sensitive, self-management support programmes.

METHODS

We explored the literature with regard to four key design considerations of diabetes self-management support programmes: Composition - the design and content of written materials and digital tools and interfaces; Structure - the combination of individual and group sessions, their frequency, and the overall duration of programmes; Facilitators - the combination of individuals used to deliver the programme; and Context - the influence and mitigation of a range of individual, socio-cultural, and environmental factors.

RESULTS

We found useful and recent examples of design innovation within a variety of countries and models of health care delivery including Brazil, Mexico, Netherlands, Spain, United Kingdom, and United States of America. Within Composition we confirmed the importance of retaining best practice in creating readily understood written information and intuitive digital interfaces; Structure the need to offer group, individual, and remote learning options in programmes of flexible duration and frequency; Facilitators where the benefits of using culturally concordant peers and community-based providers were described; and finally in Context the need to integrate self-management support programmes within existing health systems, and tailor their various constituent elements according to the language, resources, and beliefs of individuals and their communities.

CONCLUSIONS

A number of design principles across the four design considerations were identified that together offer a promising means of creating the next generation of self-management support programme more readily accessible for underserved communities. Ultimately, we recommend that the precise configuration should be co-produced by all relevant service and patient stakeholders and its delivery embedded in local health systems.

A flexible micro-randomized trial design and sample size considerations

Technological advancements have made it possible to deliver mobile health interventions to individuals. A novel framework that has emerged from such advancements is the just-in-time adaptive intervention, which aims to suggest the right support to the individuals when their needs arise. The micro-randomized trial design has been proposed recently to test the proximal effects of the components of these just-in-time adaptive interventions. However, the extant micro-randomized trial framework only considers components with a fixed number of categories added at the beginning of the study. We propose a more flexible micro-randomized trial design which allows addition of more categories to the components during the study. Note that the number and timing of the categories added during the study need to be fixed initially. The proposed design is motivated by collaboration on the Diabetes and Mental Health Adaptive Notification Tracking and Evaluation study, which learns to deliver effective text messages to encourage physical activity among patients with diabetes and depression. We developed a new test statistic and the corresponding sample size calculator for the flexible micro-randomized trial using an approach similar to the generalized estimating equation for longitudinal data. Simulation studies were conducted to evaluate the sample size calculators and an R shiny application for the calculators was developed.

The Cost Impact of Telehealth Interventions in Pediatric Surgical Specialties: A Systematic Review

BACKGROUND

Telehealth is a rapidly expanding care modality in the United States. Pediatric surgical patients often require complex care which can incur significant expenses, some of which may be alleviated by telehealth. We performed a systematic review comparing telehealth and in-person visits, and telehealth's impacts on the cost of healthcare across pediatric surgical specialties.

METHODS

A systematic review was performed using the following databases: PubMed (MEDLINE), Scopus (Elsevier), and CINAHL (EBSCOHost), searched from inception to July 10th, 2022. Studies were included per the following criteria: (1) investigated a telehealth intervention for pediatric surgical care and (2) provided some metric of telehealth cost compared to an in-person visit. Non-English or studies conducted outside of the U.S. were excluded.

RESULTS

Fourteen manuscripts met inclusion criteria and presented data on 7992 visits, including patients with a weighted average age of 7.5 ± 3.5 years. Most (11/14) studies used telehealth in a synchronous, or "real-time" context. Of the studies which calculated dollar cost savings for telehealth visits compared to in-person appointments we found a substantial range of savings per visit, from $48.50 to $344.64. Cost savings were frequently realized in terms of reduced travel expenditures, lower opportunity costs (e.g. lost wages), and decreased hospital labor requirements.

CONCLUSIONS

This review suggests that telehealth provides cost incentives to pediatric surgical care in many scenarios, including post-operative visits and some routine clinic visits. Future work should focus on standardizing the metrics by which cost impacts are analyzed and detailing which visits are most appropriately facilitated by telehealth.

LEVEL OF EVIDENCE

V.

DiaFocus: A Personal Health Technology for Adaptive Assessment in Long-Term Management of Type 2 Diabetes

Type 2 diabetes (T2D) is a large disease burden worldwide and represents an increasing and complex challenge for all societies. For the individual, T2D is a complex, multi-dimensional, and long-term challenge to manage, and it is challenging to establish and maintain good communication between the patient and healthcare professionals. This article presents DiaFocus, which is a mobile health sensing application for long-term ambulatory management of T2D. DiaFocus supports an adaptive collection of physiological, behavioral, and contextual data in combination with ecological assessments of psycho-social factors. This data is used for improving patient-clinician communication during consultations. DiaFocus is built using a generic data collection framework for mobile and wearable sensing and is highly extensible and customizable. We deployed DiaFocus in a 6-week feasibility study involving 12 patients with T2D. The patients found the DiaFocus approach and system useful and usable for diabetes management. Most patients would use such a system, if available as part of their treatment. Analysis of the collected data shows that mobile sensing is feasible for longitudinal ambulatory assessment of T2D, and helped identify the most appropriate target users being early diagnosed and technically literate T2D patients.

Effectiveness and implementation of a text messaging intervention to reduce depression and anxiety symptoms among Latinx and Non-Latinx white users during the COVID-19 pandemic

Text messaging interventions are increasingly used to help people manage depression and anxiety. However, little is known about the effectiveness and implementation of these interventions among U.S. Latinxs, who often face barriers to using mental health tools. The StayWell at Home (StayWell) intervention, a 60-day text messaging program based on cognitive behavioral therapy (CBT), was developed to help adults cope with depressive and anxiety symptoms during the COVID-19 pandemic. StayWell users (n = 398) received daily mood inquiries and automated skills-based text messages delivering CBT-informed coping strategies from an investigator-generated message bank. We conduct a Hybrid Type 1 mixed-methods study to compare the effectiveness and implementation of StayWell for Latinx and Non-Latinx White (NLW) adults using the Reach, Effectiveness, Adoption, Implementation, and Maintenance (RE-AIM) framework. Effectiveness was measured using the PHQ-8 depression and GAD-7 anxiety scales, assessed before starting and after completing StayWell. Guided by RE-AIM, we conducted a thematic text analysis of responses to an open-ended question about user experiences to help contextualize quantitative findings. Approximately 65.8% (n = 262) of StayWell users completed pre-and-post surveys. On average, depressive (-1.48, p = 0.001) and anxiety (-1.38, p = 0.001) symptoms decreased from pre-to-post StayWell. Compared to NLW users (n = 192), Latinx users (n = 70) reported an additional -1.45 point (p < 0.05) decline in depressive symptoms, adjusting for demographics. Although Latinxs reported StayWell as relatively less useable (76.8 vs. 83.9, p = 0.001) than NLWs, they were more interested in continuing the program (7.5 vs. 6.2 out of 10, p = 0.001) and recommending it to a family member/friend (7.8 vs. 7.0 out of 10, p = 0.01). Based on the thematic analysis, both Latinx and NLW users enjoyed responding to mood inquiries and sought bi-directional, personalized text messages and texts with links to more information to resources. Only NLW users stated that StayWell provided no new information than they already knew from therapy or other sources. In contrast, Latinx users suggested that engagement with a behavioral provider through text or support groups would be beneficial, highlighting this group's unmet need for behavioral health care. mHealth interventions like StayWell are well-positioned to address population-level disparities by serving those with the greatest unmet needs if they are culturally adapted and actively disseminated to marginalized groups. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT04473599.

mHealth intervention delivered in general practice to increase physical activity and reduce sedentary behaviour of patients with prediabetes and type 2 diabetes (ENERGISED): rationale and study protocol for a pragmatic randomised controlled trial

BACKGROUND

The growing number of patients with type 2 diabetes and prediabetes is a major public health concern. Physical activity is a cornerstone of diabetes management and may prevent its onset in prediabetes patients. Despite this, many patients with (pre)diabetes remain physically inactive. Primary care physicians are well-situated to deliver interventions to increase their patients' physical activity levels. However, effective and sustainable physical activity interventions for (pre)diabetes patients that can be translated into routine primary care are lacking.

METHODS

We describe the rationale and protocol for a 12-month pragmatic, multicentre, randomised, controlled trial assessing the effectiveness of an mHealth intervention delivered in general practice to increase physical activity and reduce sedentary behaviour of patients with prediabetes and type 2 diabetes (ENERGISED). Twenty-one general practices will recruit 340 patients with (pre)diabetes during routine health check-ups. Patients allocated to the active control arm will receive a Fitbit activity tracker to self-monitor their daily steps and try to achieve the recommended step goal. Patients allocated to the intervention arm will additionally receive the mHealth intervention, including the delivery of several text messages per week, with some of them delivered just in time, based on data continuously collected by the Fitbit tracker. The trial consists of two phases, each lasting six months: the lead-in phase, when the mHealth intervention will be supported with human phone counselling, and the maintenance phase, when the intervention will be fully automated. The primary outcome, average ambulatory activity (steps/day) measured by a wrist-worn accelerometer, will be assessed at the end of the maintenance phase at 12 months.

DISCUSSION

The trial has several strengths, such as the choice of active control to isolate the net effect of the intervention beyond simple self-monitoring with an activity tracker, broad eligibility criteria allowing for the inclusion of patients without a smartphone, procedures to minimise selection bias, and involvement of a relatively large number of general practices. These design choices contribute to the trial's pragmatic character and ensure that the intervention, if effective, can be translated into routine primary care practice, allowing important public health benefits.

TRIAL REGISTRATION

ClinicalTrials.gov (NCT05351359, 28/04/2022).

Mining Sensor Data to Assess Changes in Physical Activity Behaviors in Health Interventions: Systematic Review

BACKGROUND

Sensors are increasingly used in health interventions to unobtrusively and continuously capture participants' physical activity in free-living conditions. The rich granularity of sensor data offers great potential for analyzing patterns and changes in physical activity behaviors. The use of specialized machine learning and data mining techniques to detect, extract, and analyze these patterns has increased, helping to better understand how participants' physical activity evolves.

OBJECTIVE

The aim of this systematic review was to identify and present the various data mining techniques employed to analyze changes in physical activity behaviors from sensors-derived data in health education and health promotion intervention studies. We addressed two main research questions: (1) What are the current techniques used for mining physical activity sensor data to detect behavior changes in health education or health promotion contexts? (2) What are the challenges and opportunities in mining physical activity sensor data for detecting physical activity behavior changes?

METHODS

The systematic review was performed in May 2021 using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. We queried the Association for Computing Machinery (ACM), IEEE Xplore, ProQuest, Scopus, Web of Science, Education Resources Information Center (ERIC), and Springer literature databases for peer-reviewed references related to wearable machine learning to detect physical activity changes in health education. A total of 4388 references were initially retrieved from the databases. After removing duplicates and screening titles and abstracts, 285 references were subjected to full-text review, resulting in 19 articles included for analysis.

RESULTS

All studies used accelerometers, sometimes in combination with another sensor (37%). Data were collected over a period ranging from 4 days to 1 year (median 10 weeks) from a cohort size ranging between 10 and 11615 (median 74). Data preprocessing was mainly carried out using proprietary software, generally resulting in step counts and time spent in physical activity aggregated predominantly at the daily or minute level. The main features used as input for the data mining models were descriptive statistics of the preprocessed data. The most common data mining methods were classifiers, clusters, and decision-making algorithms, and these focused on personalization (58%) and analysis of physical activity behaviors (42%).

CONCLUSIONS

Mining sensor data offers great opportunities to analyze physical activity behavior changes, build models to better detect and interpret behavior changes, and allow for personalized feedback and support for participants, especially where larger sample sizes and longer recording times are available. Exploring different data aggregation levels can help detect subtle and sustained behavior changes. However, the literature suggests that there is still work remaining to improve the transparency, explicitness, and standardization of the data preprocessing and mining processes to establish best practices and make the detection methods easier to understand, scrutinize, and reproduce.

Ratings and experiences in using a mobile application to increase physical activity among university students: implications for future design

University students have low levels of physical activity and are at risk of mental health disorders. Mobile apps to encourage physical activity can help students, who are frequent smartphone-users, to improve their physical and mental health. Here we report students' qualitative feedback on a physical activity smartphone app with motivational text messaging. We provide recommendations for the design of future apps. 103 students used the app for 6 weeks in the context of a clinical trial (NCT04440553) and answered open-ended questions before the start of the study and at follow-up. A subsample (n = 39) provided additional feedback via text message, and a phone interview (n = 8). Questions focused on the perceived encouragement and support by the app, text messaging content, and recommendations for future applications. We analyzed all transcripts for emerging themes using qualitative coding in Dedoose. The majority of participants were female (69.9%), Asian or Pacific Islander (53.4%), with a mean age of 20.2 years, and 63% had elevated depressive symptoms. 26% felt encouraged or neutral toward the app motivating them to be more physically active. Participants liked messages on physical activity benefits on (mental) health, encouraging them to complete their goal, and feedback on their activity. Participants disliked messages that did not match their motivations for physical activity and their daily context (e.g., time, weekday, stress). Physical activity apps for students should be adapted to their motivations, changing daily context, and mental health issues. Feedback from this sample suggests a key to effectiveness is finding effective ways to personalize digital interventions.

Microrandomized Trials: Developing Just-in-Time Adaptive Interventions for Better Public Health

Just-in-time adaptive interventions (JITAIs) represent an intervention design that adapts the provision and type of support over time to an individual's changing status and contexts, intending to deliver the right support on the right occasion. As a novel strategy for delivering mobile health interventions, JITAIs have the potential to improve access to quality care in underserved communities and, thus, alleviate health disparities, a significant public health concern. Valid experimental designs and analysis methods are required to inform the development of JITAIs. Here, we briefly review the cutting-edge design of microrandomized trials (MRTs), covering both the classical MRT design and its outcome-adaptive counterpart. Associated statistical challenges related to the design and analysis of MRTs are also discussed. Two case studies are provided to illustrate the aforementioned concepts and designs throughout the article. We hope our work leads to better design and application of JITAIs, advancing public health research and practice. (Am J Public Health. 2023;113(1):60-69. https://doi.org/10.2105/AJPH.2022.307150).

Unsupervised Early Detection of Physical Activity Behaviour Changes from Wearable Accelerometer Data

Wearable accelerometers record physical activity with high resolution, potentially capturing the rich details of behaviour changes and habits. Detecting these changes as they emerge is valuable information for any strategy that promotes physical activity and teaches healthy behaviours or habits. Indeed, this offers the opportunity to provide timely feedback and to tailor programmes to each participant's needs, thus helping to promote the adherence to and the effectiveness of the intervention. This article presents and illustrates U-BEHAVED, an unsupervised algorithm that periodically scans step data streamed from activity trackers to detect physical activity behaviour changes to assess whether they may become habitual patterns. Using rolling time windows, current behaviours are compared with recent previous ones, identifying any significant change. If sustained over time, these new behaviours are classified as potentially new habits. We validated this detection algorithm using a physical activity tracker step dataset (N = 12,798) from 79 users. The algorithm detected 80% of behaviour changes of at least 400 steps within the same hour in users with low variability in physical activity, and of 1600 steps in those with high variability. Based on a threshold cadence of approximately 100 steps per minute for standard walking pace, this number of steps would suggest approximately 4 and 16 min of physical activity at moderate-to-vigorous intensity, respectively. The detection rate for new habits was 80% with a minimum threshold of 500 or 1600 steps within the same hour in users with low or high variability, respectively.

The Barriers and Facilitators of eHealth-Based Lifestyle Intervention Programs for People With a Low Socioeconomic Status: Scoping Review

Background

Promoting health behaviors and preventing chronic diseases through a healthy lifestyle among those with a low socioeconomic status (SES) remain major challenges. eHealth interventions are a promising approach to change unhealthy behaviors in this target group.

Objective

This review aims to identify key components, barriers, and facilitators in the development, reach, use, evaluation, and implementation of eHealth lifestyle interventions for people with a low SES. This review provides an overview for researchers and eHealth developers, and can assist in the development of eHealth interventions for people with a low SES.

Methods

We performed a scoping review based on Arksey and O’Malley’s framework. A systematic search was conducted on PubMed, MEDLINE (Ovid), Embase, Web of Science, and the Cochrane Library, using terms related to a combination of the following key constructs: eHealth, lifestyle, low SES, development, reach, use, evaluation, and implementation. There were no restrictions on the date of publication for articles retrieved upon searching the databases.

Results

The search identified 1323 studies, of which 42 met our inclusion criteria. An update of the search led to the inclusion of 17 additional studies. eHealth lifestyle interventions for people with a low SES were often delivered via internet-based methods (eg, websites, email, Facebook, and smartphone apps) and offline methods, such as texting. A minority of the interventions combined eHealth lifestyle interventions with face-to-face or telephone coaching, or wearables (blended care). We identified the use of different behavioral components (eg, social support) and technological components (eg, multimedia) in eHealth lifestyle interventions. Facilitators in the development included iterative design, working with different disciplines, and resonating intervention content with users. Facilitators for intervention reach were use of a personal approach and social network, reminders, and self-monitoring. Nevertheless, barriers, such as technological challenges for developers and limited financial resources, may hinder intervention development. Furthermore, passive recruitment was a barrier to intervention reach. Technical difficulties and the use of self-monitoring devices were common barriers for users of eHealth interventions. Only limited data on barriers and facilitators for intervention implementation and evaluation were available.

Conclusions

While we found large variations among studies regarding key intervention components, and barriers and facilitators, certain factors may be beneficial in building and using eHealth interventions and reaching people with a low SES. Barriers and facilitators offer promising elements that eHealth developers can use as a toolbox to connect eHealth with low SES individuals. Our findings suggest that one-size-fits-all eHealth interventions may be less suitable for people with a low SES. Future research should investigate how to customize eHealth lifestyle interventions to meet the needs of different low SES groups, and should identify the components that enhance their reach, use, and effectiveness.

Prediction of Tinnitus Perception Based on Daily Life MHealth Data Using Country Origin and Season

Tinnitus is an auditory phantom perception without external sound stimuli. This chronic perception can severely affect quality of life. Because tinnitus symptoms are highly heterogeneous, multimodal data analyses are increasingly used to gain new insights. MHealth data sources, with their particular focus on country- and season-specific differences, can provide a promising avenue for new insights. Therefore, we examined data from the TrackYourTinnitus (TYT) mHealth platform to create symptom profiles of TYT users. We used gradient boosting engines to classify momentary tinnitus and regress tinnitus loudness, using country of origin and season as features. At the daily assessment level, tinnitus loudness can be regressed with a mean absolute error rate of 7.9% points. In turn, momentary tinnitus can be classified with an F1 score of 93.79%. Both results indicate differences in the tinnitus of TYT users with respect to season and country of origin. The significance of the features was evaluated using statistical and explainable machine learning methods. It was further shown that tinnitus varies with temperature in certain countries. The results presented show that season and country of origin appear to be valuable features when combined with longitudinal mHealth data at the level of daily assessment.

Digital Health Technologies for Long-term Self-management of Osteoporosis: Systematic Review and Meta-analysis

Background

Osteoporosis is the fourth most common chronic disease worldwide. The adoption of preventative measures and effective self-management interventions can help improve bone health. Mobile health (mHealth) technologies can play a key role in the care and self-management of patients with osteoporosis.

Objective

This study presents a systematic review and meta-analysis of the currently available mHealth apps targeting osteoporosis self-management, aiming to determine the current status, gaps, and challenges that future research could address, as well as propose appropriate recommendations.

Methods

A systematic review of all English articles was conducted, in addition to a survey of all apps available in iOS and Android app stores as of May 2021. A comprehensive literature search (2010 to May 2021) of PubMed, Scopus, EBSCO, Web of Science, and IEEE Xplore was conducted. Articles were included if they described apps dedicated to or useful for osteoporosis (targeting self-management, nutrition, physical activity, and risk assessment) delivered on smartphone devices for adults aged ≥18 years. Of the 32 articles, a random effects meta-analysis was performed on 13 (41%) studies of randomized controlled trials, whereas the 19 (59%) remaining studies were only included in the narrative synthesis as they did not provide enough data.

Results

In total, 3906 unique articles were identified. Of these 3906 articles, 32 (0.81%) articles met the inclusion criteria and were reviewed in depth. The 32 studies comprised 14,235 participants, of whom, on average, 69.5% (n=9893) were female, with a mean age of 49.8 (SD 17.8) years. The app search identified 23 relevant apps for osteoporosis self-management. The meta-analysis revealed that mHealth-supported interventions resulted in a significant reduction in pain (Hedges g −1.09, 95% CI −1.68 to −0.45) and disability (Hedges g −0.77, 95% CI −1.59 to 0.05). The posttreatment effect of the digital intervention was significant for physical function (Hedges g 2.54, 95% CI −4.08 to 4.08) but nonsignificant for well-being (Hedges g 0.17, 95% CI −1.84 to 2.17), physical activity (Hedges g 0.09, 95% CI −0.59 to 0.50), anxiety (Hedges g −0.29, 95% CI −6.11 to 5.53), fatigue (Hedges g −0.34, 95% CI −5.84 to 5.16), calcium (Hedges g −0.05, 95% CI −0.59 to 0.50), vitamin D intake (Hedges g 0.10, 95% CI −4.05 to 4.26), and trabecular score (Hedges g 0.06, 95% CI −1.00 to 1.12).

Conclusions

Osteoporosis apps have the potential to support and improve the management of the disease and its symptoms; they also appear to be valuable tools for patients and health professionals. However, most of the apps that are currently available lack clinically validated evidence of their efficacy and focus on a limited number of symptoms. A more holistic and personalized approach within a cocreation design ecosystem is needed.

Trial Registration

PROSPERO 2021 CRD42021269399; https://tinyurl.com/2sw454a9

Involving Crowdworkers with Lived Experience in Content-Development for Push-Based Digital Mental Health Tools: Lessons Learned from Crowdsourcing Mental Health Messages

Digital tools can support individuals managing mental health concerns, but delivering sufficiently engaging content is challenging. This paper seeks to clarify how individuals with mental health concerns can contribute content to improve push-based mental health messaging tools. We recruited crowdworkers with mental health symptoms to evaluate and revise expert-composed content for an automated messaging tool, and to generate new topics and messages. A second wave of crowdworkers evaluated expert and crowdsourced content. Crowdworkers generated topics for messages that had not been prioritized by experts, including self-care, positive thinking, inspiration, relaxation, and reassurance. Peer evaluators rated messages written by experts and peers similarly. Our findings also suggest the importance of personalization, particularly when content adaptation occurs over time as users interact with example messages. These findings demonstrate the potential of crowdsourcing for generating diverse and engaging content for push-based tools, and suggest the need to support users in meaningful content customization.

Design and Preliminary Realization of a Screening and Early Warning Health Management System for Populations at High Risk for Depression

Depression has a high incidence in the world. Based on the concept of preventive treatment of disease of traditional Chinese medicine, timely screening and early warning of depression in populations at high risk for this condition can avoid, to a certain extent, the dysfunctions caused by depression. This work studied a method to collect information on depression, generate a database of depression features, design algorithms for screening populations at high risk for depression and creating an early warning model, develop an early warning short-message service (SMS) platform, and implement a scheme of depression screening and an early warning health management system. The implementation scheme included mobile application (app), cloud form, screening and early warning model, cloud platform, and computer software. Multiple modules jointly realized the screening, early warning, and management of the health functions of individuals at high risk for depression. At the same time, function modules such as mobile app and cloud form for collecting depression health information, early warning SMS platform, and health management software were designed, and the functions of the modules were preliminarily developed. Finally, the black-box test and white-box test were used to assess the system’s functions and ensure the reliability of the system. Through the integration of mobile app and computer software, this study preliminarily realized the screening and early warning health management of a population at high risk for depression.

Applying the Digital Health Social Justice Guide

Introduction

Digital health, the use of apps, text-messaging, and online interventions, can revolutionize healthcare and make care more equitable. Currently, digital health interventions are often not designed for those who could benefit most and may have unintended consequences. In this paper, we explain how privacy vulnerabilities and power imbalances, including racism and sexism, continue to influence health app design and research. We provide guidelines for researchers to design, report and evaluate digital health studies to maximize social justice in health.

Methods

From September 2020 to April 2021, we held five discussion and brainstorming sessions with researchers, students, and community partners to develop the guide and the key questions. We additionally conducted an informal literature review, invited experts to review our guide, and identified examples from our own digital health study and other studies.

Results

We identified five overarching topics with key questions and subquestions to guide researchers in designing or evaluating a digital health research study. The overarching topics are: 1. Equitable distribution; 2. Equitable design; 3. Privacy and data return; 4. Stereotype and bias; 5. Structural racism.

Conclusion

We provide a guide with five key topics and questions for social justice digital health research. Encouraging researchers and practitioners to ask these questions will help to spark a transformation in digital health toward more equitable and ethical research. Future work needs to determine if the quality of studies can improve when researchers use this guide.

EMPOWERing Patients With Diabetes Using Profiling and Targeted Feedbacks Delivered Through Smartphone App and Wearable (EMPOWER): Protocol for a Randomized Controlled Trial on Effectiveness and Implementation

Introduction

Type 2 diabetes mellitus (T2DM) poses huge burden and cost on the healthcare system. Mobile health (mHealth) interventions that incorporate wearables may be able to improve diabetes self-management. The aim of this randomized controlled trial (RCT) is to investigate the clinical and cost-effectiveness of personalized educational and behavioral interventions delivered through an EMPOWER mobile application (app) among patients with T2DM.

Methods

This is a parallel two-arm randomized controlled trial (RCT). Patients with T2DM recruited from primary care will be randomly allocated in a 1:1 ratio to either intervention or control group. The intervention group will receive personalized educational and behavioral interventions through the EMPOWER app in addition to their usual clinical care. The control group will receive the usual clinical care for their T2DM but will not have access to the EMPOWER app. Our primary outcome is patient activation score at 12 months. Secondary outcomes will include HbA1c, physical activity level and diet throughout 12 months; quality of life (QoL), medication adherence, direct healthcare cost and indirect healthcare cost at 6 and 12 months.

Discussion

This RCT will provide valuable insights into the effectiveness and implementation of personalized educational and behavioral interventions delivered through mobile application in T2DM management. Findings from this study can help to achieve sustainable and cost-effective behavioral change in patients with T2DM, and this can be potentially scaled to other chronic diseases such as hypertension and dyslipidemia.

Feasibility and Acceptability of a Physical Activity Tracker and Text Messages to Promote Physical Activity During Chemotherapy for Colorectal Cancer: Pilot Randomized Controlled Trial (Smart Pace II)

BACKGROUND

We conducted a pilot 2-arm randomized controlled trial to assess the feasibility of a digital health intervention to increase moderate-to-vigorous physical activity in patients with colorectal cancer (CRC) during chemotherapy.

OBJECTIVE

This study aimed to determine whether a digital health physical activity intervention is feasible and acceptable during chemotherapy for CRC.

METHODS

Potentially eligible patients with CRC expected to receive at least 12 weeks of chemotherapy were identified in person at the University of California, San Francisco, and on the web through advertising. Eligible patients were randomized 1:1 to a 12-week intervention (Fitbit Flex, automated SMS text messages) versus usual care. At 0 and 12 weeks, patients wore an Actigraph GT3X+ accelerometer for 7 days and completed surveys, body size measurements, and an optional 6-minute walk test. Participants could not be masked to their intervention arm, but people assessing the body size and 6-minute walk test outcomes were masked. The primary outcomes were adherence (eg, Fitbit wear and text response rate) and self-assessed acceptability of the intervention. The intervention would be considered feasible if we observed at least 80% complete follow-up and 70% adherence and satisfaction, a priori.

RESULTS

From 2018 to 2020, we screened 240 patients; 53.3% (128/240) of patients were ineligible and 26.7% (64/240) declined to participate. A total of 44 patients (44/240, 18%) were randomized to the intervention (n=22) or control (n=22) groups. Of these, 57% (25/44) were women; 68% (30/44) identified as White and 25% (11/44) identified as Asian American or Pacific Islander; and 77% (34/44) had a 4-year college degree. The median age at enrollment was 54 years (IQR 45-62 years). Follow-up at 12 weeks was 91% (40/44) complete. In the intervention arm, patients wore Fitbit devices on a median of 67 out of 84 (80%) study days and responded to a median of 17 out of 27 (63%) questions sent via SMS text message. Among 19 out of 22 (86%) intervention patients who completed the feedback survey, 89% (17/19) were satisfied with the Fitbit device; 63% (12/19) were satisfied with the SMS text messages; 68% (13/19) said the SMS text messages motivated them to exercise; 74% (14/19) said the frequency of SMS text messages (1-3 days) was ideal; and 79% (15/19) said that receiving SMS text messages in the morning and evening was ideal.

CONCLUSIONS

This pilot study demonstrated that many people receiving chemotherapy for CRC are interested in participating in digital health physical activity interventions. Fitbit adherence was high; however, participants indicated a desire for more tailored SMS text message content. Studies with more socioeconomically diverse patients with CRC are required.

TRIAL REGISTRATION

ClinicalTrials.gov NCT03524716; https://clinicaltrials.gov/ct2/show/NCT03524716.

Equity in Psychosocial Outcomes and Care for Racial and Ethnic Minorities and Socioeconomically Disadvantaged People With Diabetes

The role of social determinants of health (SDOH) in promoting equity in diabetes prevalence, incidence, and outcomes continues to be documented in the literature. Less attention has focused on disparities in psychosocial aspects of living with diabetes and the role of SDOH in promoting equity in psychosocial outcomes and care. In this review, the authors describe racial/ethnic and socioeconomic disparities in psychosocial aspects of living with diabetes, discuss promising approaches to promote equity in psychosocial care, and provide future research directions.

Development and validation pathways of artificial intelligence tools evaluated in randomised clinical trials

Objective

Given the complexities of testing the translational capability of new artificial intelligence (AI) tools, we aimed to map the pathways of training/validation/testing in development process and external validation of AI tools evaluated in dedicated randomised controlled trials (AI-RCTs).

Methods

We searched for peer-reviewed protocols and completed AI-RCTs evaluating the clinical effectiveness of AI tools and identified development and validation studies of AI tools. We collected detailed information, and evaluated patterns of development and external validation of AI tools.

Results

We found 23 AI-RCTs evaluating the clinical impact of 18 unique AI tools (2009–2021). Standard-of-care interventions were used in the control arms in all but one AI-RCT. Investigators did not provide access to the software code of the AI tool in any of the studies. Considering the primary outcome, the results were in favour of the AI intervention in 82% of the completed AI-RCTs (14 out of 17). We identified significant variation in the patterns of development, external validation and clinical evaluation approaches among different AI tools. A published development study was found only for 10 of the 18 AI tools. Median time from the publication of a development study to the respective AI-RCT was 1.4 years (IQR 0.2–2.2).

Conclusions

We found significant variation in the patterns of development and validation for AI tools before their evaluation in dedicated AI-RCTs. Published peer-reviewed protocols and completed AI-RCTs were also heterogeneous in design and reporting. Upcoming guidelines providing guidance for the development and clinical translation process aim to improve these aspects.

The Contribution of Artificial Intelligence in Achieving the Sustainable Development Goals (SDGs): What Can Eye Health Can Learn From Commercial Industry and Early Lessons From the Application of Machine Learning in Eye Health Programmes

Achieving The United Nations sustainable developments goals by 2030 will be a challenge. Researchers around the world are working toward this aim across the breadth of healthcare. Technology, and more especially artificial intelligence, has the ability to propel us forwards and support these goals but requires careful application. Artificial intelligence shows promise within healthcare and there has been fast development in ophthalmology, cardiology, diabetes, and oncology. Healthcare is starting to learn from commercial industry leaders who utilize fast and continuous testing algorithms to gain efficiency and find the optimum solutions. This article provides examples of how commercial industry is benefitting from utilizing AI and improving service delivery. The article then provides a specific example in eye health on how machine learning algorithms can be purposed to drive service delivery in a resource-limited setting by utilizing the novel study designs in response adaptive randomization. We then aim to provide six key considerations for researchers who wish to begin working with AI technology which include collaboration, adopting a fast-fail culture and developing a capacity in ethics and data science.

REinforcement learning to improve non-adherence for diabetes treatments by Optimising Response and Customising Engagement (REINFORCE): study protocol of a pragmatic randomised trial

INTRODUCTION

Achieving optimal diabetes control requires several daily self-management behaviours, especially adherence to medication. Evidence supports the use of text messages to support adherence, but there remains much opportunity to improve their effectiveness. One key limitation is that message content has been generic. By contrast, reinforcement learning is a machine learning method that can be used to identify individuals' patterns of responsiveness by observing their response to cues and then optimising them accordingly. Despite its demonstrated benefits outside of healthcare, its application to tailoring communication for patients has received limited attention. The objective of this trial is to test the impact of a reinforcement learning-based text messaging programme on adherence to medication for patients with type 2 diabetes.

METHODS AND ANALYSIS

In the REinforcement learning to Improve Non-adherence For diabetes treatments by Optimising Response and Customising Engagement (REINFORCE) trial, we are randomising 60 patients with suboptimal diabetes control treated with oral diabetes medications to receive a reinforcement learning intervention or control. Subjects in both arms will receive electronic pill bottles to use, and those in the intervention arm will receive up to daily text messages. The messages will be individually adapted using a reinforcement learning prediction algorithm based on daily adherence measurements from the pill bottles. The trial's primary outcome is average adherence to medication over the 6-month follow-up period. Secondary outcomes include diabetes control, measured by glycated haemoglobin A1c, and self-reported adherence. In sum, the REINFORCE trial will evaluate the effect of personalising the framing of text messages for patients to support medication adherence and provide insight into how this could be adapted at scale to improve other self-management interventions.

ETHICS AND DISSEMINATION

This study was approved by the Mass General Brigham Institutional Review Board (IRB) (USA). Findings will be disseminated through peer-reviewed journals, clinicaltrials.gov reporting and conferences.

TRIAL REGISTRATION NUMBER

Clinicaltrials.gov (NCT04473326).

Optimizing Adaptive Notifications in Mobile Health Interventions Systems: Reinforcement Learning from a Data-driven Behavioral Simulator

Mobile health (mHealth) intervention systems can employ adaptive strategies to interact with users. Instead of designing such complex strategies manually, reinforcement learning (RL) can be used to adaptively optimize intervention strategies concerning the user’s context. In this paper, we focus on the issue of overwhelming interactions when learning a good adaptive strategy for the user in RL-based mHealth intervention agents. We present a data-driven approach integrating psychological insights and knowledge of historical data. It allows RL agents to optimize the strategy of delivering context-aware notifications from empirical data when counterfactual information (user responses when receiving notifications) is missing. Our approach also considers a constraint on the frequency of notifications, which reduces the interaction burden for users. We evaluated our approach in several simulation scenarios using real large-scale running data. The results indicate that our RL agent can deliver notifications in a manner that realizes a higher behavioral impact than context-blind strategies.

Conversational Physical Activity Coaches for Spanish and English Speaking Women: A User Design Study

Introduction: Digital technologies, including text messaging and mobile phone apps, can be leveraged to increase people's physical activity and manage health. Chatbots, powered by artificial intelligence, can automatically interact with individuals through natural conversation. They may be more engaging than one-way messaging interventions. To our knowledge, physical activity chatbots have not been developed with low-income participants, nor in Spanish-the second most dominant language in the U.S. We recommend best practices for physical activity chatbots in English and Spanish for low-income women. Methods: We designed a prototype physical activity text-message based conversational agent based on various psychotherapeutic techniques. We recruited participants through SNAP-Ed (Supplemental Nutrition Assistance Program Education) in California (Alameda County) and Tennessee (Shelby County). We conducted qualitative interviews with participants during testing of our prototype chatbot, held a Wizard of Oz study, and facilitated a co-design workshop in Spanish with a subset of our participants. Results: We included 10 Spanish- and 8 English-speaking women between 27 and 41 years old. The majority was Hispanic/Latina (n = 14), 2 were White and 2 were Black/African American. More than half were monolingual Spanish speakers, and the majority was born outside the US (>50% in Mexico). Most participants were unfamiliar with chatbots and were initially skeptical. After testing our prototype, most users felt positively about health chatbots. They desired a personalized chatbot that addresses their concerns about privacy, and stressed the need for a comprehensive system to also aid with nutrition, health information, stress, and involve family members. Differences between English and monolingual Spanish speakers were found mostly in exercise app use, digital literacy, and the wish for family inclusion. Conclusion: Low-income Spanish- and English-speaking women are interested in using chatbots to improve their physical activity and other health related aspects. Researchers developing health chatbots for this population should focus on issues of digital literacy, app familiarity, linguistic and cultural issues, privacy concerns, and personalization. Designing and testing this intervention for and with this group using co-creation techniques and involving community partners will increase the probability that it will ultimately be effective.

Predicting the gender of individuals with tinnitus based on daily life data of the TrackYourTinnitus mHealth platform

Tinnitus is an auditory phantom perception in the absence of an external sound stimulation. People with tinnitus often report severe constraints in their daily life. Interestingly, indications exist on gender differences between women and men both in the symptom profile as well as in the response to specific tinnitus treatments. In this paper, data of the TrackYourTinnitus platform (TYT) were analyzed to investigate whether the gender of users can be predicted. In general, the TYT mobile Health crowdsensing platform was developed to demystify the daily and momentary variations of tinnitus symptoms over time. The goal of the presented investigation is a better understanding of gender-related differences in the symptom profiles of users from TYT. Based on two questionnaires of TYT, four machine learning based classifiers were trained and analyzed. With respect to the provided daily answers, the gender of TYT users can be predicted with an accuracy of 81.7%. In this context, worries, difficulties in concentration, and irritability towards the family are the three most important characteristics for predicting the gender. Note that in contrast to existing studies on TYT, daily answers to the worst symptom question were firstly investigated in more detail. It was found that results of this question significantly contribute to the prediction of the gender of TYT users. Overall, our findings indicate gender-related differences in tinnitus and tinnitus-related symptoms. Based on evidence that gender impacts the development of tinnitus, the gathered insights can be considered relevant and justify further investigations in this direction.

Feasibility and Effectiveness of Assessing Subhealth Using a Mobile Health Management App (MibyeongBogam) in Early Middle-Aged Koreans: Randomized Controlled Trial

BACKGROUND

Mobile health (mHealth) is a major source of health management systems. Moreover, the demand for mHealth, which is in need of change due to the COVID-19 pandemic, is increasing worldwide. Accordingly, interest in health care in everyday life and the importance of mHealth are growing.

OBJECTIVE

We developed the MibyeongBogam (MBBG) app that evaluates the user's subhealth status via a smartphone and provides a health management method based on that user's subhealth status for use in everyday life. Subhealth is defined as a state in which the capacity to recover to a healthy state is diminished, but without the presence of clinical disease. The objective of this study was to compare the awareness and status of subhealth after the use of the MBBG app between intervention and control groups, and to evaluate the app's practicality.

METHODS

This study was a prospective, open-label, parallel group, randomized controlled trial. The study was conducted at two hospitals in Korea with 150 healthy people in their 30s and 40s, at a 1:1 allocation ratio. Participants visited the hospital three times as follows: preintervention, intermediate visit 6 weeks after the intervention, and final visit 12 weeks after the intervention. Key endpoints were measured at the first visit before the intervention and at 12 weeks after the intervention. The primary outcome was the awareness of subhealth, and the secondary outcomes were subhealth status, health-promoting behaviors, and motivation to engage in healthy behaviors.

RESULTS

The primary outcome, subhealth awareness, tended to slightly increase for both groups after the uncompensated intervention, but there was no significant difference in the score between the two groups (intervention group: mean 23.69, SD 0.25 vs control group: mean 23.1, SD 0.25; P=.09). In the case of secondary outcomes, only some variables of the subhealth status showed significant differences between the two groups after the intervention, and the intervention group showed an improvement in the total scores of subhealth (P=.03), sleep disturbance (P=.02), depression (P=.003), anger (P=.01), and anxiety symptoms (P=.009) compared with the control group.

CONCLUSIONS

In this study, the MBBG app showed potential for improving the health, especially with regard to sleep disturbance and depression, of individuals without particular health problems. However, the effects of the app on subhealth awareness and health-promoting behaviors were not clearly evaluated. Therefore, further studies to assess improvements in health after the use of personalized health management programs provided by the MBBG app are needed. The MBBG app may be useful for members of the general public, who are not diagnosed with a disease but are unable to lead an optimal daily life due to discomfort, to seek strategies that can improve their health.

TRIAL REGISTRATION

Clinical Research Information Service KCT0003488; https://cris.nih.go.kr/cris/search/search_result_st01.jsp?seq=14379.

The need for feminist intersectionality in digital health

Digital health, including the use of mobile health apps, telemedicine, and data analytics to improve health systems, has surged during the COVID-19 pandemic. The social and economic fallout from COVID-19 has further exacerbated gender inequities, through increased domestic violence against women, soaring unemployment rates in women, and increased unpaid familial care taken up by women-all factors that can worsen women's health. Digital health can bolster gender equity through increased access to health care, empowerment of one's own health data, and reduced burden of unpaid care work. Yet, digital health is rarely designed from a gender equity perspective. In this Viewpoint, we show that because of lower access and exclusion from app design, gender imbalance in digital health leadership, and harmful gender stereotypes, digital health is disadvantaging women-especially women with racial or ethnic minority backgrounds. Tackling digital health's gender inequities is more crucial than ever. We explain our feminist intersectionality framework to tackle digital health's gender inequities and provide recommendations for future research.

Adaptive learning algorithms to optimize mobile applications for behavioral health: guidelines for design decisions

OBJECTIVE

Providing behavioral health interventions via smartphones allows these interventions to be adapted to the changing behavior, preferences, and needs of individuals. This can be achieved through reinforcement learning (RL), a sub-area of machine learning. However, many challenges could affect the effectiveness of these algorithms in the real world. We provide guidelines for decision-making.

MATERIALS AND METHODS

Using thematic analysis, we describe challenges, considerations, and solutions for algorithm design decisions in a collaboration between health services researchers, clinicians, and data scientists. We use the design process of an RL algorithm for a mobile health study "DIAMANTE" for increasing physical activity in underserved patients with diabetes and depression. Over the 1.5-year project, we kept track of the research process using collaborative cloud Google Documents, Whatsapp messenger, and video teleconferencing. We discussed, categorized, and coded critical challenges. We grouped challenges to create thematic topic process domains.

RESULTS

Nine challenges emerged, which we divided into 3 major themes: 1. Choosing the model for decision-making, including appropriate contextual and reward variables; 2. Data handling/collection, such as how to deal with missing or incorrect data in real-time; 3. Weighing the algorithm performance vs effectiveness/implementation in real-world settings.

CONCLUSION

The creation of effective behavioral health interventions does not depend only on final algorithm performance. Many decisions in the real world are necessary to formulate the design of problem parameters to which an algorithm is applied. Researchers must document and evaulate these considerations and decisions before and during the intervention period, to increase transparency, accountability, and reproducibility.

TRIAL REGISTRATION

clinicaltrials.gov, NCT03490253.

Developing Messaging Content for a Physical Activity Smartphone App Tailored to Low-Income Patients: User-Centered Design and Crowdsourcing Approach

Background

Text messaging interventions can be an effective and efficient way to improve health behavioral changes. However, most texting interventions are neither tested nor designed with diverse end users, which could reduce their impact, and there is limited evidence regarding the optimal design methodology of health text messages tailored to low-income, low–health literacy populations and non-English speakers.

Objective

This study aims to combine participant feedback, crowdsourced data, and researcher expertise to develop motivational text messages in English and Spanish that will be used in a smartphone app–based texting intervention that seeks to encourage physical activity in low-income minority patients with diabetes diagnoses and depression symptoms.

Methods

The design process consisted of 5 phases and was iterative in nature, given that the findings from each step informed the subsequent steps. First, we designed messages to increase physical activity based on the behavior change theory and knowledge from the available evidence. Second, using user-centered design methods, we refined these messages after a card sorting task and semistructured interviews (N=10) and evaluated their likeability during a usability testing phase of the app prototype (N=8). Third, the messages were tested by English- and Spanish-speaking participants on the Amazon Mechanical Turk (MTurk) crowdsourcing platform (N=134). Participants on MTurk were asked to categorize the messages into overarching theoretical categories based on the capability, opportunity, motivation, and behavior framework. Finally, each coauthor rated the messages for their overall quality from 1 to 5. All messages were written at a sixth-grade or lower reading level and culturally adapted and translated into neutral Spanish by bilingual research staff.

Results

A total of 200 messages were iteratively refined according to the feedback from target users gathered through user-centered design methods, crowdsourced results of a categorization test, and an expert review. User feedback was leveraged to discard unappealing messages and edit the thematic aspects of messages that did not resonate well with the target users. Overall, 54 messages were sorted into the correct theoretical categories at least 50% of the time in the MTurk categorization tasks and were rated 3.5 or higher by the research team members. These were included in the final text message bank, resulting in 18 messages per motivational category.

Conclusions

By using an iterative process of expert opinion, feedback from participants that were reflective of our target study population, crowdsourcing, and feedback from the research team, we were able to acquire valuable inputs for the design of motivational text messages developed in English and Spanish with a low literacy level to increase physical activity. We describe the design considerations and lessons learned for the text messaging development process and provide a novel, integrative framework for future developers of health text messaging interventions.

Conducting Internet-Based Visits for Onboarding Populations With Limited Digital Literacy to an mHealth Intervention: Development of a Patient-Centered Approach

Background

The COVID-19 pandemic has propelled patient-facing research to shift to digital and telehealth strategies. If these strategies are not adapted for minority patients of lower socioeconomic status, health inequality will further increase. Patient-centered models of care can successfully improve access and experience for minority patients.

Objective

This study aims to present the development process and preliminary acceptability of altering in-person onboarding procedures into internet-based, remote procedures for a mobile health (mHealth) intervention in a population with limited digital literacy.

Methods

We actively recruited safety-net patients (English- and Spanish-speaking adults with diabetes and depression who were receiving care at a public health care delivery system in San Francisco, United States) into a randomized controlled trial of text messaging support for physical activity. Because of the COVID-19 pandemic, we modified the in-person recruitment and onboarding procedures to internet-based, remote processes with human support. We conducted a preliminary evaluation of how the composition of the recruited cohort might have changed from the pre–COVID-19 period to the COVID-19 enrollment period. First, we analyzed the digital profiles of patients (n=32) who had participated in previous in-person onboarding sessions prior to the COVID-19 pandemic. Next, we documented all changes made to our onboarding processes to account for remote recruitment, especially those needed to support patients who were not very familiar with downloading apps onto their mobile phones on their own. Finally, we used the new study procedures to recruit patients (n=11) during the COVID-19 social distancing period. These patients were also asked about their experience enrolling into a fully digitized mHealth intervention.

Results

Recruitment across both pre–COVID-19 and COVID-19 periods (N=43) demonstrated relatively high rates of smartphone ownership but lower self-reported digital literacy, with 32.6% (14/43) of all patients reporting they needed help with using their smartphone and installing apps. Significant changes were made to the onboarding procedures, including facilitating app download via Zoom video call and/or a standard phone call and implementing brief, one-on-one staff-patient interactions to provide technical assistance personalized to each patient’s digital literacy skills. Comparing recruitment during pre–COVID-19 and COVID-19 periods, the proportion of patients with digital literacy barriers reduced from 34.4% (11/32) in the pre–COVID-19 cohort to 27.3% (3/11) in the COVID-19 cohort. Differences in digital literacy scores between both cohorts were not significant (P=.49).

Conclusions

Patients of lower socioeconomic status have high interest in using digital platforms to manage their health, but they may require additional upfront human support to gain access. One-on-one staff-patient partnerships allowed us to provide unique technical assistance personalized to each patient’s digital literacy skills, with simple strategies to troubleshoot patient barriers upfront. These additional remote onboarding strategies can mitigate but not eliminate digital barriers for patients without extensive technology experience.

Trial Registration

Clinicaltrials.gov NCT0349025, https://clinicaltrials.gov/ct2/show/NCT03490253

Daily Motivational Text Messages to Promote Physical Activity in University Students: Results From a Microrandomized Trial

BACKGROUND

Low physical activity is an important risk factor for common physical and mental disorders. Physical activity interventions delivered via smartphones can help users maintain and increase physical activity, but outcomes have been mixed.

PURPOSE

Here we assessed the effects of sending daily motivational and feedback text messages in a microrandomized clinical trial on changes in physical activity from one day to the next in a student population.

METHODS

We included 93 participants who used a physical activity app, "DIAMANTE" for a period of 6 weeks. Every day, their phone pedometer passively tracked participants' steps. They were microrandomized to receive different types of motivational messages, based on a cognitive-behavioral framework, and feedback on their steps. We used generalized estimation equation models to test the effectiveness of feedback and motivational messages on changes in steps from one day to the next.

RESULTS

Sending any versus no text message initially resulted in an increase in daily steps (729 steps, p = .012), but this effect decreased over time. A multivariate analysis evaluating each text message category separately showed that the initial positive effect was driven by the motivational messages though the effect was small and trend-wise significant (717 steps; p = .083), but not the feedback messages (-276 steps, p = .4).

CONCLUSION

Sending motivational physical activity text messages based on a cognitive-behavioral framework may have a positive effect on increasing steps, but this decreases with time. Further work is needed to examine using personalization and contextualization to improve the efficacy of text-messaging interventions on physical activity outcomes.

CLINICALTRIALS.GOV IDENTIFIER

NCT04440553.