A Personalized Smartphone-Delivered Just-in-time Adaptive Intervention (JitaBug) to Increase Physical Activity in Older Adults: Mixed Methods Feasibility Study

Effectiveness of artificial intelligence vs. human coaching in diabetes prevention: a study protocol for a randomized controlled trial

BACKGROUND

Prediabetes is a highly prevalent condition that heralds an increased risk of progression to type 2 diabetes, along with associated microvascular and macrovascular complications. The Diabetes Prevention Program (DPP) is an established effective intervention for diabetes prevention. However, participation in this 12-month lifestyle change program has historically been low. Digital DPPs have emerged as a scalable alternative, accessible asynchronously and recognized by the Centers for Disease Control and Prevention (CDC). Yet, most digital programs still incorporate human coaching, potentially limiting scalability. Furthermore, existing effectiveness results of digital DPPs are primarily derived from per protocol, longitudinal non-randomized studies, or comparisons to control groups that do not represent the standard of care DPP. The potential of an AI-powered DPP as an alternative to the DPP is yet to be investigated. We propose a randomized controlled trial (RCT) to directly compare these two approaches.

METHODS

This open-label, multicenter, non-inferiority RCT will compare the effectiveness of a fully automated AI-powered digital DPP (ai-DPP) with a standard of care human coach-based DPP (h-DPP). A total of 368 participants with elevated body mass index (BMI) and prediabetes will be randomized equally to the ai-DPP (smartphone app and Bluetooth-enabled body weight scale) or h-DPP (referral to a CDC recognized DPP). The primary endpoint, assessed at 12 months, is the achievement of the CDC's benchmark for type 2 diabetes risk reduction, defined as any of the following: at least 5% weight loss, at least 4% weight loss and at least 150 min per week on average of physical activity, or at least a 0.2-point reduction in hemoglobin A1C. Physical activity will be objectively measured using serial actigraphy at baseline and at 1-month intervals throughout the trial. Secondary endpoints, evaluated at 6 and 12 months, will include changes in A1C, weight, physical activity measures, program engagement, and cost-effectiveness. Participants include adults aged 18-75 years with laboratory confirmed prediabetes, a BMI of ≥ 25 kg/m2 (≥ 23 kg/m2 for Asians), English proficiency, and smartphone users. This U.S. study is conducted at Johns Hopkins Medicine in Baltimore, MD, and Reading Hospital (Tower Health) in Reading, PA.

DISCUSSION

Prediabetes is a significant public health issue, necessitating scalable interventions for the millions affected. Our pragmatic clinical trial is unique in directly comparing a fully automated AI-powered approach without direct human coach interaction. If proven effective, it could be a scalable, cost-effective strategy. This trial will offer vital insights into both AI and human coach-based behavioral change strategies in real-world clinical settings.

TRIAL REGISTRATION

ClinicalTrials.gov NCT05056376. Registered on September 24, 2021, https://clinicaltrials.gov/study/NCT05056376.

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.

Digital interventions for healthy ageing and cognitive health in older adults: a systematic review of mixed method studies and meta-analysis

BACKGROUND

Currently, there is no systematic review to investigate the effectiveness of digital interventions for healthy ageing and cognitive health of older adults. This study aimed to conduct a systematic review to evaluate the effectiveness of digital intervention studies for facilitating healthy ageing and cognitive health and further identify the considerations of its application to older adults.

METHODS

A systematic review and meta-analysis of literature were conducted across CINAHL, Medline, ProQuest, Cochrane, Scopus, and PubMed databases following the PRISMA guideline. All included studies were appraised using the Mixed Methods Appraisal Tool Checklist by independent reviewers. Meta-analyses were performed using JBI SUMARI software to compare quantitative studies. Thematic analyses were used for qualitative studies and synthesised into the emerging themes.

RESULTS

Thirteen studies were included. Quantitative results showed no statistically significant pooled effect between health knowledge and healthy behaviour (I2 =76, p=0.436, 95% CI [-0.32,0.74]), and between cardiovascular-related health risks and care dependency I2=0, p=0.426, 95% CI [0.90,1.29]). However, a statistically significant cognitive function preservation was found in older adults who had long-term use of laptop/cellphone devices and had engaged in the computer-based physical activity program (I2=0, p<0.001, 95% CI [0.01, 0.21]). Qualitative themes for the considerations of digital application to older adults were digital engagement, communication, independence, human connection, privacy, and cost.

CONCLUSIONS

Digital interventions used in older adults to facilitate healthy ageing were not always effective. Health knowledge improvement does not necessarily result in health risk reduction in that knowledge translation is key. Factors influencing knowledge translation (i.e., digital engagement, human coaching etc) were identified to determine the intervention effects. However, using digital devices appeared beneficial to maintain older adults' cognitive functions in the longer term. Therefore, the review findings suggest that the expanded meaning of a person-centred concept (i.e., from social, environmental, and healthcare system aspects) should be pursued in future practice. Privacy and cost concerns of technologies need ongoing scrutiny from policy bodies. Future research looking into the respective health benefits can provide more understanding of the current digital intervention applied to older adults.

STUDY REGISTRATION

PROSPERO record ID: CRD42023400707 https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=400707 .

Exploring the Feasibility of Using ChatGPT to Create Just-in-Time Adaptive Physical Activity mHealth Intervention Content: Case Study

BACKGROUND

Achieving physical activity (PA) guidelines' recommendation of 150 minutes of moderate-to-vigorous PA per week has been shown to reduce the risk of many chronic conditions. Despite the overwhelming evidence in this field, PA levels remain low globally. By creating engaging mobile health (mHealth) interventions through strategies such as just-in-time adaptive interventions (JITAIs) that are tailored to an individual's dynamic state, there is potential to increase PA levels. However, generating personalized content can take a long time due to various versions of content required for the personalization algorithms. ChatGPT presents an incredible opportunity to rapidly produce tailored content; however, there is a lack of studies exploring its feasibility.

OBJECTIVE

This study aimed to (1) explore the feasibility of using ChatGPT to create content for a PA JITAI mobile app and (2) describe lessons learned and future recommendations for using ChatGPT in the development of mHealth JITAI content.

METHODS

During phase 1, we used Pathverse, a no-code app builder, and ChatGPT to develop a JITAI app to help parents support their child's PA levels. The intervention was developed based on the Multi-Process Action Control (M-PAC) framework, and the necessary behavior change techniques targeting the M-PAC constructs were implemented in the app design to help parents support their child's PA. The acceptability of using ChatGPT for this purpose was discussed to determine its feasibility. In phase 2, we summarized the lessons we learned during the JITAI content development process using ChatGPT and generated recommendations to inform future similar use cases.

RESULTS

In phase 1, by using specific prompts, we efficiently generated content for 13 lessons relating to increasing parental support for their child's PA following the M-PAC framework. It was determined that using ChatGPT for this case study to develop PA content for a JITAI was acceptable. In phase 2, we summarized our recommendations into the following six steps when using ChatGPT to create content for mHealth behavior interventions: (1) determine target behavior, (2) ground the intervention in behavior change theory, (3) design the intervention structure, (4) input intervention structure and behavior change constructs into ChatGPT, (5) revise the ChatGPT response, and (6) customize the response to be used in the intervention.

CONCLUSIONS

ChatGPT offers a remarkable opportunity for rapid content creation in the context of an mHealth JITAI. Although our case study demonstrated that ChatGPT was acceptable, it is essential to approach its use, along with other language models, with caution. Before delivering content to population groups, expert review is crucial to ensure accuracy and relevancy. Future research and application of these guidelines are imperative as we deepen our understanding of ChatGPT and its interactions with human input.

The acceptability, usability, engagement and optimisation of a mHealth service promoting healthy lifestyle behaviours: A mixed method feasibility study

Objective

Mobile health (mHealth) services suffer from high attrition rates yet represent a viable strategy for adults to improve their health. There is a need to develop evidence-based mHealth services and to constantly evaluate their feasibility. This study explored the acceptability, usability, engagement and optimisation of a co-developed mHealth service, aiming to promote healthy lifestyle behaviours.

Methods

The service LongLife Active® (LLA) is a mobile app with coaching. Adults were recruited from the general population. Quantitative results and qualitative findings guided the reasoning for the acceptability, usability, engagement and optimisation of LLA. Data from: questionnaires, log data, eight semi-structured interviews with users, feedback comments from users and two focus groups with product developers and coaches were collected. Inductive content analysis was used to analyse the qualitative data. A mixed method approach was used to interpret the findings.

Results

The final sample was 55 users (82% female), who signed up to use the service for 12 weeks. Engagement data was available for 43 (78%). The action plan was the most popular function engaged with by users. The mean scores for acceptability and usability were 3.3/5.0 and 50/100, respectively, rated by 15 users. Users expressed that the service's health focus was unique, and the service gave them a 'kickstart' in their behaviour change. Many ways to optimise the service were identified, including to increase personalisation, promote motivation and improve usability.

Conclusion

By incorporating suggestions for optimisation, this service has the potential to support peoples' healthy lifestyle behaviours.

The Use of Wearable Devices to Measure Sedentary Behavior during COVID-19: Systematic Review and Future Recommendations

The SARS-CoV-2 pandemic resulted in approximately 7 million deaths and impacted 767 million individuals globally, primarily through infections. Acknowledging the impactful influence of sedentary behaviors, particularly exacerbated by COVID-19 restrictions, a substantial body of research has emerged, utilizing wearable sensor technologies to assess these behaviors. This comprehensive review aims to establish a framework encompassing recent studies concerning wearable sensor applications to measure sedentary behavior parameters during the COVID-19 pandemic, spanning December 2019 to December 2022. After examining 582 articles, 7 were selected for inclusion. While most studies displayed effective reporting standards and adept use of wearable device data for their specific research aims, our inquiry revealed deficiencies in apparatus accuracy documentation and study methodology harmonization. Despite methodological variations, diverse metrics, and the absence of thorough device accuracy assessments, integrating wearables within the pandemic context offers a promising avenue for objective measurements and strategies against sedentary behaviors.

A scoping review of 'Pacing' for management of Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS): lessons learned for the long COVID pandemic

BACKGROUND

Controversy over treatment for people with myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a barrier to appropriate treatment. Energy management or pacing is a prominent coping strategy for people with ME/CFS. Whilst a definitive definition of pacing is not unanimous within the literature or healthcare providers, it typically comprises regulating activity to avoid post exertional malaise (PEM), the worsening of symptoms after an activity. Until now, characteristics of pacing, and the effects on patients' symptoms had not been systematically reviewed. This is problematic as the most common approach to pacing, pacing prescription, and the pooled efficacy of pacing was unknown. Collating evidence may help advise those suffering with similar symptoms, including long COVID, as practitioners would be better informed on methodological approaches to adopt, pacing implementation, and expected outcomes.

OBJECTIVES

In this scoping review of the literature, we aggregated type of, and outcomes of, pacing in people with ME/CFS.

ELIGIBILITY CRITERIA

Original investigations concerning pacing were considered in participants with ME/CFS.

SOURCES OF EVIDENCE

Six electronic databases (PubMed, Scholar, ScienceDirect, Scopus, Web of Science and the Cochrane Central Register of Controlled Trials [CENTRAL]) were searched; and websites MEPedia, Action for ME, and ME Action were also searched for grey literature, to fully capture patient surveys not published in academic journals.

METHODS

A scoping review was conducted. Review selection and characterisation was performed by two independent reviewers using pretested forms.

RESULTS

Authors reviewed 177 titles and abstracts, resulting in 17 included studies: three randomised control trials (RCTs); one uncontrolled trial; one interventional case series; one retrospective observational study; two prospective observational studies; four cross-sectional observational studies; and five cross-sectional analytical studies. Studies included variable designs, durations, and outcome measures. In terms of pacing administration, studies used educational sessions and diaries for activity monitoring. Eleven studies reported benefits of pacing, four studies reported no effect, and two studies reported a detrimental effect in comparison to the control group.

CONCLUSIONS

Highly variable study designs and outcome measures, allied to poor to fair methodological quality resulted in heterogenous findings and highlights the requirement for more research examining pacing. Looking to the long COVID pandemic, our results suggest future studies should be RCTs utilising objectively quantified digitised pacing, over a longer duration of examination (i.e. longitudinal studies), using the core outcome set for patient reported outcome measures. Until these are completed, the literature base is insufficient to inform treatment practises for people with ME/CFS and long COVID.

Designing personalised mHealth solutions: An overview

INTRODUCTION

Mobile health, or mHealth, is based on mobile information and communication technologies and provides solutions for empowering individuals to participate in healthcare. Personalisation techniques have been used to increase user engagement and adherence to interventions delivered as mHealth solutions. This study aims to explore the current state of personalisation in mHealth, including its current trends and implementation.

MATERIALS AND METHODS

We conducted a review following PRISMA guidelines. Four databases (PubMed, ACM Digital Library, IEEE Xplore, and APA PsycInfo) were searched for studies on mHealth solutions that integrate personalisation. The retrieved papers were assessed for eligibility and useful information regarding integrated personalisation techniques.

RESULTS

Out of the 1,139 retrieved studies, 62 were included in the narrative synthesis. Research interest in the personalisation of mHealth solutions has increased since 2020. mHealth solutions were mainly applied to endocrine, nutritional, and metabolic diseases; mental, behavioural, or neurodevelopmental diseases; or the promotion of healthy lifestyle behaviours. Its main purposes are to support disease self-management and promote healthy lifestyle behaviours. Mobile applications are the most prevalent technological solution. Although several design models, such as user-centred and patient-centred designs, were used, no specific frameworks or models for personalisation were followed. These solutions rely on behaviour change theories, use gamification or motivational messages, and personalise the content rather than functionality. A broad range of data is used for personalisation purposes. There is a lack of studies assessing the efficacy of these solutions; therefore, further evidence is needed.

DISCUSSION

Personalisation in mHealth has not been well researched. Although several techniques have been integrated, the effects of using a combination of personalisation techniques remain unclear. Although personalisation is considered a persuasive strategy, many mHealth solutions do not employ it.

CONCLUSIONS

Open research questions concern guidelines for successful personalisation techniques in mHealth, design frameworks, and comprehensive studies on the effects and interactions among multiple personalisation techniques.

Digital Therapeutics (DTx) Expand Multimodal Treatment Options for Chronic Low Back Pain: The Nexus of Precision Medicine, Patient Education, and Public Health

Digital therapeutics (DTx, software as a medical device) provide personalized treatments for chronic diseases and expand precision medicine beyond pharmacogenomics-based pharmacotherapies. In this perspective article, we describe how DTx for chronic low back pain (CLBP) can be integrated with pharmaceutical drugs (e.g., NSAIDs, opioids), physical therapy (PT), cognitive behavioral therapy (CBT), and patient empowerment. An example of an FDA-authorized DTx for CLBP is RelieVRx, a prescription virtual reality (VR) app that reduces pain severity as an adjunct treatment for moderate to severe low back pain. RelieVRx is an immersive VR system that delivers at-home pain management modalities, including relaxation, self-awareness, pain distraction, guided breathing, and patient education. The mechanism of action of DTx is aligned with recommendations from the American College of Physicians to use non-pharmacological modalities as the first-line therapy for CLBP. Herein, we discuss how DTx can provide multimodal therapy options integrating conventional treatments with exposome-responsive, just-in-time adaptive interventions (JITAI). Given the flexibility of software-based therapies to accommodate diverse digital content, we also suggest that music-induced analgesia can increase the clinical effectiveness of digital interventions for chronic pain. DTx offers opportunities to simultaneously address the chronic pain crisis and opioid epidemic while supporting patients and healthcare providers to improve therapy outcomes.

Put your money where your feet are: The real-world effects of StepBet gamified deposit contracts for physical activity

Background

Gamification and deposit contracts (a financial incentive in which participants pledge their own money) can enhance effectiveness of mobile behavior change interventions. However, to assess their potential for improving population health, research should investigate implementation of gamified deposit contracts outside the research setting. Therefore, we analyzed data from StepBet, a smartphone application originally developed by WayBetter, Inc.

Objective

To perform a naturalistic evaluation of StepBet gamified deposit contracts, for whom they work best, and under which conditions they are most effective to help increase physical activity.

Methods

WayBetter provided data of StepBet participants that participated in a stepcount challenge between 2015 and 2020 (N = 72,974). StepBet challenges were offered on the StepBet smartphone application. The modal challenge consisted of a $40 deposit made prior to a 6-week challenge period during which participants needed to reach daily and weekly step goals in order to regain their deposit. Participants who met their goals also received additional earnings which were paid out from the money lost by those who failed their challenge. Challenge step goals were tailored on a 90-day historic step count retrieval that was also used as the baseline comparison for this study. Primary outcomes were increase in step count (continuous) and challenge success (dichotomous).

Results

Overall, average daily step counts increased by 31.2 % (2423 steps, SD = 3462) from 7774 steps (SD = 3112) at baseline to 10,197 steps (SD = 4162) during the challenge. The average challenge success rate was 73 %. Those who succeeded in their challenge (n = 53,281) increased their step count by 44.0 % (3465 steps, SD = 3013), while those who failed their challenge (n = 19,693) decreased their step count by -5.3 % (-398 steps, SD = 3013). Challenges started as a New Year's resolution were slightly more successful (77.7 %) than those started during the rest of the year (72.6 %).

Discussion

In a real-world setting, and among a large and diverse sample, participating in a gamified deposit contract challenge was associated with a large increase in step counts. A majority of challenges were successful and succeeding in a challenge was associated with a large and clinically relevant increase in step counts. Based on these findings, we recommend implementing gamified deposit contracts for physical activity where possible. An interesting avenue for future research is to explore possible setback effects among people who fail a challenge, and how setbacks can be mitigated.

Pre-registration

Open Science Framework (doi:10.17605/OSF.IO/D237C).

Development and Validation of Multivariable Prediction Algorithms to Estimate Future Walking Behavior in Adults: Retrospective Cohort Study

BACKGROUND

Physical inactivity is associated with numerous health risks, including cancer, cardiovascular disease, type 2 diabetes, increased health care expenditure, and preventable, premature deaths. The majority of Americans fall short of clinical guideline goals (ie, 8000-10,000 steps per day). Behavior prediction algorithms could enable efficacious interventions to promote physical activity by facilitating delivery of nudges at appropriate times.

OBJECTIVE

The aim of this paper is to develop and validate algorithms that predict walking (ie, >5 min) within the next 3 hours, predicted from the participants' previous 5 weeks' steps-per-minute data.

METHODS

We conducted a retrospective, closed cohort, secondary analysis of a 6-week microrandomized trial of the HeartSteps mobile health physical-activity intervention conducted in 2015. The prediction performance of 6 algorithms was evaluated, as follows: logistic regression, radial-basis function support vector machine, eXtreme Gradient Boosting (XGBoost), multilayered perceptron (MLP), decision tree, and random forest. For the MLP, 90 random layer architectures were tested for optimization. Prior 5-week hourly walking data, including missingness, were used for predictors. Whether the participant walked during the next 3 hours was used as the outcome. K-fold cross-validation (K=10) was used for the internal validation. The primary outcome measures are classification accuracy, the Mathew correlation coefficient, sensitivity, and specificity.

RESULTS

The total sample size included 6 weeks of data among 44 participants. Of the 44 participants, 31 (71%) were female, 26 (59%) were White, 36 (82%) had a college degree or more, and 15 (34%) were married. The mean age was 35.9 (SD 14.7) years. Participants (n=3, 7%) who did not have enough data (number of days <10) were excluded, resulting in 41 (93%) participants. MLP with optimized layer architecture showed the best performance in accuracy (82.0%, SD 1.1), whereas XGBoost (76.3%, SD 1.5), random forest (69.5%, SD 1.0), support vector machine (69.3%, SD 1.0), and decision tree (63.6%, SD 1.5) algorithms showed lower performance than logistic regression (77.2%, SD 1.2). MLP also showed superior overall performance to all other tried algorithms in Mathew correlation coefficient (0.643, SD 0.021), sensitivity (86.1%, SD 3.0), and specificity (77.8%, SD 3.3).

CONCLUSIONS

Walking behavior prediction models were developed and validated. MLP showed the highest overall performance of all attempted algorithms. A random search for optimal layer structure is a promising approach for prediction engine development. Future studies can test the real-world application of this algorithm in a "smart" intervention for promoting physical activity.

Older adults as designers of behavior change strategies to increase physical activity-Report of a participatory design process

Background

Despite the significant value of physical activity for the health of older adults, this population often fails to achieve recommended activity levels. Digital interventions show promise in providing support for self-managed physical activity. However, more information is needed about older adults' preferences for digital support to change physical activity behaviors as well as the process of designing them. The aim of this paper was to describe the participatory design process in which older adults were involved in the co-creation of digitally supported behavioral change strategies to support self-managed physical activity, and how the results were integrated in a prototype.

Methods

The participatory design process involved with nine older adults and two researchers. The participants were divided in two groups, and each group participated in three workshops and completed home tasks in between workshops. Following an iterative design process influenced by theories of behavior change, the workshops and home tasks were continuously analyzed, and the content and process were developed between groups and the next set of workshops. Prototypes of a mobile health (mHealth) solution for fall preventive exercise for older adults were developed in which the conceptualized strategies were integrated. To support coherence in reporting and evaluation, the developed techniques were mapped to the Behavior Change Technique Taxonomy v1 and the basic human psychosocial needs according to the Self-determination Theory.

Results

The results highlight different preferences of older adults for feedback on physical activity performance, as well as the importance of transparency regarding the identification of the sender of feedback. Preferences for content and wording of feedback varied greatly. Subsequently, the design process resulted in a virtual health coach with three different motivational profiles and tools for goal setting and self-monitoring. These behavior change strategies were integrated in the exercise application Safe Step v1. The conformity of the design concepts with the needs of Self-determination Theory and Behavior Change Technique Taxonomy v1 are presented.

Conclusion

The participatory design process exemplifies how older adults successfully contributed to the design of theory-based digital behavior change support, from idea to finished solution. Tailoring feedback with a transparent sender is important to support and not undermine motivation.