Microrandomized trials: An experimental design for developing just-in-time adaptive interventions

An overview of and recommendations for more accessible digital mental health services

Mental health concerns are common, and various evidence-based interventions for mental health conditions have been developed. However, many people have difficulty accessing appropriate mental health care and this has been exacerbated by the COVID-19 pandemic. Digital mental health services, such as those delivered by mobile phone or web-based platforms, offer the possibility of expanding the reach and accessibility of mental health care. To achieve this goal, digital mental health interventions and plans for their implementation must be designed with the end users in mind. In this Review, we describe the evidence base for digital mental health interventions across various diagnoses and treatment targets. Then, we explain the different formats for digital mental health intervention delivery, and offer considerations for their use across key age groups. We discuss the role that the COVID-19 pandemic has played in emphasizing the value of these interventions, and offer considerations for ensuring equity in access to digital mental health interventions among diverse populations. As healthcare providers continue to embrace the role that technology can play in broadening access to care, the design and implementation of digital mental healthcare solutions must be carefully considered to maximize their effectiveness and accessibility.

Digital Life Data in the Clinical Whitespace

In our increasingly digital world, aspects of our lives are encoded in the routine interactions we have with technology. Over the past few years, psychologists and technologists have been exploring what possibilities these digital life data might hold for improving mental health and well-being. Here I examine some of the recent advances in this field, particularly in the use of language data; consider the ethical and pragmatic implications of this technology; and examine a few areas where I believe these advances could significantly alter the way in which mental health and well-being are approached. This technology holds special promise for providing information about a patient’s life in between clinical encounters, in the clinical whitespace.

Using Health Concept Surveying to Elicit Usable Evidence: Case Studies of a Novel Evaluation Methodology

BACKGROUND

Developers, designers, and researchers use rapid prototyping methods to project the adoption and acceptability of their health intervention technology (HIT) before the technology becomes mature enough to be deployed. Although these methods are useful for gathering feedback that advances the development of HITs, they rarely provide usable evidence that can contribute to our broader understanding of HITs.

OBJECTIVE

In this research, we aim to develop and demonstrate a variation of vignette testing that supports developers and designers in evaluating early-stage HIT designs while generating usable evidence for the broader research community.

METHODS

We proposed a method called health concept surveying for untangling the causal relationships that people develop around conceptual HITs. In health concept surveying, investigators gather reactions to design concepts through a scenario-based survey instrument. As the investigator manipulates characteristics related to their HIT, the survey instrument also measures proximal cognitive factors according to a health behavior change model to project how HIT design decisions may affect the adoption and acceptability of an HIT. Responses to the survey instrument were analyzed using path analysis to untangle the causal effects of these factors on the outcome variables.

RESULTS

We demonstrated health concept surveying in 3 case studies of sensor-based health-screening apps. Our first study (N=54) showed that a wait time incentive could influence more people to go see a dermatologist after a positive test for skin cancer. Our second study (N=54), evaluating a similar application design, showed that although visual explanations of algorithmic decisions could increase participant trust in negative test results, the trust would not have been enough to affect people's decision-making. Our third study (N=263) showed that people might prioritize test specificity or sensitivity depending on the nature of the medical condition.

CONCLUSIONS

Beyond the findings from our 3 case studies, our research uses the framing of the Health Belief Model to elicit and understand the intrinsic and extrinsic factors that may affect the adoption and acceptability of an HIT without having to build a working prototype. We have made our survey instrument publicly available so that others can leverage it for their own investigations.

Reinforcement learning as an innovative model-based approach: Examples from precision dosing, digital health and computational psychiatry

Model-based approaches are instrumental for successful drug development and use. Anchored within pharmacological principles, through mathematical modeling they contribute to the quantification of drug response variability and enables precision dosing. Reinforcement learning (RL)-a set of computational methods addressing optimization problems as a continuous learning process-shows relevance for precision dosing with high flexibility for dosing rule adaptation and for coping with high dimensional efficacy and/or safety markers, constituting a relevant approach to take advantage of data from digital health technologies. RL can also support contributions to the successful development of digital health applications, recognized as key players of the future healthcare systems, in particular for reducing the burden of non-communicable diseases to society. RL is also pivotal in computational psychiatry-a way to characterize mental dysfunctions in terms of aberrant brain computations-and represents an innovative modeling approach forpsychiatric indications such as depression or substance abuse disorders for which digital therapeutics are foreseen as promising modalities.

Building on the past 50 years, not starting over: A balanced interpretation of meta-analyses, reviews, and commentaries on treatments for suicide and self-injury

Several recent meta-analyses on interventions for self-injurious thoughts and behaviors (SITBs) have been conducted. The primary finding of these meta-analyses is that the observed effects of interventions for SITBs are generally quite small and are far from where we need to be as a field. Although we agree with these general findings, we disagree, however, with many of the overly bleak conclusions drawn from these findings that emphasize creating new treatments while discounting the benefit of improving existing interventions and the decades of research that were involved in creating them. Accordingly, we offer three future directions with promise to build upon and improve our existing treatments, while we simultaneously work to develop new ones: (1) determine which intervention(s) are needed for which person and at which time, (2) conduct more research on intervention length before concluding that brief interventions are just as efficacious as longer ones, and (3) evaluate the potential of comprehensive models of suicide prevention as a more efficacious alternative to any one individual intervention.

A personalized mobile app for physical activity: An experimental mixed-methods study

Objectives

To investigate the feasibility of the be.well app and its personalization approach which regularly considers users’ preferences, amongst university students.

Methods

We conducted a mixed-methods, pre-post experiment, where participants used the app for 2 months. Eligibility criteria included: age 18–34 years; owning an iPhone with Internet access; and fluency in English. Usability was assessed by a validated questionnaire; engagement metrics were reported. Changes in physical activity were assessed by comparing the difference in daily step count between baseline and 2 months. Interviews were conducted to assess acceptability; thematic analysis was conducted.

Results

Twenty-three participants were enrolled in the study (mean age = 21.9 years, 71.4% women). The mean usability score was 5.6 ± 0.8 out of 7. The median daily engagement time was 2 minutes. Eighteen out of 23 participants used the app in the last month of the study. Qualitative data revealed that people liked the personalized activity suggestion feature as it was actionable and promoted user autonomy. Some users also expressed privacy concerns if they had to provide a lot of personal data to receive highly personalized features. Daily step count increased after 2 months of the intervention (median difference = 1953 steps/day, p-value <.001, 95% CI 782 to 3112).

Conclusions

Incorporating users’ preferences in personalized advice provided by a physical activity app was considered feasible and acceptable, with preliminary support for its positive effects on daily step count. Future randomized studies with longer follow up are warranted to determine the effectiveness of personalized mobile apps in promoting physical activity.

Just-in-Time Adaptive Interventions for Suicide Prevention: Promise, Challenges, and Future Directions

The suicide rate (currently 14 per 100,000) has barely changed in the United States over the past 100 years. There is a need for new ways of preventing suicide. Further, research has revealed that suicidal thoughts and behaviors and the factors that drive them are dynamic, heterogeneous, and interactive. Most existing interventions for suicidal thoughts and behaviors are infrequent, not accessible when most needed, and not systematically tailored to the person using their own data (e.g., from their own smartphone). Advances in technology offer an opportunity to develop new interventions that may better match the dynamic, heterogeneous, and interactive nature of suicidal thoughts and behaviors. Just-In-Time Adaptive Interventions (JITAIs), which use smartphones and wearables, are designed to provide the right type of support at the right time by adapting to changes in internal states and external contexts, offering a promising pathway toward more effective suicide prevention. In this review, we highlight the potential of JITAIs for suicide prevention, challenges ahead (e.g., measurement, ethics), and possible solutions to these challenges.

Technology-supported strategies for promoting user engagement with digital mental health interventions: A systematic review

Background

Although digital mental health interventions (DMHIs) offer a potential solution for increasing access to mental health treatment, their integration into real-world settings has been slow. A key reason for this is poor user engagement. A growing number of studies evaluating strategies for promoting engagement with DMHIs means that a review of the literature is now warranted. This systematic review is the first to synthesise evidence on technology-supported strategies for promoting engagement with DMHIs.

Methods

MEDLINE, EmbASE, PsycINFO and PubMed databases were searched from 1 January 1995 to 1 October 2021. Experimental or quasi-experimental studies examining the effect of technology-supported engagement strategies deployed alongside DMHIs were included, as were secondary analyses of such studies. Title and abstract screening, full-text coding and quality assessment were performed independently by two authors. Narrative synthesis was used to summarise findings from the included studies.

Results

24 studies (10,266 participants) were included. Engagement strategies ranged from reminders, coaching, personalised information and peer support. Most strategies were disseminated once a week, usually via email or telephone. There was some empirical support for the efficacy of technology-based strategies towards promoting engagement. However, findings were mixed regardless of strategy type or study aim.

Conclusions

Technology-supported strategies appear to increase engagement with DMHIs; however, their efficacy varies widely by strategy type. Future research should involve end-users in the development and evaluation of these strategies to develop a more cohesive set of strategies that are acceptable and effective for target audiences, and explore the mechanism(s) through which such strategies promote engagement.

Optimizing a Just-in-Time Adaptive Intervention to Improve Dietary Adherence in Behavioral Obesity Treatment: Protocol for a Microrandomized Trial

BACKGROUND

Behavioral obesity treatment (BOT) is a gold standard approach to weight loss and reduces the risk of cardiovascular disease. However, frequent lapses from the recommended diet stymie weight loss and prevent individuals from actualizing the health benefits of BOT. There is a need for innovative treatment solutions to improve adherence to the prescribed diet in BOT.

OBJECTIVE

The aim of this study is to optimize a smartphone-based just-in-time adaptive intervention (JITAI) that uses daily surveys to assess triggers for dietary lapses and deliver interventions when the risk of lapse is high. A microrandomized trial design will evaluate the efficacy of any interventions (ie, theory-driven or a generic alert to risk) on the proximal outcome of lapses during BOT, compare the effects of theory-driven interventions with generic risk alerts on the proximal outcome of lapse, and examine contextual moderators of interventions.

METHODS

Adults with overweight or obesity and cardiovascular disease risk (n=159) will participate in a 6-month web-based BOT while using the JITAI to prevent dietary lapses. Each time the JITAI detects elevated lapse risk, the participant will be randomized to no intervention, a generic risk alert, or 1 of 4 theory-driven interventions (ie, enhanced education, building self-efficacy, fostering motivation, and improving self-regulation). The primary outcome will be the occurrence of lapse in the 2.5 hours following randomization. Contextual moderators of intervention efficacy will also be explored (eg, location and time of day). The data will inform an optimized JITAI that selects the theory-driven approach most likely to prevent lapses in a given moment.

RESULTS

The recruitment for the microrandomized trial began on April 19, 2021, and is ongoing.

CONCLUSIONS

This study will optimize a JITAI for dietary lapses so that it empirically tailors the provision of evidence-based intervention to the individual and context. The finalized JITAI will be evaluated for efficacy in a future randomized controlled trial of distal health outcomes (eg, weight loss).

TRIAL REGISTRATION

ClinicalTrials.gov NCT04784585; http://clinicaltrials.gov/ct2/show/NCT04784585.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/33568.

A Theory- and Evidence-Based Digital Intervention Tool for Weight Loss Maintenance (NoHoW Toolkit): Systematic Development and Refinement Study

Background

Many weight loss programs show short-term effectiveness, but subsequent weight loss maintenance is difficult to achieve. Digital technologies offer a promising means of delivering behavior change approaches at low costs and on a wide scale. The Navigating to a Healthy Weight (NoHoW) project, which was funded by the European Union’s Horizon 2020 research and innovation program, aimed to develop, test, and evaluate a digital toolkit designed to promote successful long-term weight management. The toolkit was tested in an 18-month, large-scale, international, 2×2 factorial (motivation and self-regulation vs emotion regulation) randomized controlled trial that was conducted on adults with overweight or obesity who lost ≥5% of their body weight in the preceding 12 months before enrollment into the intervention.

Objective

This paper aims to describe the development of the NoHoW Toolkit, focusing on the logic models, content, and specifications, as well as the results from user testing.

Methods

The toolkit was developed by using a systematic approach, which included the development of the theory-based logic models, the selection of behavior change techniques, the translation of these techniques into a web-based app (NoHoW Toolkit components), technical development, and the user evaluation and refinement of the toolkit.

Results

The toolkit included a set of web-based tools and inputs from digital tracking devices (smart scales and activity trackers) and modules that targeted weight, physical activity, and dietary behaviors. The final toolkit comprised 34 sessions that were distributed through 15 modules and provided active content over a 4-month period. The motivation and self-regulation arm consisted of 8 modules (17 sessions), the emotion regulation arm was presented with 7 modules (17 sessions), and the combined arm received the full toolkit (15 modules; 34 sessions). The sessions included a range of implementations, such as videos, testimonies, and questionnaires. Furthermore, the toolkit contained 5 specific data tiles for monitoring weight, steps, healthy eating, mood, and sleep.

Conclusions

A systematic approach to the development of digital solutions based on theory, evidence, and user testing may significantly contribute to the advancement of the science of behavior change and improve current solutions for sustained weight management. Testing the toolkit by using a 2×2 design provided a unique opportunity to examine the effect of motivation and self-regulation and emotion regulation separately, as well as the effect of their interaction in weight loss maintenance.

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).

Practices for monitoring and responding to incoming data on self-injurious thoughts and behaviors in intensive longitudinal studies: A systematic review

Advancements in the understanding and prevention of self-injurious thoughts and behaviors (SITBs) are urgently needed. Intensive longitudinal data collection methods-such as ecological momentary assessment-capture fine-grained, "real-world" information about SITBs as they occur and thus have the potential to narrow this gap. However, collecting real-time data on SITBs presents complex ethical and practical considerations, including about whether and how to monitor and respond to incoming information about SITBs from suicidal or self-injuring individuals during the study. We conducted a systematic review of protocols for monitoring and responding to incoming data in previous and ongoing intensive longitudinal studies of SITBs. Across the 61 included unique studies/samples, there was no clear most common approach to managing these ethical and safety considerations. For example, studies were fairly evenly split between either using automated notifications triggered by specific survey responses (e.g., indicating current suicide risk) or monitoring and intervening upon (generally with a phone-based risk assessment) incoming responses (36%), using both automated notifications and monitoring/intervening (35%), or neither using automated notifications nor monitoring/intervening (29%). Certain study characteristics appeared to influence the safety practices used. Future research that systematically evaluates optimal, feasible strategies for managing risk in real-time monitoring research on SITBs is needed.

Translating strategies for promoting engagement in mobile health: A proof-of-concept microrandomized trial

OBJECTIVE

Mobile technologies allow for accessible and cost-effective health monitoring and intervention delivery. Despite these advantages, mobile health (mHealth) engagement is often insufficient. While monetary incentives may increase engagement, they can backfire, dampening intrinsic motivations and undermining intervention scalability. Theories from psychology and behavioral economics suggest useful nonmonetary strategies for promoting engagement; however, examinations of the applicability of these strategies to mHealth engagement are lacking. This proof-of-concept study evaluates the translation of theoretically-grounded engagement strategies into mHealth, by testing their potential utility in promoting daily self-reporting.

METHOD

A microrandomized trial (MRT) was conducted with adolescents and emerging adults with past-month substance use. Participants were randomized multiple times daily to receive theoretically-grounded strategies, namely reciprocity (the delivery of inspirational quote prior to self-reporting window) and nonmonetary reinforcers (e.g., the delivery of meme/gif following self-reporting completion) to improve proximal engagement in daily mHealth self-reporting.

RESULTS

Daily self-reporting rates (62.3%; n = 68) were slightly lower than prior literature, albeit with much lower financial incentives. The utility of specific strategies was found to depend on contextual factors pertaining to the individual's receptivity and risk for disengagement. For example, the effect of reciprocity significantly varied depending on whether this strategy was employed (vs. not employed) during the weekend. The nonmonetary reinforcement strategy resulted in different outcomes when operationalized in various ways.

CONCLUSIONS

While the results support the translation of the reciprocity strategy into this mHealth setting, the translation of nonmonetary reinforcement requires further consideration prior to inclusion in a full scale MRT. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

One view of the next decade of research on behavioral and biobehavioral approaches to cancer prevention and control: intervention optimization

As a new decade begins, we propose that the time is right to reexamine current methods and procedures and look for opportunities to accelerate progress in cancer prevention and control. In this article we offer our view of the next decade of research on behavioral and biobehavioral interventions for cancer prevention and control. We begin by discussing and questioning several implicit conventions. We then briefly introduce an alternative research framework: the multiphase optimization strategy (MOST). MOST, a principled framework for intervention development, optimization, and evaluation, stresses not only intervention effectiveness, but also intervention affordability, scalability, and efficiency. We review some current limitations of MOST along with future directions for methodological work in this area, and suggest some changes in the scientific environment we believe would permit wider adoption of intervention optimization. We propose that wider adoption of intervention optimization would have a positive impact on development and successful implementation of interventions for cancer prevention and control and on intervention science more broadly, including accumulation of a coherent base of knowledge about what works and what does not; establishment of an empirical basis for adaptation of interventions to different settings with different levels and types of resources; and, in the long run, acceleration of progress from Stage 0 to Stage V in the National Institutes of Health Model of Stages of Intervention Development.

Dynamic models of stress-smoking responses based on high-frequency sensor data

Self-reports indicate that stress increases the risk for smoking; however, intensive data from sensors can provide a more nuanced understanding of stress in the moments leading up to and following smoking events. Identifying personalized dynamical models of stress-smoking responses can improve characterizations of smoking responses following stress, but techniques used to identify these models require intensive longitudinal data. This study leveraged advances in wearable sensing technology and digital markers of stress and smoking to identify person-specific models of stress and smoking system dynamics by considering stress immediately before, during, and after smoking events. Adult smokers (n = 45) wore the AutoSense chestband (respiration-inductive plethysmograph, electrocardiogram, accelerometer) with MotionSense (accelerometers, gyroscopes) on each wrist for three days prior to a quit attempt. The odds of minute-level smoking events were regressed on minute-level stress probabilities to identify person-specific dynamic models of smoking responses to stress. Simulated pulse responses to a continuous stress episode revealed a consistent pattern of increased odds of smoking either shortly after the beginning of the simulated stress episode or with a delay, for all participants. This pattern is followed by a dramatic reduction in the probability of smoking thereafter, for about half of the participants (49%). Sensor-detected stress probabilities indicate a vulnerability for smoking that may be used as a tailoring variable for just-in-time interventions to support quit attempts.

A Text Messaging Intervention (StayWell at Home) to Counteract Depression and Anxiety During COVID-19 Social Distancing: Pre-Post Study

BACKGROUND

Social distancing and stay-at-home orders are critical interventions to slow down person-to-person transmission of COVID-19. While these societal changes help contain the pandemic, they also have unintended negative consequences, including anxiety and depression. We developed StayWell, a daily skills-based SMS text messaging program, to mitigate COVID-19-related depression and anxiety symptoms among people who speak English and Spanish in the United States.

OBJECTIVE

This paper describes the changes in StayWell participants' anxiety and depression levels after 60 days of exposure to skills-based SMS text messages.

METHODS

We used self-administered, empirically supported web-based questionnaires to assess the demographic and clinical characteristics of StayWell participants. Anxiety and depression were measured using the 2-item Generalized Anxiety Disorder (GAD-2) scale and the 8-item Patient Health Questionnaire-8 (PHQ-8) scale at baseline and 60-day timepoints. We used 2-tailed paired t tests to detect changes in PHQ-8 and GAD-2 scores from baseline to follow-up measured 60 days later.

RESULTS

The analytic sample includes 193 participants who completed both the baseline and 60-day exit questionnaires. At the 60-day time point, there were significant reductions in both PHQ-8 and GAD-2 scores from baseline. We found an average reduction of -1.72 (95% CI -2.35 to -1.09) in PHQ-8 scores and -0.48 (95% CI -0.71 to -0.25) in GAD-2 scores. These improvements translated to an 18.5% and 17.2% reduction in mean PHQ-8 and GAD-2 scores, respectively.

CONCLUSIONS

StayWell is an accessible, low-intensity population-level mental health intervention. Participation in StayWell focused on COVID-19 mental health coping skills and was related to improved depression and anxiety symptoms. In addition to improvements in outcomes, we found high levels of engagement during the 60-day intervention period. Text messaging interventions could serve as an important public health tool for disseminating strategies to manage mental health.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04473599; https://clinicaltrials.gov/ct2/show/NCT04473599.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.2196/23592.

Estimating time-varying causal excursion effect in mobile health with binary outcomes

Advances in wearables and digital technology now make it possible to deliver behavioral mobile health interventions to individuals in their everyday life. The micro-randomized trial is increasingly used to provide data to inform the construction of these interventions. In a micro-randomized trial, each individual is repeatedly randomized among multiple intervention options, often hundreds or even thousands of times, over the course of the trial. This work is motivated by multiple micro-randomized trials that have been conducted or are currently in the field, in which the primary outcome is a longitudinal binary outcome. The primary aim of such micro-randomized trials is to examine whether a particular time-varying intervention has an effect on the longitudinal binary outcome, often marginally over all but a small subset of the individual's data. We propose the definition of causal excursion effect that can be used in such primary aim analysis for micro-randomized trials with binary outcomes. Under rather restrictive assumptions one can, based on existing literature, derive a semiparametric, locally efficient estimator of the causal effect. Starting from this estimator, we develop an estimator that can be used as the basis of a primary aim analysis under more plausible assumptions. Simulation studies are conducted to compare the estimators. We illustrate the developed methods using data from the micro-randomized trial, BariFit. In BariFit, the goal is to support weight maintenance for individuals who received bariatric surgery.

IntelligentPooling: Practical Thompson Sampling for mHealth

In mobile health (mHealth) smart devices deliver behavioral treatments repeatedly over time to a user with the goal of helping the user adopt and maintain healthy behaviors. Reinforcement learning appears ideal for learning how to optimally make these sequential treatment decisions. However, significant challenges must be overcome before reinforcement learning can be effectively deployed in a mobile healthcare setting. In this work we are concerned with the following challenges: 1) individuals who are in the same context can exhibit differential response to treatments 2) only a limited amount of data is available for learning on any one individual, and 3) non-stationary responses to treatment. To address these challenges we generalize Thompson-Sampling bandit algorithms to develop IntelligentPooling. IntelligentPooling learns personalized treatment policies thus addressing challenge one. To address the second challenge, IntelligentPooling updates each user's degree of personalization while making use of available data on other users to speed up learning. Lastly, IntelligentPooling allows responsivity to vary as a function of a user's time since beginning treatment, thus addressing challenge three.

Person-specific dose-finding for a digital messaging intervention to promote physical activity

OBJECTIVE

Digital messaging is an established method for promoting physical activity. Systematic approaches for dose-finding have not been widely used in behavioral intervention development. We apply system identification tools from control systems engineering to estimate dynamical models and inform decision rules for digital messaging intervention to promote physical activity.

METHOD

Insufficiently active emerging and young adults (n = 45) wore an activity monitor that recorded minute-level step counts and heart rate and received 0-6 digital messages daily on their smartphone for 6 months. Messages were drawn from 3 content libraries (move more, sit less, inspirational quotes). Location recordings via location services in the user's smartphone were used to lookup weather indices at the time and place of message delivery. Following system identification, responses to each message type were simulated under different conditions. Response features were extracted to summarize dynamic processes.

RESULTS

A generic model based on composite data was conservative and did not capture the heterogeneous responses evident in person-specific models. No messages were uniformly ineffective but responses to specific message content in different contexts varied between people. Exterior temperature at the time of message receipt moderated the size of some message effects.

CONCLUSIONS

A generic model of message effects on physical activity can provide the initial evidence for context-sensitive decision rules in a just-in-time adaptive intervention, but it is likely to be error-prone and inefficient. As individual data accumulates, person-specific models should be estimated to optimize treatment and evolve as people are exposed to new environments and accumulate new experiences. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Development features and study characteristics of mobile health apps in the management of chronic conditions: a systematic review of randomised trials

COVID-19 pandemic challenges have accelerated the reliance on digital health fuelling the expanded incorporation of mobile apps into healthcare services, particularly for the management of long-term conditions such as chronic diseases (CDs). However, the impact of health apps on outcomes for CD remains unclear, potentially owing to both the poor adoption of formal development standards in the design process and the methodological quality of studies. A systematic search of randomised trials was performed on Medline, ScienceDirect, the Cochrane Library and Scopus to provide a comprehensive outlook and review the impact of health apps on CD. We identified 69 studies on diabetes (n = 29), cardiovascular diseases (n = 13), chronic respiratory diseases (n = 13), cancer (n = 10) or their combinations (n = 4). The apps rarely adopted developmental factors in the design stage, with only around one-third of studies reporting user or healthcare professional engagement. Apps differed significantly in content, with a median of eight behaviour change techniques adopted, most frequently pertaining to the ‘Feedback and monitoring’ (91%) and ‘Shaping knowledge’ (72%) categories. As for the study methodologies, all studies adopted a traditional randomised control trial (RCT) design, with relatively short follow-ups and limited sample sizes. Findings were not significant for the majority of studies across all CD, with most RCTs revealing a high risk of bias. To support the adoption of apps for CD management, this review reinforces the need for more robust development and appropriate study characteristics to sustain evidence generation and elucidate whether study results reflect the true benefits of apps or a biased estimate due to unsuitable designs.

An Intervention Mapping Study: Developing the Choosing Health digital weight loss and maintenance intervention (Preprint)

Background

Digital health promotion programs tailored to the individual are a potential cost-effective and scalable solution to enable self-management and provide support to people with excess body weight. However, solutions that are widely accessible, personalized, and theory- and evidence-based are still limited.

Objective

This study aimed to develop a digital behavior change program, Choosing Health, that could identify modifiable predictors of weight loss and maintenance for each individual and use these to provide tailored support.

Methods

We applied an Intervention Mapping protocol to design the program. This systematic approach to develop theory- and evidence-based health promotion programs consisted of 6 steps: development of a logic model of the problem, a model of change, intervention design and intervention production, the implementation plan, and the evaluation plan. The decisions made during the Intervention Mapping process were guided by theory, existing evidence, and our own research—including 4 focus groups (n=40), expert consultations (n=12), and interviews (n=11). The stakeholders included researchers, public representatives (including individuals with overweight and obesity), and experts from a variety of relevant backgrounds (including nutrition, physical activity, and the health care sector).

Results

Following a structured process, we developed a tailored intervention that has the potential to reduce excess body weight and support behavior changes in people with overweight and obesity. The Choosing Health intervention consists of tailored, personalized text messages and email support that correspond with theoretical domains potentially predictive of weight outcomes for each participant. The intervention content includes behavior change techniques to support motivation maintenance, self-regulation, habit formation, environmental restructuring, social support, and addressing physical and psychological resources.

Conclusions

The use of an Intervention Mapping protocol enabled the systematic development of the Choosing Health intervention and guided the implementation and evaluation of the program. Through the involvement of different stakeholders, including representatives of the general public, we were able to map out program facilitators and barriers while increasing the ecological validity of the program to ensure that we build an intervention that is useful, user-friendly, and informative. We also summarized the lessons learned for the Choosing Health intervention development and for other health promotion programs.

International Registered Report Identifier (IRRID)

RR2-10.1136/bmjopen-2020-040183

The multiphase optimization strategy (MOST) in child maltreatment prevention research

Each year hundreds of thousands of children and families receive behavioral interventions designed to prevent child maltreatment; yet rates of maltreatment have not declined in over a decade. To reduce the prevalence and prevent the life-long negative consequences of child maltreatment, behavioral interventions must not only be effective, but also affordable, scalable, and efficient to meet the demand for these services. An innovative approach to intervention science is needed. The purpose of this article is to introduce the multiphase optimization strategy (MOST) to the field of child maltreatment prevention. MOST is an engineering-inspired framework for developing, optimizing, and evaluating multicomponent behavioral interventions. MOST enables intervention scientists to empirically examine the performance of each intervention component, independently and in combination. Using a hypothetical example of a home visiting intervention and artificial data, this article demonstrates how MOST may be used to optimize the content of a parent-focused in-home intervention and the engagement strategies of an intervention to increase completion rate to identify an intervention that is effective, efficient, economical, and scalable. We suggest that MOST will ultimately improve prevention science and hasten the progress of translational science to prevent child maltreatment.

Current Evidence and Directions for Future Research in eHealth Physical Activity Interventions for Adults Affected by Cancer: Systematic Review

Background

Physical activity (PA) interventions can increase PA and improve well-being among adults affected by cancer; however, most adults do not meet cancer-specific PA recommendations. Lack of time, facility access, and travel distances are barriers to participation in PA interventions. eHealth technologies may address some of these barriers, serving as a viable way to promote PA behavior change in this population. However, no review from July 2018 has synthesized available evidence across eHealth and cancer types or examined the use of behavioral theory and behavior change techniques (BCTs), leaving important gaps in knowledge.

Objective

This review aims to provide a comprehensive, updated overview of evidence on eHealth PA interventions for adults with cancer by describing the current state of the literature, exploring associations between intervention characteristics and effectiveness, and identifying future research needs.

Methods

MEDLINE, Embase, CINAHL, SportDiscus, Scopus, and CENTRAL were searched for eHealth PA interventions for adults affected by cancer. Study selection and data extraction were performed in duplicate, with consultation from the senior author (NCR). BCT coding, risk of bias, and completeness of reporting were performed using standardized tools. Results were summarized via narrative synthesis and harvest plots. Weight analyses were conducted to explore the associations between intervention characteristics and effectiveness.

Results

A total of 71 articles (67 studies) involving 6655 participants (mean age 56.7 years, SD 8.2) were included. Nearly 50% (32/67) of the articles were published after July 2018. Significant postintervention PA increases were noted in 52% (35/67) of the studies, and PA maintenance was noted in 41% (5/12) of the studies that included a follow-up. Study duration, primary objectives, and eHealth modality (eg, websites, activity trackers, and SMS text messaging) varied widely. Social cognitive theory (23/67, 34%) was the most used theory. The mean number of BCTs used across the studies was 13.5 (SD 5.5), with self-monitoring, credible sources, and goal setting being used in >90% of studies. Weight analyses showed the greatest associations between increased PA levels and PA as a primary outcome (0.621), interventions using websites (0.656) or mobile apps (0.563), interventions integrating multiple behavioral theories (0.750), and interventions using BCTs of problem solving (0.657) and action planning (0.645). All studies had concerns with high risk of bias, mostly because of the risk of confounding, measurement bias, and incomplete reporting.

Conclusions

A range of eHealth PA interventions may increase PA levels among adults affected by cancer, and specific components (eg, websites, use of theory, and action planning) may be linked to greater effectiveness. However, more work is needed to ascertain and optimize effectiveness, measure long-term effects, and address concerns with bias and incomplete reporting. This evidence is required to support arguments for integrating eHealth within PA promotion in oncology.

A Suite of Mobile Conversational Agents for Daily Stress Management (Popbots): Mixed Methods Exploratory Study

BACKGROUND

Approximately 60%-80% of the primary care visits have a psychological stress component, but only 3% of patients receive stress management advice during these visits. Given recent advances in natural language processing, there is renewed interest in mental health chatbots. Conversational agents that can understand a user's problems and deliver advice that mitigates the effects of daily stress could be an effective public health tool. However, such systems are complex to build and costly to develop.

OBJECTIVE

To address these challenges, our aim is to develop and evaluate a fully automated mobile suite of shallow chatbots-we call them Popbots-that may serve as a new species of chatbots and further complement human assistance in an ecosystem of stress management support.

METHODS

After conducting an exploratory Wizard of Oz study (N=14) to evaluate the feasibility of a suite of multiple chatbots, we conducted a web-based study (N=47) to evaluate the implementation of our prototype. Each participant was randomly assigned to a different chatbot designed on the basis of a proven cognitive or behavioral intervention method. To measure the effectiveness of the chatbots, the participants' stress levels were determined using self-reported psychometric evaluations (eg, web-based daily surveys and Patient Health Questionnaire-4). The participants in these studies were recruited through email and enrolled on the web, and some of them participated in follow-up interviews that were conducted in person or on the web (as necessary).

RESULTS

Of the 47 participants, 31 (66%) completed the main study. The findings suggest that the users viewed the conversations with our chatbots as helpful or at least neutral and came away with increasingly positive sentiment toward the use of chatbots for proactive stress management. Moreover, those users who used the system more often (ie, they had more than or equal to the median number of conversations) noted a decrease in depression symptoms compared with those who used the system less often based on a Wilcoxon signed-rank test (W=91.50; Z=-2.54; P=.01; r=0.47). The follow-up interviews with a subset of the participants indicated that half of the common daily stressors could be discussed with chatbots, potentially reducing the burden on human coping resources.

CONCLUSIONS

Our work suggests that suites of shallow chatbots may offer benefits for both users and designers. As a result, this study's contributions include the design and evaluation of a novel suite of shallow chatbots for daily stress management, a summary of benefits and challenges associated with random delivery of multiple conversational interventions, and design guidelines and directions for future research into similar systems, including authoring chatbot systems and artificial intelligence-enabled recommendation algorithms.

Smartphone-Based Interventions to Reduce Sedentary Behavior and Promote Physical Activity Using Integrated Dynamic Models: Systematic Review

BACKGROUND

Traditional psychological theories are inadequate to fully leverage the potential of smartphones and improve the effectiveness of physical activity (PA) and sedentary behavior (SB) change interventions. Future interventions need to consider dynamic models taken from other disciplines, such as engineering (eg, control systems). The extent to which such dynamic models have been incorporated in the development of interventions for PA and SB remains unclear.

OBJECTIVE

This review aims to quantify the number of studies that have used dynamic models to develop smartphone-based interventions to promote PA and reduce SB, describe their features, and evaluate their effectiveness where possible.

METHODS

Databases including PubMed, PsycINFO, IEEE Xplore, Cochrane, and Scopus were searched from inception to May 15, 2019, using terms related to mobile health, dynamic models, SB, and PA. The included studies involved the following: PA or SB interventions involving human adults; either developed or evaluated integrated psychological theory with dynamic theories; used smartphones for the intervention delivery; the interventions were adaptive or just-in-time adaptive; included randomized controlled trials (RCTs), pilot RCTs, quasi-experimental, and pre-post study designs; and were published from 2000 onward. Outcomes included general characteristics, dynamic models, theory or construct integration, and measured SB and PA behaviors. Data were synthesized narratively. There was limited scope for meta-analysis because of the variability in the study results.

RESULTS

A total of 1087 publications were screened, with 11 publications describing 8 studies included in the review. All studies targeted PA; 4 also included SB. Social cognitive theory was the major psychological theory upon which the studies were based. Behavioral intervention technology, control systems, computational agent model, exploit-explore strategy, behavioral analytic algorithm, and dynamic decision network were the dynamic models used in the included studies. The effectiveness of quasi-experimental studies involved reduced SB (1 study; P=.08), increased light PA (1 study; P=.002), walking steps (2 studies; P=.06 and P<.001), walking time (1 study; P=.02), moderate-to-vigorous PA (2 studies; P=.08 and P=.81), and nonwalking exercise time (1 study; P=.31). RCT studies showed increased walking steps (1 study; P=.003) and walking time (1 study; P=.06). To measure activity, 5 studies used built-in smartphone sensors (ie, accelerometers), 3 of which used the phone's GPS, and 3 studies used wearable activity trackers.

CONCLUSIONS

To our knowledge, this is the first systematic review to report on smartphone-based studies to reduce SB and promote PA with a focus on integrated dynamic models. These findings highlight the scarcity of dynamic model-based smartphone studies to reduce SB or promote PA. The limited number of studies that incorporate these models shows promising findings. Future research is required to assess the effectiveness of dynamic models in promoting PA and reducing SB.

TRIAL REGISTRATION

International Prospective Register of Systematic Reviews (PROSPERO) CRD42020139350; https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=139350.

Toward a Just-in-Time Adaptive Intervention to Reduce Emerging Adult Alcohol Use: Testing Approaches for Identifying When to Intervene

ABBREVIATIONS

JITAI: Just-in-time adaptive intervention; ROC: receiver operating characteristic; AUC: area under the curve; MRT: micro-randomized trial.

Evaluation of Changes in Depression, Anxiety, and Social Anxiety Using Smartphone Sensor Features: Longitudinal Cohort Study

BACKGROUND

The assessment of behaviors related to mental health typically relies on self-report data. Networked sensors embedded in smartphones can measure some behaviors objectively and continuously, with no ongoing effort.

OBJECTIVE

This study aims to evaluate whether changes in phone sensor-derived behavioral features were associated with subsequent changes in mental health symptoms.

METHODS

This longitudinal cohort study examined continuously collected phone sensor data and symptom severity data, collected every 3 weeks, over 16 weeks. The participants were recruited through national research registries. Primary outcomes included depression (8-item Patient Health Questionnaire), generalized anxiety (Generalized Anxiety Disorder 7-item scale), and social anxiety (Social Phobia Inventory) severity. Participants were adults who owned Android smartphones. Participants clustered into 4 groups: multiple comorbidities, depression and generalized anxiety, depression and social anxiety, and minimal symptoms.

RESULTS

A total of 282 participants were aged 19-69 years (mean 38.9, SD 11.9 years), and the majority were female (223/282, 79.1%) and White participants (226/282, 80.1%). Among the multiple comorbidities group, depression changes were preceded by changes in GPS features (Time: r=-0.23, P=.02; Locations: r=-0.36, P<.001), exercise duration (r=0.39; P=.03) and use of active apps (r=-0.31; P<.001). Among the depression and anxiety groups, changes in depression were preceded by changes in GPS features for Locations (r=-0.20; P=.03) and Transitions (r=-0.21; P=.03). Depression changes were not related to subsequent sensor-derived features. The minimal symptoms group showed no significant relationships. There were no associations between sensor-based features and anxiety and minimal associations between sensor-based features and social anxiety.

CONCLUSIONS

Changes in sensor-derived behavioral features are associated with subsequent depression changes, but not vice versa, suggesting a directional relationship in which changes in sensed behaviors are associated with subsequent changes in symptoms.

A quality-improvement optimization pilot of BariFit, a mobile health intervention to promote physical activity after bariatric surgery

Bariatric surgery is the most effective treatment for severe obesity (body mass index >40), helping individuals lose, on average, 25%-29% of their body weight over the first year. However, many patients begin to plateau and regain weight within 12-24 months, and 20% of patients begin to regain weight within 6 months postsurgery. As physical activity (PA) is an important predictor of weight loss and maintenance postsurgery, there is a need for scalable, effective lifestyle interventions to help bariatric patients increase PA in order to maximize their weight loss and maintenance. To assess feasibility of using mobile health (mHealth) tools to support PA postsurgery, we conducted a quality-improvement optimization pilot of BariFit, an mHealth intervention that combines commercial devices and custom text messages. Fifty-one bariatric patients enrolled in a 16-week optimization pilot of BariFit. To assess feasibility, pre-post changes in PA were assessed using activPAL. In addition, the pilot randomized, using a 2 × 2 factorial design, two adaptive approaches to daily step goals (variable and 60th percentile goals) and provision of rest days (yes/no), and microrandomized provision of SMS-delivered activity suggestions five times a day for each participant. Adherence to using study equipment was over 95% at 16 weeks. Participants increased PA by 1,866 steps from baseline to end-of-study (p < .007). Participants who received variable step goals averaged 1,141 more steps per day (p = .096) than those who received 60th percentile goals. Activity suggestions had no effect. mHealth interventions are feasible for supporting PA postbariatric surgery.

An iterative, interdisciplinary, collaborative framework for developing and evaluating digital behavior change interventions

The rapid expansion of technology promises to transform the behavior science field by revolutionizing the ways in which individuals can monitor and improve their health behaviors. To fully live into this promise, the behavior science field must address distinct challenges, including: building interventions that are not only scientifically sound but also engaging; using evaluation methods to precisely assess intervention components for intervention optimization; and building personalized interventions that acknowledge and adapt to the dynamic ecosystem of individual and contextual variables that impact behavior change. The purpose of this paper is to provide a framework to address these challenges by leveraging behavior science, human-centered design, and data science expertise throughout the cycle of developing and evaluating digital behavior change interventions (DBCIs). To define this framework, we reviewed current models and practices for intervention development and evaluation, as well as technology industry models for product development. The framework promotes an iterative process, aiming to maximize outcomes by incorporating faster and more frequent testing cycles into the lifecycle of a DBCI. Within the framework provided, we describe each phase, from development to evaluation, to discuss the optimal practices, necessary stakeholders, and proposed evaluation methods. The proposed framework may inform practices in both academia and industry, as well as highlight the need to offer collaborative platforms to ensure successful partnerships that can lead to more effective DBCIs that reach broad and diverse populations.

Innovative methods for observing and changing complex health behaviors: four propositions

Precision health initiatives aim to progressively move from traditional, group-level approaches to health diagnostics and treatments toward ones that are individualized, contextualized, and timely. This article aims to provide an overview of key methods and approaches that can help facilitate this transition in the health behavior change domain. This article is a narrative review of the methods used to observe and change complex health behaviors. On the basis of the available literature, we argue that health behavior change researchers should progressively transition from (i) low- to high-resolution behavioral assessments, (ii) group-only to group- and individual-level statistical inference, (iii) narrative theoretical models to dynamic computational models, and (iv) static to adaptive and continuous tuning interventions. Rather than providing an exhaustive and technical presentation of each method and approach, this article articulates why and how researchers interested in health behavior change can apply these innovative methods. Practical examples contributing to these efforts are presented. If successfully adopted and implemented, the four propositions in this article have the potential to greatly improve our public health and behavior change practices in the near future.

A roadmap to using randomization in clinical trials

BACKGROUND

Randomization is the foundation of any clinical trial involving treatment comparison. It helps mitigate selection bias, promotes similarity of treatment groups with respect to important known and unknown confounders, and contributes to the validity of statistical tests. Various restricted randomization procedures with different probabilistic structures and different statistical properties are available. The goal of this paper is to present a systematic roadmap for the choice and application of a restricted randomization procedure in a clinical trial.

METHODS

We survey available restricted randomization procedures for sequential allocation of subjects in a randomized, comparative, parallel group clinical trial with equal (1:1) allocation. We explore statistical properties of these procedures, including balance/randomness tradeoff, type I error rate and power. We perform head-to-head comparisons of different procedures through simulation under various experimental scenarios, including cases when common model assumptions are violated. We also provide some real-life clinical trial examples to illustrate the thinking process for selecting a randomization procedure for implementation in practice.

RESULTS

Restricted randomization procedures targeting 1:1 allocation vary in the degree of balance/randomness they induce, and more importantly, they vary in terms of validity and efficiency of statistical inference when common model assumptions are violated (e.g. when outcomes are affected by a linear time trend; measurement error distribution is misspecified; or selection bias is introduced in the experiment). Some procedures are more robust than others. Covariate-adjusted analysis may be essential to ensure validity of the results. Special considerations are required when selecting a randomization procedure for a clinical trial with very small sample size.

CONCLUSIONS

The choice of randomization design, data analytic technique (parametric or nonparametric), and analysis strategy (randomization-based or population model-based) are all very important considerations. Randomization-based tests are robust and valid alternatives to likelihood-based tests and should be considered more frequently by clinical investigators.

Power Constrained Bandits

Contextual bandits often provide simple and effective personalization in decision making problems, making them popular tools to deliver personalized interventions in mobile health as well as other health applications. However, when bandits are deployed in the context of a scientific study-e.g. a clinical trial to test if a mobile health intervention is effective-the aim is not only to personalize for an individual, but also to determine, with sufficient statistical power, whether or not the system's intervention is effective. It is essential to assess the effectiveness of the intervention before broader deployment for better resource allocation. The two objectives are often deployed under different model assumptions, making it hard to determine how achieving the personalization and statistical power affect each other. In this work, we develop general meta-algorithms to modify existing algorithms such that sufficient power is guaranteed while still improving each user's well-being. We also demonstrate that our meta-algorithms are robust to various model mis-specifications possibly appearing in statistical studies, thus providing a valuable tool to study designers.

Breast cancer survivors' preferences for social support features in technology-supported physical activity interventions: findings from a mixed methods evaluation

Incorporating peer and professional social support features into remotely delivered, technology-supported physical activity interventions may increase their effectiveness. However, very little is known about survivors' preferences for potential social features. This study explored breast cancer survivors' preferences for both traditional (e.g., coaching calls and peer support) and innovative (i.e., message boards and competitions) social support features within remotely delivered, technology-supported physical activity interventions. Survivors [N = 96; Mage = 55.8 (SD = 10.2)] self-reported demographic and disease characteristics and physical activity. A subset (n = 28) completed semistructured phone interviews. Transcribed interviews were evaluated using a thematic content analysis approach and consensus review. Following interviews, the full sample self-reported preferences for social features for remotely delivered physical activity interventions via online questionnaires. Questionnaire data were analyzed using descriptive statistics. Four themes emerged from interview data: (a) technology increases social connectedness; (b) interest in professional involvement/support; (c) connecting with similar survivors; and (d) apprehension regarding competitive social features. Quantitative data indicated that most survivors were interested in social features including a coach (77.1 per cent), team (66.7 per cent), and exercise buddy (57.3 per cent). Survivors endorsed sharing their activity data with their team (80.0 per cent) and buddy (76.6 per cent), but opinions were mixed regarding a progress board ranking their activity in relation to other participants' progress. Survivors were interested in using a message board to share strategies to increase activity (74.5 per cent) and motivational comments (73.4 per cent). Social features are of overall interest to breast cancer survivors, yet preferences for specific social support features varied. Engaging survivors in developing and implementing remotely delivered, technology-supported social features may enhance their effectiveness.

Ambulatory assessment for precision psychiatry: Foundations, current developments and future avenues

Precision psychiatry stands to benefit from the latest digital technologies for assessment and analyses to tailor treatment towards individuals. Insights into dynamic psychological processes as they unfold in humans' everyday life can critically add value in understanding symptomatology and environmental stressors to provide individualized treatment where and when needed. Towards this goal, ambulatory assessment encompasses methodological approaches to investigate behavioral, physiological, and biological processes in humans' everyday life. It combines repeated assessments of symptomatology over time, e.g., via Ecological Momentary Assessment (e.g., smartphone-diaries), with monitoring of physical behavior, environmental characteristics (such as geolocations, social interactions) and physiological function via sensors, e.g., mobile accelerometers, global-positioning-systems, and electrocardiography. In this review, we expand on promises of ambulatory assessment in the investigation of mental states (e.g., real-life, dynamical and contextual perspective), on chances for precision psychiatry such as the prediction of courses of psychiatric disorders, detection of tipping points and critical windows of relapse, and treatment effects as exemplified by ongoing projects, and on future avenues of how ambulatory interventions can benefit personalized care for psychiatric patients (e.g., through real-time feedback in everyday life). Ambulatory assessment is a key contributor to precision psychiatry, opening up promising avenues in research, diagnoses, prevention and treatment.

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.

Exploring Breaks in Sedentary Behavior of Older Adults Immediately After Receiving Personalized Haptic Feedback: Intervention Study

BACKGROUND

"Push" components of mobile health interventions may be promising to create conscious awareness of habitual sedentary behavior; however, the effect of these components on the near-time, proximal outcome, being breaks in sedentary behavior immediately after receiving a push notification, is still unknown, especially in older adults.

OBJECTIVE

The aims of this study are to examine if older adults break their sedentary behavior immediately after receiving personalized haptic feedback on prolonged sedentary behavior and if the percentage of breaks differs depending on the time of the day when the feedback is provided.

METHODS

A total of 26 Flemish older adults (mean age 64.4 years, SD 3.8) wore a triaxial accelerometer (Activator, PAL Technologies Ltd) for 3 weeks. The accelerometer generated personalized haptic feedback by means of vibrations each time a participant sat for 30 uninterrupted minutes. Accelerometer data on sedentary behavior were used to estimate the proximal outcome, which was sedentary behavior breaks immediately (within 1, 3, and 5 minutes) after receiving personalized haptic feedback. Generalized estimating equations were used to investigate whether or not participants broke up their sedentary behavior immediately after receiving haptic feedback. A time-related variable was added to the model to investigate if the sedentary behavior breaks differed depending on the time of day.

RESULTS

A total of 2628 vibrations were provided to the participants during the 3-week intervention period. Of these 2628 vibrations, 379 (14.4%), 570 (21.7%), and 798 (30.4%) resulted in a sedentary behavior break within 1, 3 and 5 minutes, respectively. Although the 1-minute interval did not reveal significant differences in the percentage of breaks depending on the time at which the haptic feedback was provided, the 3- and 5-minute intervals did show significant differences in the percentage of breaks depending on the time at which the haptic feedback was provided. Concretely, the percentage of sedentary behavior breaks was significantly higher if personalized haptic feedback was provided between noon and 3 PM compared to if the feedback was provided between 6 and 9 AM (odds ratio 1.58, 95% CI 1.01-2.47, within 3 minutes; odds ratio 1.78, 95% CI 1.11-2.84, within 5 minutes).

CONCLUSIONS

The majority of haptic vibrations, especially those in the morning, did not result in a break in the sedentary behavior of older adults. As such, simply bringing habitual sedentary behavior into conscious awareness seems to be insufficient to target sedentary behavior. More research is needed to optimize push components in interventions aimed at the reduction of the sedentary behavior of older adults.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04003324; https://clinicaltrials.gov/ct2/show/NCT04003324.

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.

Opportunity for efficiency in clinical development: An overview of adaptive clinical trial designs and innovative machine learning tools, with examples from the cardiovascular field

Modern data analysis tools and statistical modeling techniques are increasingly used in clinical research to improve diagnosis, estimate disease progression and predict treatment outcomes. What seems less emphasized is the importance of the study design, which can have a serious impact on the study cost, time and statistical efficiency. This paper provides an overview of different types of adaptive designs in clinical trials and their applications to cardiovascular trials. We highlight recent proliferation of work on adaptive designs over the past two decades, including some recent regulatory guidelines on complex trial designs and master protocols. We also describe the increasing role of machine learning and use of metaheuristics to construct increasingly complex adaptive designs or to identify interesting features for improved predictions and classifications.

Investigating Group-Specific Models of Hospital Workers’ Well-Being: Implications for Algorithmic Bias

Hospital workers often experience burnout due to the demanding job responsibilities and long work hours. Data yielding from ambulatory monitoring combined with machine learning algorithms can afford us a better understanding of the naturalistic processes that contribute to this burnout. Motivated by the challenges related to the accurate tracking of well-being in real-life, prior work has investigated group-specific machine learning (GS-ML) models that are tailored to groups of participants. We examine a novel GS-ML for estimating well-being from real-life multimodal measures collected in situ from hospital workers. In contrast to the majority of prior work that uses pre-determined clustering criteria, we propose an iterative procedure that refines participant clusters based on the representations learned by the GS-ML models. Motivated by prior work that highlights the differential impact of job demands on well-being, we further explore the participant clusters in terms of demography and job-related attributes. Results indicate that the GS-ML models mostly outperform general models in estimating well-being constructs. The GS-ML models further depict different degrees of predictive power for each participant cluster, as distinguished upon age, education, occupational role, and number of supervisees. The observed discrepancies with respect to the GS-ML model decisions are discussed in association with algorithmic bias.

A latent profile analysis using the theory of planned behavior to predict alcohol use

OBJECTIVE

The current study sought to identify subgroups of adult drinkers who differ in their level of association between alcohol-related Theory of Planned Behavior (TPB) constructs (attitudes, perceived norms, self-efficacy, and intentions), and explore if distinct subgroup profiles relate to alcohol use two weeks later.

DESIGN

Participants (N = 121) were recruited to participate in a two-week study about daily experiences with exercise and alcohol (M_age = 30.93; SD_age = 9.88; 59.2% female; 71.1% Caucasian).

MAIN OUTCOME MEASURES

Alcohol attitudes, subjective norms, alcohol refusal self-efficacy, and intentions were used to create class membership. Behavioral outcomes included (1) drinking frequency, (2) drinking quantity, and (3) drinking to get drunk.

RESULTS

Two classes of drinkers were determined - Class 1 was categorized by moderate scores on all constructs, whereas Class 2 was categorized by moderate scores on attitudes and high scores on norms, alcohol refusal self-efficacy, and intentions. Class designation was associated with frequency, but not quantity of use.

CONCLUSION

The current study suggests that a minority of individuals who score moderately across all constructs should receive intervention efforts that focus on just those included in the TPB, while the vast majority may require additional constructs to be addressed.

An Ecological Momentary Intervention for people with social anxiety: A descriptive case study

This study describes the development and pilot evaluation of a smartphone- delivered Ecological Momentary Intervention (EMI) for people with social anxiety symptoms. Using a software engineering framework (agile modeling, model-driven development, bottom-up development), mental health experts and software developers collaborated to develop a 4-module EMI app designed to reduce social anxiety in real-time. Fifty-five participants with social anxiety were randomly allocated to the EMI or a wait-list control arm. App downloads, usage and user satisfaction data were collected and mental health outcomes assessed at baseline and post-intervention. Software development practices allowed mental health experts to distil core elements of a psychological intervention into discrete software components but there were challenges in engaging mental health experts in the process. Relative to control there was no significant reduction in social anxiety among the EMI participants in the pilot trial. However, post-test data were available for only 4 intervention and 10 control participants and only 2 (4.0%) of the EMI participants downloaded the app. The two participants who both accessed the app and completed the post-test reported being satisfied with the intervention. Future research should address managing resources and providing additional training to support ongoing engagement with key stakeholders.

["Alternative study designs" for the evaluation of digital health applications - a real alternative?]

INTRODUCTION

After the Digital Healthcare Act (Digitale-Versorgung-Gesetz, DVG) reformed digital health applications' (Digitale Gesundheitsanwendungen, DiGAs) access to German Statutory Health Insurance (SHI) reimbursement, the discussion concerning necessary evidence requirements has intensified. In the past, different "alternative study designs" have been proposed to replace randomized controlled trials (RCTs) in the DiGA efficacy and benefit assessments. The present paper examines the suitability of these alternative designs for informing SHI reimbursement decisions.

METHODS

The four alternative study designs primarily discussed in the context of DiGA - "Continuous Evaluation of Evolving Behavioral Intervention Technologies" (CEEBIT), "Multiphase Optimization Strategy" (MOST), "Sequential Multiple Assignment Randomized Trial" (SMART) and "Micro-Randomized Trial" (MRT) - are characterized and compared on the basis of relevant primary and secondary sources. Subsequently, their suitability for effectiveness and benefit evaluation in the context of SHI reimbursement decisions is discussed.

RESULTS

None of the study designs examined aims primarily at conclusively demonstrating efficacy and benefit. Three of the four designs (MOST, SMART, MRT) focus on the development and optimization of interventions. In order to reduce resource requirements, the approaches presented sometimes deviate considerably from the methodological approach in traditional RCTs. This is especially true for their applied statistical error tolerance and their underlying randomization logic. Three of the four concepts (MOST, SMART, MRT) therefore still require RCTs after the development phase in order to demonstrate the effectiveness and benefit of the optimized intervention.

DISCUSSION

The methodological differences of the alternative study designs compared to classical RCTs are accompanied by serious potentials for bias and uncertainties with regard to the identified intervention effects. These may be acceptable in the context of intervention development, but do not appear to be appropriate for use in collective SHI reimbursement decisions.

CONCLUSION

The alternative study designs presented cannot be regarded as a suitable RCT alternative for efficacy and benefit assessments. A pragmatic study design, which continues to meet high methodological standards, and better utilization of real-world data could, in the future, contribute to a compromise between the justified claims to sufficient certainty of results on the one hand and appropriate procedural effort on the other.

Smoking Cessation Using Wearable Sensors: Protocol for a Microrandomized Trial

BACKGROUND

Cigarette smoking has numerous health consequences and is the leading cause of morbidity and mortality in the United States. Mindfulness has the ability to enhance resilience to stressors and can strengthen an individual's ability to deal with discomfort, which may be particularly useful when managing withdrawal and craving to smoke.

OBJECTIVE

This study aims to evaluate feasibility results from an intervention that provides real-time, real-world mindfulness strategies to a sample of racially and ethnically diverse smokers making a quit attempt.

METHODS

This study uses a microrandomized trial design to deliver mindfulness-based strategies in real time to individuals attempting to quit smoking. Data will be collected via wearable sensors, a study smartphone, and questionnaires filled out during the in-person study visits.

RESULTS

Recruitment is complete, and data management is ongoing.

CONCLUSIONS

The data collected during this feasibility trial will provide preliminary findings about whether mindfulness strategies delivered in real time are a useful quit smoking aid that warrants additional investigation.

TRIAL REGISTRATION

Clinicaltrials.gov NCT03404596; https://clinicaltrials.gov/ct2/show/NCT03404596.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/22877.

Workshop on Implementation Science and Digital Therapeutics for Behavioral Health

Digital therapeutics can overcome many of the barriers to translation of evidence-based treatment for substance use, mental health, and other behavioral health conditions. Delivered via nearly ubiquitous platforms such as the web, smartphone applications, text messaging, and videoconferencing, digital therapeutics can transcend the time and geographic boundaries of traditional clinical settings so that individuals can access care when and where they need it. There is strong empirical support for digital therapeutic approaches for behavioral health, yet implementation science with regard to scaling use of digital therapeutics for behavioral health is still in its early stages. In this paper, we summarize the proceedings of a day-long workshop, "Implementation Science and Digital Therapeutics," sponsored and hosted by the Center for Technology and Behavioral Health at Dartmouth College. The Center for Technology and Behavioral Health is an interdisciplinary P30 Center of Excellence funded by the National Institute on Drug Abuse, with the mission of promoting state-of-the-technology and state-of-the-science for the development, evaluation, and sustainable implementation of digital therapeutic approaches for substance use and related conditions. Workshop presentations were grounded in current models of implementation science. Directions and opportunities for collaborative implementation science research to promote broad adoption of digital therapeutics for behavioral health are offered.

Just-in-time adaptive intervention to promote fluid consumption in patients with kidney stones

OBJECTIVE

Kidney stones are painful and costly. Prevention guidelines emphasize a simple behavior change: increasing fluid intake and urine output. Unfortunately, adherence to those prevention guidelines is limited, and patients report forgetting or not being thirsty enough. This study evaluated the acceptability of using semiautomated tracking of fluid consumption to trigger just-in-time reminders to drink and increase the experienced automaticity of fluid intake.

METHOD

In a single-group trial, participants with a history of kidney stones (n = 31) used the sip^IT digital tools (H2OPal connected water bottle, H2OPal mobile app for self-tracking, Fitbit smartwatch app for gesture detection) for 3 months.

RESULTS

The semiautomated monitoring system detected 46,654 drinking events. From baseline to 1-month follow-up, the experienced automaticity of fluid intake increased significantly (d = 0.50) and remained elevated at 3-month follow-up (d = 0.64). A major barrier to adherence (lack of thirst) decreased from baseline to follow-ups. Retention rates and participant feedback indicated that this digital tool was acceptable to patients.

CONCLUSION

Semiautomated tracking of fluid consumption can be used to trigger just-in-time reminders. Based on this demonstration, the sip^IT tools are ready for testing in a rigorous Phase II trial to evaluate efficacy for increasing fluid consumption and urine output as recommended for preventing the recurrence of kidney stones. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

A Text Messaging Intervention for Coping With Social Distancing During COVID-19 (StayWell at Home): Protocol for a Randomized Controlled Trial

BACKGROUND

Social distancing is a crucial intervention to slow down person-to-person transmission of COVID-19. However, social distancing has negative consequences, including increases in depression and anxiety. Digital interventions, such as text messaging, can provide accessible support on a population-wide scale. We developed text messages in English and Spanish to help individuals manage their depressive mood and anxiety during the COVID-19 pandemic.

OBJECTIVE

In a two-arm randomized controlled trial, we aim to examine the effect of our 60-day text messaging intervention. Additionally, we aim to assess whether the use of machine learning to adapt the messaging frequency and content improves the effectiveness of the intervention. Finally, we will examine the differences in daily mood ratings between the message categories and time windows.

METHODS

The messages were designed within two different categories: behavioral activation and coping skills. Participants will be randomized into (1) a random messaging arm, where message category and timing will be chosen with equal probabilities, and (2) a reinforcement learning arm, with a learned decision mechanism for choosing the messages. Participants in both arms will receive one message per day within three different time windows and will be asked to provide their mood rating 3 hours later. We will compare self-reported daily mood ratings; self-reported depression, using the 8-item Patient Health Questionnaire; and self-reported anxiety, using the 7-item Generalized Anxiety Disorder scale at baseline and at intervention completion.

RESULTS

The Committee for the Protection of Human Subjects at the University of California Berkeley approved this study in April 2020 (No. 2020-04-13162). Data collection began in April 2020 and will run to April 2021. As of August 24, 2020, we have enrolled 229 participants. We plan to submit manuscripts describing the main results of the trial and results from the microrandomized trial for publication in peer-reviewed journals and for presentations at national and international scientific meetings.

CONCLUSIONS

Results will contribute to our knowledge of effective psychological tools to alleviate the negative effects of social distancing and the benefit of using machine learning to personalize digital mental health interventions.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04473599; https://clinicaltrials.gov/ct2/show/NCT04473599.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/23592.

Microrandomized Trial Design for Evaluating Just-in-Time Adaptive Interventions Through Mobile Health Technologies for Cardiovascular Disease

Smartphone and wearable device use is rising broadly and can be leveraged for chronic disease management. Just-in-time adaptive interventions promise to deliver personalized, dynamic interventions directly to patients through use of push notifications from mobile devices. Although just-in-time adaptive interventions are a powerful tool for shaping health behavior, their application to cardiovascular disease management has been limited as they can be challenging to design. Herein, we provide a general overview and conceptual framework for microrandomized trials, a novel experimental study design that can be used to optimize just-in-time adaptive interventions. Microrandomized trials leverage mobile devices to sequentially randomize participants to types or levels of an intervention to determine the effectiveness of an intervention and time-varying moderators of those effects. Microrandomized trials are an efficient study design that can be used to determine which intervention components to include in just-in-time adaptive interventions and to optimize their decision rules while maintaining the strength of causal inference associated with traditional randomized controlled trials.

The H2020 "NoHoW Project": A Position Statement on Behavioural Approaches to Longer-Term Weight Management

There is substantial evidence documenting the effects of behavioural interventions on weight loss (WL). However, behavioural approaches to initial WL are followed by some degree of longer-term weight regain, and large trials focusing on evidence-based approaches to weight loss maintenance (WLM) have generally only demonstrated small beneficial effects. The current state-of-the-art in behavioural interventions for WL and WLM raises questions of (i) how we define the relationship between WL and WLM, (ii) how energy balance (EB) systems respond to WL and influence behaviours that primarily drive weight regain, (iii) how intervention content, mode of delivery and intensity should be targeted to keep weight off, (iv) which mechanisms of action in complex interventions may prevent weight regain and (v) how to design studies and interventions to maximise effective longer-term weight management. In considering these issues a writing team within the NoHoW Consortium was convened to elaborate a position statement, and behaviour change and obesity experts were invited to discuss these positions and to refine them. At present the evidence suggests that developing the skills to self-manage EB behaviours leads to more effective WLM. However, the effects of behaviour change interventions for WL and WLM are still relatively modest and our understanding of the factors that disrupt and undermine self-management of eating and physical activity is limited. These factors include physiological resistance to weight loss, gradual compensatory changes in eating and physical activity and reactive processes related to stress, emotions, rewards and desires that meet psychological needs. Better matching of evidence-based intervention content to quantitatively tracked EB behaviours and the specific needs of individuals may improve outcomes. Improving objective longitudinal tracking of energy intake and energy expenditure over time would provide a quantitative framework in which to understand the dynamics of behaviour change, mechanisms of action of behaviour change interventions and user engagement with intervention components to potentially improve weight management intervention design and evaluation.