Optimizing a mobile just-in-time adaptive intervention (JITAI) for weight loss in young adults: Rationale and design of the AGILE factorial randomized trial

BACKGROUND

Young adults (YAs) are underrepresented in behavioral health and weight loss interventions and express interest in flexible, highly tailored programs. Mobile interventions are a lower-burden, scalable approach to providing behavioral support. Just-in-time-adaptive interventions (JITAI) promise to deliver the "right" support at the "right" time using real-time data from smartphones and sensors. JITAIs hold promise for promoting behavior changes needed for weight loss (dietary intake, activity, and self-weighing); however, there is limited evidence for selecting treatment components and levels of adaptation that are needed for success.

METHODS

The AGILE (Adaptive Goals and Interventions for Lifestyle Enhancement) trial utilizes the Multiphase Optimization Strategy (MOST) framework and a 25 full factorial experimental trial to test the efficacy of 5 intervention components, each with two levels, on weight loss among 608 YAs recruited from around the United States. All participants will receive a core 6-month weight loss intervention that includes evidence-based lessons, behavioral skills training, and daily weighing. With the goal of determining if greater adaptation leads to greater weight loss, we will test standard versus adaptive options of 5 additional intervention components: 1) diet monitoring approach (standard vs. simplified), 2) adaptive physical activity goals (weekly vs. daily), 3) decision points for message timing (fixed vs. adaptive), 4) decision rules for message content (standard vs. adaptive), and 5) message choice (no vs. yes). Assessments will occur at baseline, 3 months, and 6 months.

CONCLUSIONS

Results of this trial will be used to create an optimized JITAI for weight loss in young adults.

A Scoping Review of Artificial Intelligence for Precision Nutrition

BACKGROUND

With the role of artificial intelligence (AI) in precision nutrition rapidly expanding, a scoping review on recent studies and potential future directions is demanded.

OBJECTIVE

This scoping review examines: (1) the current landscape, including publication venues, targeted diseases, AI applications, methods, evaluation metrics, and considerations of minority and cultural factors; (2) common patterns in AI-driven precision nutrition studies; and (3) gaps, challenges and future research directions.

METHODS

Following the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) process, we extracted 198 articles from major databases with search keywords in three categories: precision nutrition keywords, artificial intelligence keywords and natural language processing keywords.

RESULTS

The extracted literature reveals a surge in AI-driven precision nutrition research, with ∼75% (n=148) published since 2020. It also showcases a diverse publication landscape, with these studies predominantly focusing on diet-related diseases, such as diabetes and cardiovascular conditions, while emphasizing health optimization, disease prevention, and management. We highlight diverse datasets and critically discuss methodologies and evaluation metrics to guide future studies. Importantly, we underscore the significance of minority and cultural aspects in enhancing health technologies and advancing equity. Future research should deepen the integration of these factors to fully harness AI's potential in precision nutrition.

STATEMENT OF SIGNIFICANCE

This scoping review offers the most recent advancements in artificial intelligence for precision nutrition studies, expanding the scope to not only AI methodologies and their applications but also evaluates publication venues, targeted disease, datasets used and minority and cultural factors, which have been mostly overlooked in prior studies. Furthermore, with numerous gaps and challenges presented in the discussion section, this review significantly improves the understanding of AI's role in precision nutrition and provides new insights for future research.

Personalized interventions for behaviour change: A scoping review of just-in-time adaptive interventions

PURPOSE

Examine the development, implementation and evaluation of just-in-time adaptive interventions (JITAIs) in behaviour change and evaluate the quality of intervention reporting.

METHODS

A scoping review of JITAIs incorporating mobile health (mHealth) technologies to improve health-related behaviours in adults. We searched MEDLINE, Embase and PsycINFO using terms related to JITAIs, mHealth, behaviour change and intervention methodology. Narrative analysis assessed theoretical foundations, real-time data capturing and processing methods, outcome evaluation and summarized JITAI efficacy. Quality of intervention reporting was assessed using the template for intervention description and replication (TIDieR) checklist.

RESULTS

Sixty-two JITAIs across physical activity, sedentary behaviour, dietary behaviour, substance use, sexual behaviour, fluid intake, treatment adherence, social skills, gambling behaviour and self-management skills were included. The majority (71%) aimed to evaluate feasibility, acceptability and/or usability. Supporting evidence for JITAI development was identified in 46 studies, with 67% applying this to develop tailored intervention content. Over half (55%) relied solely on self-reported data for tailoring, and 13 studies used only passive monitoring data. While data processing methods were commonly reported, 44% did not specify their techniques. 89% of JITAI designs achieved full marks on the TIDieR checklist and provided sufficient details on JITAI components. Overall, JITAIs proved to be feasible, acceptable and user-friendly across behaviours and settings. Randomized trials showed tailored interventions were efficacious, though outcomes varied by behaviour.

CONCLUSIONS

JITAIs offer a promising approach to developing personalized interventions, with their potential effects continuously growing. The recommended checklist emphasizes the importance of reporting transparency in establishing robust intervention designs.

The recent history and near future of digital health in the field of behavioral medicine: an update on progress from 2019 to 2024

The field of behavioral medicine has a long and successful history of leveraging digital health tools to promote health behavior change. Our 2019 summary of the history and future of digital health in behavioral medicine (Arigo in J Behav Med 8: 67-83, 2019) was one of the most highly cited articles in the Journal of Behavioral Medicine from 2010 to 2020; here, we provide an update on the opportunities and challenges we identified in 2019. We address the impact of the COVID-19 pandemic on behavioral medicine research and practice and highlight some of the digital health advances it prompted. We also describe emerging challenges and opportunities in the evolving ecosystem of digital health in the field of behavioral medicine, including the emergence of new evidence, research methods, and tools to promote health and health behaviors. Specifically, we offer updates on advanced research methods, the science of digital engagement, dissemination and implementation science, and artificial intelligence technologies, including examples of uses in healthcare and behavioral medicine. We also provide recommendations for next steps in these areas with attention to ethics, training, and accessibility considerations. The field of behavioral medicine has made meaningful advances since 2019 and continues to evolve with impressive pace and innovation.

User Engagement With mHealth Interventions to Promote Treatment Adherence and Self-Management in People With Chronic Health Conditions: Systematic Review

BACKGROUND

There are numerous mobile health (mHealth) interventions for treatment adherence and self-management; yet, little is known about user engagement or interaction with these technologies.

OBJECTIVE

This systematic review aimed to answer the following questions: (1) How is user engagement defined and measured in studies of mHealth interventions to promote adherence to prescribed medical or health regimens or self-management among people living with a health condition? (2) To what degree are patients engaging with these mHealth interventions? (3) What is the association between user engagement with mHealth interventions and adherence or self-management outcomes? (4) How often is user engagement a research end point?

METHODS

Scientific database (Ovid MEDLINE, Embase, Web of Science, PsycINFO, and CINAHL) search results (2016-2021) were screened for inclusion and exclusion criteria. Data were extracted in a standardized electronic form. No risk-of-bias assessment was conducted because this review aimed to characterize user engagement measurement rather than certainty in primary study results. The results were synthesized descriptively and thematically.

RESULTS

A total of 292 studies were included for data extraction. The median number of participants per study was 77 (IQR 34-164). Most of the mHealth interventions were evaluated in nonrandomized studies (157/292, 53.8%), involved people with diabetes (51/292, 17.5%), targeted medication adherence (98/292, 33.6%), and comprised apps (220/292, 75.3%). The principal findings were as follows: (1) >60 unique terms were used to define user engagement; "use" (102/292, 34.9%) and "engagement" (94/292, 32.2%) were the most common; (2) a total of 11 distinct user engagement measurement approaches were identified; the use of objective user log-in data from an app or web portal (160/292, 54.8%) was the most common; (3) although engagement was inconsistently evaluated, most of the studies (99/195, 50.8%) reported >1 level of engagement due to the use of multiple measurement methods or analyses, decreased engagement across time (76/99, 77%), and results and conclusions suggesting that higher engagement was associated with positive adherence or self-management (60/103, 58.3%); and (4) user engagement was a research end point in only 19.2% (56/292) of the studies.

CONCLUSIONS

The results revealed major limitations in the literature reviewed, including significant variability in how user engagement is defined, a tendency to rely on user log-in data over other measurements, and critical gaps in how user engagement is evaluated (infrequently evaluated over time or in relation to adherence or self-management outcomes and rarely considered a research end point). Recommendations are outlined in response to our findings with the goal of improving research rigor in this area.

TRIAL REGISTRATION

PROSPERO International Prospective Register of Systematic Reviews CRD42022289693; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022289693.

A naturalistic examination of feeling fat: Characteristics, predictors, and the relationship with eating disorder behaviors

OBJECTIVE

Although literature implicates feeling fat in the maintenance of binge-spectrum eating disorders (EDs; e.g., bulimia nervosa, binge-ED), research in this area is small, nascent, and relies on retrospective self-report. The current study sought to understand the temporal pattern of feeling fat and its role as a precipitant and consequence of ED behaviors.

METHODS

Totally 106 treatment-seeking adults with binge-spectrum EDs completed 7-14-day ecological momentary assessments. They rated feeling fat, negative affect states, and reported on ED behaviors six times per day. Multilevel models evaluated whether feeling fat mediates prospective links between negative affect states and ED behaviors, assessed if negative affect states mediate the prospective association of feeling fat on ED behaviors, and examined the bidirectional prospective association between feeling fat and ED behaviors.

RESULTS

Feeling fat was highest in the early morning (6-8:59 a.m.). Individuals with binge-ED-spectrum EDs demonstrated greater variability in feeling fat than those with bulimia nervosa-spectrum EDs who had stable and high levels of feeling fat. Guilt, sadness, anxiety, and the overall NA at Time 2 mediated the prospective associations between at Time 1 feeling fat and Time 3 dietary restraint, actual dietary restriction, and compensatory exercise. There was a bidirectional prospective association between feeling fat and binge eating.

DISCUSSION

Feeling fat serves as a proximal predictor and mediator of the prospective association between guilt and binge eating. Feeling fat and binge eating mutually reinforce each other.

PUBLIC SIGNIFICANCE

Little is understood regarding the experience of feeling fat in natural environments among individuals with binge-spectrum eating disorders. We found that the risk for having the experience of feeling fat is high in the morning and evening. Feeling fat triggers guilt, anxiety, and sadness which in turn, increases engagement in dietary restraint/restriction and compensatory exercise. Feeling fat also triggers binge eating, and binge eating leads to feelings of fatness.

Supervised machine learning to predict smoking lapses from Ecological Momentary Assessments and sensor data: Implications for just-in-time adaptive intervention development

Specific moments of lapse among smokers attempting to quit often lead to full relapse, which highlights a need for interventions that target lapses before they might occur, such as just-in-time adaptive interventions (JITAIs). To inform the decision points and tailoring variables of a lapse prevention JITAI, we trained and tested supervised machine learning algorithms that use Ecological Momentary Assessments (EMAs) and wearable sensor data of potential lapse triggers and lapse incidence. We aimed to identify a best-performing and feasible algorithm to take forwards in a JITAI. For 10 days, adult smokers attempting to quit were asked to complete 16 hourly EMAs/day assessing cravings, mood, activity, social context, physical context, and lapse incidence, and to wear a Fitbit Charge 4 during waking hours to passively collect data on steps and heart rate. A series of group-level supervised machine learning algorithms (e.g., Random Forest, XGBoost) were trained and tested, without and with the sensor data. Their ability to predict lapses for out-of-sample (i) observations and (ii) individuals were evaluated. Next, a series of individual-level and hybrid (i.e., group- and individual-level) algorithms were trained and tested. Participants (N = 38) responded to 6,124 EMAs (with 6.9% of responses reporting a lapse). Without sensor data, the best-performing group-level algorithm had an area under the receiver operating characteristic curve (AUC) of 0.899 (95% CI = 0.871-0.928). Its ability to classify lapses for out-of-sample individuals ranged from poor to excellent (AUCper person = 0.524-0.994; median AUC = 0.639). 15/38 participants had adequate data for individual-level algorithms to be constructed, with a median AUC of 0.855 (range: 0.451-1.000). Hybrid algorithms could be constructed for 25/38 participants, with a median AUC of 0.692 (range: 0.523 to 0.998). With sensor data, the best-performing group-level algorithm had an AUC of 0.952 (95% CI = 0.933-0.970). Its ability to classify lapses for out-of-sample individuals ranged from poor to excellent (AUCper person = 0.494-0.979; median AUC = 0.745). 11/30 participants had adequate data for individual-level algorithms to be constructed, with a median AUC of 0.983 (range: 0.549-1.000). Hybrid algorithms could be constructed for 20/30 participants, with a median AUC of 0.772 (range: 0.444 to 0.968). In conclusion, high-performing group-level lapse prediction algorithms without and with sensor data had variable performance when applied to out-of-sample individuals. Individual-level and hybrid algorithms could be constructed for a limited number of individuals but had improved performance, particularly when incorporating sensor data for participants with sufficient wear time. Feasibility constraints and the need to balance multiple success criteria in the JITAI development and implementation process are discussed.

Person-specific and pooled prediction models for binge eating, alcohol use and binge drinking in bulimia nervosa and alcohol use disorder

BACKGROUND

Machine learning could predict binge behavior and help develop treatments for bulimia nervosa (BN) and alcohol use disorder (AUD). Therefore, this study evaluates person-specific and pooled prediction models for binge eating (BE), alcohol use, and binge drinking (BD) in daily life, and identifies the most important predictors.

METHODS

A total of 120 patients (BN: 50; AUD: 51; BN/AUD: 19) participated in an experience sampling study, where over a period of 12 months they reported on their eating and drinking behaviors as well as on several other emotional, behavioral, and contextual factors in daily life. The study had a burst-measurement design, where assessments occurred eight times a day on Thursdays, Fridays, and Saturdays in seven bursts of three weeks. Afterwards, person-specific and pooled models were fit with elastic net regularized regression and evaluated with cross-validation. From these models, the variables with the 10% highest estimates were identified.

RESULTS

The person-specific models had a median AUC of 0.61, 0.80, and 0.85 for BE, alcohol use, and BD respectively, while the pooled models had a median AUC of 0.70, 0.90, and 0.93. The most important predictors across the behaviors were craving and time of day. However, predictors concerning social context and affect differed among BE, alcohol use, and BD.

CONCLUSIONS

Pooled models outperformed person-specific models and the models for alcohol use and BD outperformed those for BE. Future studies should explore how the performance of these models can be improved and how they can be used to deliver interventions in daily life.

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.

Effectiveness of an Artificial Intelligence-Assisted App for Improving Eating Behaviors: Mixed Methods Evaluation

BACKGROUND

A plethora of weight management apps are available, but many individuals, especially those living with overweight and obesity, still struggle to achieve adequate weight loss. An emerging area in weight management is the support for one's self-regulation over momentary eating impulses.

OBJECTIVE

This study aims to examine the feasibility and effectiveness of a novel artificial intelligence-assisted weight management app in improving eating behaviors in a Southeast Asian cohort.

METHODS

A single-group pretest-posttest study was conducted. Participants completed the 1-week run-in period of a 12-week app-based weight management program called the Eating Trigger-Response Inhibition Program (eTRIP). This self-monitoring system was built upon 3 main components, namely, (1) chatbot-based check-ins on eating lapse triggers, (2) food-based computer vision image recognition (system built based on local food items), and (3) automated time-based nudges and meal stopwatch. At every mealtime, participants were prompted to take a picture of their food items, which were identified by a computer vision image recognition technology, thereby triggering a set of chatbot-initiated questions on eating triggers such as who the users were eating with. Paired 2-sided t tests were used to compare the differences in the psychobehavioral constructs before and after the 7-day program, including overeating habits, snacking habits, consideration of future consequences, self-regulation of eating behaviors, anxiety, depression, and physical activity. Qualitative feedback were analyzed by content analysis according to 4 steps, namely, decontextualization, recontextualization, categorization, and compilation.

RESULTS

The mean age, self-reported BMI, and waist circumference of the participants were 31.25 (SD 9.98) years, 28.86 (SD 7.02) kg/m2, and 92.60 (SD 18.24) cm, respectively. There were significant improvements in all the 7 psychobehavioral constructs, except for anxiety. After adjusting for multiple comparisons, statistically significant improvements were found for overeating habits (mean -0.32, SD 1.16; P<.001), snacking habits (mean -0.22, SD 1.12; P<.002), self-regulation of eating behavior (mean 0.08, SD 0.49; P=.007), depression (mean -0.12, SD 0.74; P=.007), and physical activity (mean 1288.60, SD 3055.20 metabolic equivalent task-min/day; P<.001). Forty-one participants reported skipping at least 1 meal (ie, breakfast, lunch, or dinner), summing to 578 (67.1%) of the 862 meals skipped. Of the 230 participants, 80 (34.8%) provided textual feedback that indicated satisfactory user experience with eTRIP. Four themes emerged, namely, (1) becoming more mindful of self-monitoring, (2) personalized reminders with prompts and chatbot, (3) food logging with image recognition, and (4) engaging with a simple, easy, and appealing user interface. The attrition rate was 8.4% (21/251).

CONCLUSIONS

eTRIP is a feasible and effective weight management program to be tested in a larger population for its effectiveness and sustainability as a personalized weight management program for people with overweight and obesity.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04833803; https://classic.clinicaltrials.gov/ct2/show/NCT04833803.

MyTrack+: Human-centered design of an mHealth app to support long-term weight loss maintenance

A growing body of research has focused on the utility of adaptive intervention models for promoting long-term weight loss maintenance; however, evaluation of these interventions often requires customized smartphone applications. Building such an app from scratch can be resource-intensive. To support a novel clinical trial of an adaptive intervention for weight loss maintenance, we developed a companion app, MyTrack+, to pair with a main commercial app, FatSecret (FS), leveraging a user-centered design process for rapid prototyping and reducing software engineering efforts. MyTrack+ seamlessly integrates data from FS and the BodyTrace smart scale, enabling participants to log and self-monitor their health data, while also incorporating customized questionnaires and timestamps to enhance data collection for the trial. We iteratively refined the app by first developing initial mockups and incorporating feedback from a usability study with 17 university students. We further improved the app based on an in-the-wild pilot study with 33 participants in the target population, emphasizing acceptance, simplicity, customization options, and dual app usage. Our work highlights the potential of using an iterative human-centered design process to build a companion app that complements a commercial app for rapid prototyping, reducing costs, and enabling efficient research progress.

Experiences of emotional eating in an Acceptance and Commitment Therapy based weight management intervention (SWiM): A qualitative study

BACKGROUND

Emotional eating is a barrier to weight management. Interventions based on Acceptance and Commitment Therapy (ACT) promote the acceptance of uncomfortable feelings, which can reduce the urge to use food as a coping mechanism. We aimed to explore how participants of an ACT-based weight management intervention (WMI) experience emotional eating and relevant intervention content.

METHODS

We conducted semi-structured telephone interviews with participants of a digital ACT-based guided self-help WMI. Fifteen participants were purposefully selected to represent a range of demographic characteristics and emotional eating scores. We used reflexive thematic analysis to explore experiences of emotional eating.

RESULTS

We generated five themes. Participants improved emotional eating by disconnecting emotions from behaviours though increased self-awareness (theme 1) and by implementing alternative coping strategies, including preparation, substitution, and acceptance (theme 2). Most participants maintained improvements in emotional eating over time but wished for more opportunities to re-engage with intervention content, including more immediate support in triggering situations (theme 3). Participants who struggled to engage with emotional eating related intervention content often displayed an external locus of control over emotional eating triggers (theme 4). The perceived usefulness of the intervention depended on participants' prior experiences of emotional eating, and was thought insufficient for participants with complex emotional experiences (theme 5).

DISCUSSION

This ACT-based WMI helped participants with emotional eating by improving self-awareness and teaching alternative coping strategies. Intervention developers may consider adding ongoing forms of intervention that provide both real-time and long-term support. Additionally, a better understanding of how to support people with an external locus of control and people with complex experiences of emotional eating is needed. Future research may explore ways of personalising WMIs based on participants' emotional needs.

Predicting high-risk periods for weight regain following initial weight loss

OBJECTIVE

The aim of this study was to develop a predictive algorithm of "high-risk" periods for weight regain after weight loss.

METHODS

Longitudinal mixed-effects models and random forest regression were used to select predictors and develop an algorithm to predict weight regain on a week-to-week basis, using weekly questionnaire and self-monitoring data (including daily e-scale data) collected over 40 weeks from 46 adults who lost ≥5% of baseline weight during an initial 12-week intervention (Study 1). The algorithm was evaluated in 22 adults who completed the same Study 1 intervention but lost <5% of baseline weight and in 30 adults recruited for a separate 30-week study (Study 2).

RESULTS

The final algorithm retained the frequency of self-monitoring caloric intake and weight plus self-report ratings of hunger and the importance of weight-management goals compared with competing life demands. In the initial training data set, the algorithm predicted weight regain the following week with a sensitivity of 75.6% and a specificity of 45.8%; performance was similar (sensitivity: 81%-82%, specificity: 30%-33%) in testing data sets.

CONCLUSIONS

Weight regain can be predicted on a proximal, week-to-week level. Future work should investigate the clinical utility of adaptive interventions for weight-loss maintenance and develop more sophisticated predictive models of weight regain.

The Effectiveness of Strategies to Improve User Engagement With Digital Health Interventions Targeting Nutrition, Physical Activity, and Overweight and Obesity: Systematic Review and Meta-Analysis

BACKGROUND

Digital health interventions (DHIs) are effective in improving poor nutrition, physical inactivity, overweight and obesity. There is evidence suggesting that the impact of DHIs may be enhanced by improving user engagement. However, little is known about the overall effectiveness of strategies on engagement with DHIs.

OBJECTIVE

This study aims to assess the overall effectiveness of strategies to improve engagement with DHIs targeting nutrition, physical activity, and overweight or obesity and explore associations between strategies and engagement outcomes. The secondary aim was to explore the impact of these strategies on health risk outcomes.

METHODS

The MEDLINE, Embase, PsycINFO, CINAHL, CENTRAL, Scopus, and Academic Source Complete databases were searched up to July 24, 2023. Eligible studies were randomized controlled trials that evaluated strategies to improve engagement with DHIs and reported on outcomes related to DHI engagement (use or user experience). Strategies were classified according to behavior change techniques (BCTs) and design features (eg, supplementary emails). Multiple-variable meta-analyses of the primary outcomes (usage and user experience) were undertaken to assess the overall effectiveness of strategies. Meta-regressions were conducted to assess associations between strategies and use and user experience outcomes. Synthesis of secondary outcomes followed the "Synthesis Without Meta-Analysis" guidelines. The methodological quality and evidence was assessed using the Cochrane risk-of-bias tool, and the Grading of Recommendations Assessment, Development, and Evaluation tool respectively.

RESULTS

Overall, 54 studies (across 62 publications) were included. Pooled analysis found very low-certainty evidence of a small-to-moderate positive effect of the use of strategies to improve DHI use (standardized mean difference=0.33, 95% CI 0.20-0.46; P<.001) and very low-certainty evidence of a small-to-moderate positive effect on user experience (standardized mean difference=0.29, 95% CI 0.07-0.52; P=.01). A significant positive association was found between the BCTs social support (effect size [ES]=0.40, 95% CI 0.14-0.66; P<.001) and shaping knowledge (ES=0.39, 95% CI 0.03-0.74; P=.03) and DHI use. A significant positive association was found among the BCTs social support (ES=0.70, 95% CI 0.18-1.22; P=.01), repetition and substitution (ES=0.29, 95% CI 0.05-0.53; P=.03), and natural consequences (ES=0.29, 95% CI 0.05-0.53; P=.02); the design features email (ES=0.29, 95% CI 0.05-0.53; P=.02) and SMS text messages (ES=0.34, 95% CI 0.11-0.57; P=.01); and DHI user experience. For secondary outcomes, 47% (7/15) of nutrition-related, 73% (24/33) of physical activity-related, and 41% (14/34) of overweight- and obesity-related outcomes reported an improvement in health outcomes.

CONCLUSIONS

Although findings suggest that the use of strategies may improve engagement with DHIs targeting such health outcomes, the true effect is unknown because of the low quality of evidence. Future research exploring whether specific forms of social support, repetition and substitution, natural consequences, emails, and SMS text messages have a greater impact on DHI engagement is warranted.

TRIAL REGISTRATION

PROSPERO CRD42018077333; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=77333.

A systematic review of ecological momentary assessment studies of appetite and affect in the experience of temptations and lapses during weight loss dieting

Dietary temptations and lapses challenge control over eating and act as barriers toward successful weight loss. These are difficult to assess in laboratory settings or with retrospective measures as they occur momentarily and driven by the current environment. A better understanding of how these experiences unfold within real-world dieting attempts could help inform strategies to increase the capacity to cope with the changes in appetitive and affective factors that surround these experiences. We performed a narrative synthesis on the empirical evidence of appetitive and affective outcomes measured using ecological momentary assessment (EMA) during dieting in individuals with obesity and their association with dietary temptations and lapses. A search of three databases (Scopus, Medline, and PsycInfo) identified 10 studies. Within-person changes in appetite and affect accompany temptations and lapses and are observable in the moments precipitating a lapse. Lapsing in response to these may be mediated through the strength of a temptation. Negative abstinence-violation effects occur following a lapse, which negatively impact self-attitudes. Engagement in coping strategies during temptations is effective for preventing lapses. These findings indicate that monitoring changes in sensations during dieting could help identify the crucial moments when coping strategies are most effective for aiding with dietary adherence.

Application of machine learning to discover interactions predictive of dietary lapses

The purpose of this study it to build a machine learning model to predict dietary lapses with comparable accuracy, sensitivity, and specificity to previous literature while recovering predictor interactions. The sample for the current study consisted of merged data from two separate studies of individuals with obesity/overweight (total N = 87). Participants completed six ecological momentary assessment surveys per day where they were asked about 16 risk factors of lapse and if they had lapsed from their dietary prescriptions since the previous survey. Alcohol consumption and self-efficacy were the most prevalent in the top 10 stable interactions. Alcohol consumption decreased the protective effect of self-efficacy, motivation, and planning. Higher planning predicted higher risk for lapse only when consuming alcohol. Low motivation, hunger, cravings, and lack of healthy food availability increased the protective effect of self-efficacy. Higher self-efficacy increased risk effect of positive mood and having recently eaten a meal on lapse. For individuals with lower levels of self-efficacy, planning increased the risk of lapse. Alcohol intake and self-efficacy interact with several variables to predict dietary lapses, and these interactions should be targeted in just-in-time adaptive interventions that deliver interventions for lapses.

Autonomic indices and loss-of-control eating in adolescents: an ecological momentary assessment study

BACKGROUND

Loss-of-control (LOC) eating commonly develops during adolescence, and it predicts full-syndrome eating disorders and excess weight gain. Although negative emotions and emotion dysregulation are hypothesized to precede and predict LOC eating, they are rarely examined outside the self-report domain. Autonomic indices, including heart rate (HR) and heart rate variability (HRV), may provide information about stress and capacity for emotion regulation in response to stress.

METHODS

We studied whether autonomic indices predict LOC eating in real-time in adolescents with LOC eating and body mass index (BMI) ⩾70th percentile. Twenty-four adolescents aged 12-18 (67% female; BMI percentile mean ± standard deviation = 92.6 ± 9.4) who reported at least twice-monthly LOC episodes wore biosensors to monitor HR, HRV, and physical activity for 1 week. They reported their degree of LOC after all eating episodes on a visual analog scale (0-100) using a smartphone.

RESULTS

Adjusting for physical activity and time of day, higher HR and lower HRV predicted higher self-reported LOC after eating. Parsing between- and within-subjects effects, there was a significant, positive, within-subjects association between pre-meal HR and post-meal LOC rating. However, there was no significant within-subjects effect for HRV, nor were there between-subjects effects for either electrophysiologic variable.

CONCLUSIONS

Findings suggest that autonomic indices may either be a marker of risk for subsequent LOC eating or contribute to LOC eating. Linking physiological markers with behavior in the natural environment can improve knowledge of illness mechanisms and provide new avenues for intervention.

Predicting Disengagement to Better Support Outcomes in a Web-Based Weight Loss Program Using Machine Learning Models: Cross-Sectional Study

BACKGROUND

Engagement is key to interventions that achieve successful behavior change and improvements in health. There is limited literature on the application of predictive machine learning (ML) models to data from commercially available weight loss programs to predict disengagement. Such data could help participants achieve their goals.

OBJECTIVE

This study aimed to use explainable ML to predict the risk of member disengagement week by week over 12 weeks on a commercially available web-based weight loss program.

METHODS

Data were available from 59,686 adults who participated in the weight loss program between October 2014 and September 2019. Data included year of birth, sex, height, weight, motivation to join the program, use statistics (eg, weight entries, entries into the food diary, views of the menu, and program content), program type, and weight loss. Random forest, extreme gradient boosting, and logistic regression with L1 regularization models were developed and validated using a 10-fold cross-validation approach. In addition, temporal validation was performed on a test cohort of 16,947 members who participated in the program between April 2018 and September 2019, and the remaining data were used for model development. Shapley values were used to identify globally relevant features and explain individual predictions.

RESULTS

The average age of the participants was 49.60 (SD 12.54) years, the average starting BMI was 32.43 (SD 6.19), and 81.46% (39,594/48,604) of the participants were female. The class distributions (active and inactive members) changed from 39,369 and 9235 in week 2 to 31,602 and 17,002 in week 12, respectively. With 10-fold-cross-validation, extreme gradient boosting models had the best predictive performance, which ranged from 0.85 (95% CI 0.84-0.85) to 0.93 (95% CI 0.93-0.93) for area under the receiver operating characteristic curve and from 0.57 (95% CI 0.56-0.58) to 0.95 (95% CI 0.95-0.96) for area under the precision-recall curve (across 12 weeks of the program). They also presented a good calibration. Results obtained with temporal validation ranged from 0.51 to 0.95 for area under a precision-recall curve and 0.84 to 0.93 for area under the receiver operating characteristic curve across the 12 weeks. There was a considerable improvement in area under a precision-recall curve of 20% in week 3 of the program. On the basis of the computed Shapley values, the most important features for predicting disengagement in the following week were those related to the total activity on the platform and entering a weight in the previous weeks.

CONCLUSIONS

This study showed the potential of applying ML predictive algorithms to help predict and understand participants' disengagement with a web-based weight loss program. Given the association between engagement and health outcomes, these findings can prove valuable in providing better support to individuals to enhance their engagement and potentially achieve greater weight loss.

Digital Health Solutions for Weight Loss and Obesity: A Narrative Review

Personal exercise programmes have long been used and prescribed for weight loss and the improvement of quality of life in obese patients. While individualised programmes are usually the preferred option, they can be more costly and challenging to deliver in person. A move to digital programmes with a wider reach has commenced, and demand has increased due to the SARS-CoV-2 pandemic. In this review, we evaluate the current status of digital exercise programme delivery and its evolution over the past decade, with a focus on personalisation. We used specific keywords to search for articles that met our predetermined inclusion and exclusion criteria in order to provide valuable evidence and insights for future research. We identified 55 studies in total in four key areas of focus, from the more recent development of apps and personal digital assistants to web-based programmes and text or phone call interventions. In summary, we observed that apps may be useful for a low-intensity approach and can improve adherence to programmes through self-monitoring, but they are not always developed in an evidence-based manner. Engagement and adherence are important determinants of weight loss and subsequent weight maintenance. Generally, professional support is required to achieve weight loss goals.

Smartphone-supported behavioural weight loss treatment in adults with severe obesity: study protocol for an exploratory randomised controlled trial (SmartBWL)

INTRODUCTION

Behavioural weight loss (BWL) treatment is the standard evidence-based treatment for severe obesity (SO; body mass index ≥40.0 kg/m2 or ≥35.0 kg/m2 with obesity-related comorbidity), leading to moderate weight loss which often cannot be maintained in the long term. Because weight loss depends on patients' use of weight management skills, it is important to support them in daily life. In an ecological momentary intervention design, this clinical trial aims to adapt, refine and evaluate a personalised cognitive-behavioural smartphone application (app) in BWL treatment to foster patients' weight management skills use in everyday life. It is hypothesised that using the app is feasible and acceptable, improves weight loss and increases skills use and well-being.

METHODS AND ANALYSIS

In the pilot phase, the app will be adapted, piloted and optimised for BWL treatment following a participatory patient-oriented approach. In the subsequent single-centre, assessor-blind, exploratory randomised controlled trial, 90 adults with SO will be randomised to BWL treatment over 6 months with versus without adjunctive app. Primary outcome is the amount of weight loss (kg) at post-treatment (6 months), compared with pretreatment, derived from measured body weight. Secondary outcomes encompass feasibility, acceptance, weight management skills use, well-being and anthropometrics assessed at pretreatment, midtreatment (3 months), post-treatment (6 months) and 6-month follow-up (12 months). An intent-to-treat linear model with randomisation arm, pretreatment weight and stratification variables as covariates will serve to compare arms regarding weight at post-treatment. Secondary analyses will include linear mixed models, generalised linear models and regression and mediation analyses. For safety analysis (serious) adverse events will be analysed descriptively.

ETHICS AND DISSEMINATION

The study was approved by the Ethics Committee of the University of Leipzig (DE-21-00013674) and notified to the Federal Institute for Drugs and Medical Devices. Study results will be disseminated through peer-reviewed publications.

REGISTRATION

This study was registered at the German Clinical Trials Register (DRKS00026018), www.drks.de.

TRIAL REGISTRATION NUMBER

DRKS00026018.

Toward Individualized Prediction of Binge-Eating Episodes Based on Ecological Momentary Assessment Data: Item Development and Pilot Study in Patients With Bulimia Nervosa and Binge-Eating Disorder

BACKGROUND

Prevention of binge eating through just-in-time mobile interventions requires the prediction of respective high-risk times, for example, through preceding affective states or associated contexts. However, these factors and states are highly idiographic; thus, prediction models based on averages across individuals often fail.

OBJECTIVE

We developed an idiographic, within-individual binge-eating prediction approach based on ecological momentary assessment (EMA) data.

METHODS

We first derived a novel EMA-item set that covers a broad set of potential idiographic binge-eating antecedents from literature and an eating disorder focus group (n=11). The final EMA-item set (6 prompts per day for 14 days) was assessed in female patients with bulimia nervosa or binge-eating disorder. We used a correlation-based machine learning approach (Best Items Scale that is Cross-validated, Unit-weighted, Informative, and Transparent) to select parsimonious, idiographic item subsets and predict binge-eating occurrence from EMA data (32 items assessing antecedent contextual and affective states and 12 time-derived predictors).

RESULTS

On average 67.3 (SD 13.4; range 43-84) EMA observations were analyzed within participants (n=13). The derived item subsets predicted binge-eating episodes with high accuracy on average (mean area under the curve 0.80, SD 0.15; mean 95% CI 0.63-0.95; mean specificity 0.87, SD 0.08; mean sensitivity 0.79, SD 0.19; mean maximum reliability of rD 0.40, SD 0.13; and mean rCV 0.13, SD 0.31). Across patients, highly heterogeneous predictor sets of varying sizes (mean 7.31, SD 1.49; range 5-9 predictors) were chosen for the respective best prediction models.

CONCLUSIONS

Predicting binge-eating episodes from psychological and contextual states seems feasible and accurate, but the predictor sets are highly idiographic. This has practical implications for mobile health and just-in-time adaptive interventions. Furthermore, current theories around binge eating need to account for this high between-person variability and broaden the scope of potential antecedent factors. Ultimately, a radical shift from purely nomothetic models to idiographic prediction models and theories is required.

[Keyword Network Analysis and Topic Modeling of News Articles Related to Artificial Intelligence and Nursing]

PURPOSE

The purpose of this study was to identify the main keywords, network properties, and main topics of news articles related to artificial intelligence technology in the field of nursing.

METHODS

After collecting artificial intelligence-and nursing-related news articles published between January 1, 1991, and July 24, 2022, keywords were extracted via preprocessing. A total of 3,267 articles were searched, and 2,996 were used for the final analysis. Text network analysis and topic modeling were performed using NetMiner 4.4.

RESULTS

As a result of analyzing the frequency of appearance, the keywords used most frequently were education, medical robot, telecom, dementia, and the older adults living alone. Keyword network analysis revealed the following results: a density of 0.002, an average degree of 8.79, and an average distance of 2.43; the central keywords identified were 'education,' 'medical robot,' and 'fourth industry.' Five topics were derived from news articles related to artificial intelligence and nursing: 'Artificial intelligence nursing research and development in the health and medical field,' 'Education using artificial intelligence for children and youth care,' 'Nursing robot for older adults care,' 'Community care policy and artificial intelligence,' and 'Smart care technology in an aging society.'

CONCLUSION

The use of artificial intelligence may be helpful among the local community, older adult, children, and adolescents. In particular, health management using artificial intelligence is indispensable now that we are facing a super-aging society. In the future, studies on nursing intervention and development of nursing programs using artificial intelligence should be conducted.

Using a complexity science approach to evaluate the effectiveness of just-in-time adaptive interventions: A meta-analysis

Objective

Just-in-time adaptive interventions (JITAIs), which allow individuals to receive the right amount of tailored support at the right time and place, hold enormous potential for promoting behavior change. However, research on JITAIs' implementation and evaluation is still in its early stages, and more empirical evidence is needed. This meta-analysis took a complexity science approach to evaluate the effectiveness of JITAIs that promote healthy behaviors and assess whether key design principles can increase JITAIs' impacts.

Methods

We searched five databases for English-language papers. Study eligibility required that interventions objectively measured health outcomes, had a control condition or pre-post-test design, and were conducted in the real-world setting. We included randomized and non-randomized trials. Data extraction encompassed interventions' features, methodologies, theoretical foundations, and delivery modes. RoB 2 and ROBINS-I were used to assess risk of bias.

Results

The final analysis included 21 effect sizes with 592 participants. All included studies used pre- and post-test design. A three-level random meta-analytic model revealed a medium effect of JITAIs on objective behavior change (g = 0.77 (95% confidence interval (CI); 0.32 to 1.22), p < 0.001). The summary effect was robust to bias. Moderator analysis indicated that design principles, such as theoretical foundations, targeted behaviors, and passive or active assessments, did not moderate JITAIs' effects. Passive assessments were more likely than a combination of passive and active assessments to relate to higher intervention retention rates.

Conclusions

This review demonstrated some evidence for the efficacy of JITAIs. However, high-quality randomized trials and data on non-adherence are needed.

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

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

A feasibility study on the efficacy of a patient-owned wound surveillance system for diabetic foot ulcer care (ePOWS study)

Objective

Wound image analysis tools hold promise in helping patients to monitor their wounds. We aim to perform a novel feasibility study on the efficacy of a patient-owned wound surveillance system for diabetic foot ulcer (DFU) care.

Methods

This two-institutional, prospective, single-arm pilot study examined patients with DFU. An artificial intelligence-enabled image analysis app calculating the wound surface area was installed and patients or caregivers were instructed to take pictures of wounds during dressing changes. Patients were followed until wound deterioration, wound healing, or wound stability at 6 months occurred and the outcomes of interest included study adherence, algorithm performance, and user experience.

Results

Between January 2021 and December 2021, 39 patients were enrolled in the study, with a mean age of 61.6 ± 8.6 years, and 69% (n = 27) of subjects were male. All patients had documented diabetes and 85% (n = 33) of them had peripheral arterial disease. A mean follow-up for those completing the study was 12.0 ± 8.5 weeks. At the conclusion of the study, 80% of patients (n = 20) had primary wound healing whilst 20% (n = 5) had wound deterioration. The study completion rate was 64% (n = 25). Usage of the app for surveillance of DFU healing, as compared to physician evaluation, yielded a sensitivity of 100%, specificity of 20%, positive predictive value of 83%, and negative predictive value of 100%. Of those who provided user experience feedback, 59% (n = 10) felt the app was easy to use, 47% (n = 8) would recommend the wound analysis app to others but only 6% would pay for the app out of pocket (n = 1).

Conclusion

Implementation of a patient-owned wound surveillance system is feasible. Most patients were able to effectively monitor wounds using a smartphone app-based solution. The image analysis algorithm demonstrates strong performance in identifying wound healing and is capable of detecting deterioration prior to interval evaluation by a physician. Patients generally found the app easy to use but were reluctant to pay for the use of the solution out of pocket.

Personal motivation, self-regulation barriers and strategies for weight loss in people with overweight and obesity: a thematic framework analysis

OBJECTIVE

To explore motivations, self-regulation barriers and strategies in a multi-ethnic Southeast Asian population with overweight and obesity.

DESIGN

Qualitative design using semi-structured face-to-face and videoconferencing interviews. Data were analysed using thematic framework analysis and constant comparison method.

SETTING

Specialist weight management clinic.

PARTICIPANTS

Twenty-two participants were purposively sampled from 13 April to 30 April 2021. Median age and BMI of the participants were 37·5 (interquartile range (IQR) = 13·3) and 39·2 kg/m² (IQR = 6·1), respectively. And 31·8 % were men, majority had a high intention to adopt healthy eating behaviours (median = 6·5; IQR = 4·8-6·3) and 59 % of the participants had a medium level of self-regulation.

RESULTS

Six themes and fifteen subthemes were derived. Participants were motivated to lose weight by the sense of responsibility as the family's pillar of support and to feel 'normal' again. We coupled self-regulation barriers with corresponding strategies to come up with four broad themes: habitual overconsumption - mindful self-discipline; proximity and convenience of food available - mental tenacity; momentary lack of motivation and sense of control - motivational boosters; and overeating triggers - removing triggers. We highlighted six unique overeating triggers namely: trigger activities (e.g. using social media); eating with family, friends and colleagues; provision of food by someone; emotions (e.g. feeling bored at home, sad and stressed); physiological condition (e.g. premenstrual syndrome); and the time of the day.

CONCLUSIONS

Future weight management interventions should consider encompassing participant-led weight loss planning, motivation boosters and self-regulation skills to cope with momentary overeating triggers.

Randomized Clinical Trials of Machine Learning Interventions in Health Care: A Systematic Review

IMPORTANCE

Despite the potential of machine learning to improve multiple aspects of patient care, barriers to clinical adoption remain. Randomized clinical trials (RCTs) are often a prerequisite to large-scale clinical adoption of an intervention, and important questions remain regarding how machine learning interventions are being incorporated into clinical trials in health care.

OBJECTIVE

To systematically examine the design, reporting standards, risk of bias, and inclusivity of RCTs for medical machine learning interventions.

EVIDENCE REVIEW

In this systematic review, the Cochrane Library, Google Scholar, Ovid Embase, Ovid MEDLINE, PubMed, Scopus, and Web of Science Core Collection online databases were searched and citation chasing was done to find relevant articles published from the inception of each database to October 15, 2021. Search terms for machine learning, clinical decision-making, and RCTs were used. Exclusion criteria included implementation of a non-RCT design, absence of original data, and evaluation of nonclinical interventions. Data were extracted from published articles. Trial characteristics, including primary intervention, demographics, adherence to the CONSORT-AI reporting guideline, and Cochrane risk of bias were analyzed.

FINDINGS

Literature search yielded 19 737 articles, of which 41 RCTs involved a median of 294 participants (range, 17-2488 participants). A total of 16 RCTS (39%) were published in 2021, 21 (51%) were conducted at single sites, and 15 (37%) involved endoscopy. No trials adhered to all CONSORT-AI standards. Common reasons for nonadherence were not assessing poor-quality or unavailable input data (38 trials [93%]), not analyzing performance errors (38 [93%]), and not including a statement regarding code or algorithm availability (37 [90%]). Overall risk of bias was high in 7 trials (17%). Of 11 trials (27%) that reported race and ethnicity data, the median proportion of participants from underrepresented minority groups was 21% (range, 0%-51%).

CONCLUSIONS AND RELEVANCE

This systematic review found that despite the large number of medical machine learning-based algorithms in development, few RCTs for these technologies have been conducted. Among published RCTs, there was high variability in adherence to reporting standards and risk of bias and a lack of participants from underrepresented minority groups. These findings merit attention and should be considered in future RCT design and reporting.

Dietary lapses are associated with meaningful elevations in daily caloric intake and added sugar consumption during a lifestyle modification intervention

Objective

Lapses from the dietary prescription in lifestyle modification interventions for overweight/obesity are common and impact weight loss outcomes. While it is expected that lapses influence weight via increased consumption, there are no studies that have evaluated how dietary lapses affect dietary intake during treatment. This study examined the association between daily lapses and daily energy and macronutrient intake during a lifestyle modification intervention.

Methods

This study used an intensive longitudinal design to observe participants throughout a 6-month lifestyle modification intervention. Participants (n = 32) were adults with overweight/obesity (body mass index 25-50 kg/m2) and a diagnosed cardiovascular disease risk factor (e.g., hypertension) with a desire to lose weight. Participants underwent a gold-standard individual in-person lifestyle modification protocol consisting of 3 months of weekly sessions with 3 months of monthly sessions. Each participant's dietary prescription included a calorie target range that was based on their starting weight. Participants completed ecological momentary assessment (EMA; repeated daily smartphone surveys) every other week to self-report on dietary lapses and telephone-based 24-h dietary recalls every 6 weeks.

Results

On days with EMA and recalled intake (n = 210 days), linear mixed models demonstrated significant associations between daily lapse and higher total daily caloric intake (B = 139.20, p < 0.05), more daily grams of added sugar (B = 16.24, p < 0.001), and likelihood of exceeding the daily calorie goal (B = 0.89, p < 0.05). The associations between daily lapse and intake of all other daily macronutrients were non-significant.

Conclusions

This study contributes to literature suggesting that dietary lapses pose a threat to weight loss success. Results indicate that reducing lapse frequency could reduce overall caloric intake and added sugar consumption.

Engagement and Outcomes Associated with Contextual Annotation Features of a Digital Health Solution

BACKGROUND

Digital health solutions targeting diabetes self-care are popular and promising, but important questions remain about how these tools can most effectively help patients. Consistent with evidence of the salutary effects of note-taking in education, features that enable annotation of structured data entry might enhance the meaningfulness of the interaction, thereby promoting persistent use and benefits of a digital health solution.

METHOD

To examine the potential benefits of note-taking, we explored how patients with type 2 diabetes used annotation features of a digital health solution and assessed the relationship between annotation and persistence in engagement as well as improvements in glycated hemoglobin (A1C). Secondary data from 3142 users of the BlueStar digital health solution collected between December 2013 and June 2017 were analyzed, with a subgroup of 372 reporting A1C lab values.

RESULTS

About a third of patients recorded annotations while using the platform. Annotation themes largely reflected self-management behaviors (diet, physical activity, medication adherence) and well-being (mood, health status). Early use of contextual annotations was associated with greater engagement over time and with greater improvements in A1C.

CONCLUSIONS

Our research provides preliminary evidence of the benefits of annotation features in a digital health solution. Future research is needed to assess the causal impact of note-taking and the moderating role of thematic content reflected in notes.

Goal language is associated with attrition and weight loss on a digital program: Observational study

Behavioral weight loss reduces risk of weight-related health complications. Outcomes of behavioral weight loss programs include attrition and weight loss. There is reason to believe that individuals' written language on a weight management program may be associated with outcomes. Exploring associations between written language and these outcomes could potentially inform future efforts towards real-time automated identification of moments or individuals at high risk of suboptimal outcomes. Thus, in the first study of its kind, we explored whether individuals' written language in actual use of a program (i.e., outside of a controlled trial) is associated with attrition and weight loss. We examined two types of language: goal setting (i.e., language used in setting a goal at the start of the program) and goal striving (i.e., language used in conversations with a coach about the process of striving for goals) and whether they are associated with attrition and weight loss on a mobile weight management program. We used the most established automated text analysis program, Linguistic Inquiry Word Count (LIWC), to retrospectively analyze transcripts extracted from the program database. The strongest effects emerged for goal striving language. In striving for goals, psychologically distanced language was associated with more weight loss and less attrition, while psychologically immediate language was associated with less weight loss and higher attrition. Our results highlight the potential importance of distanced and immediate language in understanding outcomes like attrition and weight loss. These results, generated from real-world language, attrition, and weight loss (i.e., from individuals' natural usage of the program), have important implications for how future work can better understand outcomes, especially in real-world settings.

Factors Influencing Adherence to mHealth Apps for Prevention or Management of Noncommunicable Diseases: Systematic Review

BACKGROUND

Mobile health (mHealth) apps show vast potential in supporting patients and health care systems with the increasing prevalence and economic costs of noncommunicable diseases (NCDs) worldwide. However, despite the availability of evidence-based mHealth apps, a substantial proportion of users do not adhere to them as intended and may consequently not receive treatment. Therefore, understanding the factors that act as barriers to or facilitators of adherence is a fundamental concern in preventing intervention dropouts and increasing the effectiveness of digital health interventions.

OBJECTIVE

This review aimed to help stakeholders develop more effective digital health interventions by identifying factors influencing the continued use of mHealth apps targeting NCDs. We further derived quantified adherence scores for various health domains to validate the qualitative findings and explore adherence benchmarks.

METHODS

A comprehensive systematic literature search (January 2007 to December 2020) was conducted on MEDLINE, Embase, Web of Science, Scopus, and ACM Digital Library. Data on intended use, actual use, and factors influencing adherence were extracted. Intervention-related and patient-related factors with a positive or negative influence on adherence are presented separately for the health domains of NCD self-management, mental health, substance use, nutrition, physical activity, weight loss, multicomponent lifestyle interventions, mindfulness, and other NCDs. Quantified adherence measures, calculated as the ratio between the estimated intended use and actual use, were derived for each study and compared with the qualitative findings.

RESULTS

The literature search yielded 2862 potentially relevant articles, of which 99 (3.46%) were included as part of the inclusion criteria. A total of 4 intervention-related factors indicated positive effects on adherence across all health domains: personalization or tailoring of the content of mHealth apps to the individual needs of the user, reminders in the form of individualized push notifications, user-friendly and technically stable app design, and personal support complementary to the digital intervention. Social and gamification features were also identified as drivers of app adherence across several health domains. A wide variety of patient-related factors such as user characteristics or recruitment channels further affects adherence. The derived adherence scores of the included mHealth apps averaged 56.0% (SD 24.4%).

CONCLUSIONS

This study contributes to the scarce scientific evidence on factors that positively or negatively influence adherence to mHealth apps and is the first to quantitatively compare adherence relative to the intended use of various health domains. As underlying studies mostly have a pilot character with short study durations, research on factors influencing adherence to mHealth apps is still limited. To facilitate future research on mHealth app adherence, researchers should clearly outline and justify the app's intended use; report objective data on actual use relative to the intended use; and, ideally, provide long-term use and retention data.

Momentary associations between fear of weight gain and dietary restriction among individuals with binge-spectrum eating disorders

OBJECTIVE

Fear of weight gain (FOWG) is increasingly implicated in the maintenance of binge-spectrum eating disorders (EDs; e.g., bulimia nervosa [BN], binge-eating disorder [BED]) through the pathway of increased dietary restriction. However, particularly in binge-spectrum EDs, research is nascent and based on retrospective self-report. To improve treatment outcomes, it is critical to better understand the momentary relations between FOWG and dietary restriction.

METHOD

Sixty-seven adults with binge spectrum EDs completed a 7-14-day ecological momentary assessment protocol that included items regarding FOWG, ED behaviors, and types of dietary restriction (e.g., attempted restraint vs. actual restriction) several times per day. Multilevel models were used to evaluate reciprocal associations between FOWG and dietary restriction, and to evaluate the indirect of effects of dietary restriction on the relation between FOWG and binge eating.

RESULTS

While main effects were not statistically significant, ED presentation significantly moderated the association between increases in FOWG at time1 and both attempted and actual avoidance of enjoyable foods at time2 such that those with BN-spectrum EDs were more likely to avoid enjoyable foods following increased FOWG compared to those with BED-spectrum EDs. Engagement in restriction at time1 was not associated with decreased FOWG at time2.

DISCUSSION

Prospective associations between FOWG and restriction suggest that individuals with BN may be more likely to restrict their eating following increased FOWG. These findings suggest FOWG may be an important target for future treatments.

A review of the quality and content of mobile apps to support lifestyle modifications following a transient ischaemic attack or 'minor' stroke

Objective

Secondary prevention is recommended to reduce cardiovascular risk after transient ischaemic attack (TIA) or ‘minor’ stroke. Mobile health interventions can provide accessible, cost-effective approaches to address modifiable risk factors, such as physical inactivity, hypertension and being overweight. The objective of this study was to evaluate the quality of apps for supporting lifestyle change following a TIA or ‘minor’ stroke.

Methods

Systematic searches of Google Play and the Apple Store were carried out to identify mobile apps released between 1 November 2019 and 1 October 2021. Keywords were used including stroke, TIA, lifestyle, prevention and recovery. Quality was assessed using the Mobile Application Rating Scale (MARS). Common components were identified with the Behaviour Change Technique (BCT) Taxonomy. Descriptive statistics were used to summarize the performance results for each app.

Results

Searches identified 2545 potential apps. Thirty remained after removing duplicates and screening titles and descriptions. Six were eligible after full review of their content. All apps included at least one BCT (range: 1–16 BCTs). The most frequent BCTs included ‘information about health consequences’ (n = 5/6), ‘verbal or visual communication from a credible source’ (n = 4/6) and ‘action planning’ (n = 4/6). The mean MARS score was 2.57/5 (SD: 0.51; range: 1.78–3.36). No apps were of ‘good’ overall quality (scoring more than 4/5).

Conclusions

This is the first review of mobile health interventions for this population. Only a small number of apps were available. None were targeted specifically at people with a TIA or ‘minor’ stroke. Overall quality was low. Further work is needed to develop and test accessible, user designed, and evidence-informed digital interventions in this population.

Momentary predictors of dietary lapse from a mobile health weight loss intervention

Identifying factors that influence risk of dietary lapses (i.e., instances of dietary non-adherence) is important because lapses contribute to suboptimal weight loss outcomes. Existing research examining lapse risk factors has had methodological limitations, including retrospective recall biases, subjective operationalizations of lapse, and has investigated lapses among participants in gold-standard behavioral weight loss programs (which are not accessible to most Americans). The current study will address these limitations by being the first to prospectively assess several risk factors of lapse (objectively operationalized) in the context of a commercial mobile health (mHealth) intervention, a highly popular and accessible method of weight loss. N = 159 adults with overweight or obesity enrolled in an mHealth commercial weight loss program completed ecological momentary assessments (EMAs) of 15 risk factors and lapses (defined as exceeding a point target for a meal/snack) over a 2-week period. N = 9 participants were excluded due to low EMA compliance, resulting in a sample of N = 150. Dietary lapses were predicted by momentary increases in urges to deviate from one's eating plan (b = .55, p < .001), cravings (b = .55, p < .001), alcohol consumption (b = .51, p < .001), and tiredness (b = .19, p < .001), and decreases in confidence related to meeting dietary goals (b = -.21, p < .001) and planning food intake (b = -.15, p < .001). This study was among the first to identify prospective predictors of lapse in the context of a commercial mHealth weight loss program. Findings can inform mHealth weight loss programs, including just-in-time interventions that measure these risk factors, calculate when risk of lapse is high, and deliver momentary interventions to prevent lapses.

Comparing ecological momentary assessment to sensor-based approaches in predicting dietary lapse

Ecological momentary assessment (EMA; brief self-report surveys) of dietary lapse risk factors (e.g., cravings) has shown promise in predicting and preventing dietary lapse (nonadherence to a dietary prescription), which can improve weight loss interventions. Passive sensors also can measure lapse risk factors and may offer advantages over EMA (e.g., objective, automatic, semicontinuous data collection), but currently can measure only a few lapse predictors, a notable limitation. This study preliminarily compared the burden and accuracy of commercially available sensors versus established EMA in lapse prediction. N = 23 adults with overweight/obesity completed a 6-week commercial app-based weight loss program. Participants wore a Fitbit, enabled GPS tracking, completed EMA, and reported on EMA and sensor burden poststudy via a 5-point Likert scale. Sensed risk factors were physical activity and sleep (accelerometer), geolocation (GPS), and time, from which 233 features (measurable characteristics of sensor signals) were extracted. EMA measured 19 risk factors, lapse, and categorized GPS into meaningful geolocations. Two supervised binary classification models (LASSO) were created: the sensor model predicted lapse with 63% sensitivity (true prediction rate of lapse) and 60% specificity (true prediction rate of non-lapse) and EMA model with 59% sensitivity and 72% specificity. EMA model accuracy was higher, but self-reported EMA burden (M = 2.96, SD = 1.02) also was higher (M = 1.50, SD = 0.94). EMA model accuracy was superior, but EMA burden was higher than sensor burden. Findings highlight the promise of sensors in contributing to lapse prediction, and future research may use EMA, sensors, or both depending on prioritization of accuracy versus participant burden.

Examination of the relationship between lapses and weight loss in a smartphone-based just-in time adaptive intervention

We developed a smartphone-based just-in-time adaptive intervention (JITAI), called OnTrack, that provides personalized intervention to prevent dietary lapses (i.e., nonadherence from the behavioral weight loss intervention diet). OnTrack utilizes ecological momentary assessment (EMA; repeated electronic surveys) for self-reporting lapse triggers, predicts lapses using machine learning, and provides brief intervention to prevent lapse. We have established preliminary feasibility, acceptability, and efficacy of OnTrack, but no study has examined our hypothesized mechanism of action: reduced lapse frequency will be associated with greater weight loss while using OnTrack. This secondary analysis investigated the association between lapse frequency and the weekly percentage of weight loss. Post hoc analyses evaluated the moderating effect of OnTrack engagement on this association. Participants (N = 121) with overweight/obesity (MBMI = 34.51; 84.3% female; 69.4% White) used OnTrack with a digital weight loss program for 10 weeks. Engagement with OnTrack (i.e., EMA completed and interventions accessed) was recorded automatically, participants self-reported dietary lapses via EMA, and weighed weekly using Bluetooth scales. Linear mixed models with a random effect of subject and fixed effect of time revealed a nonsignificant association between weekly lapses and the percentage of weight loss. Post hoc analyses revealed a statistically significant moderation effect of OnTrack engagement such that fewer EMA and interventions completed conferred the expected associations between lapses and weight loss. Lapses were not associated with weight loss in this study and one explanation may be the influence of engagement levels on this relationship. Future research should investigate the role of engagement in evaluating JITAIs.

Personalized mobile technologies for lifestyle behavior change: A systematic review, meta-analysis, and meta-regression

Given that the one-size-fits-all approach to mobile health interventions have limited effects, a personalized approach might be necessary to promote healthy behaviors and prevent chronic conditions. Our systematic review aims to evaluate the effectiveness of personalized mobile interventions on lifestyle behaviors (i.e., physical activity, diet, smoking and alcohol consumption), and identify the effective key features of such interventions. We included any experimental trials that tested a personalized mobile app or fitness tracker and reported any lifestyle behavior measures. We conducted a narrative synthesis for all studies, and a meta-analysis of randomized controlled trials. Thirty-nine articles describing 31 interventions were included (n = 77,243, 64% women). All interventions personalized content and rarely personalized other features. Source of data included system-captured (12 interventions), user-reported (11 interventions) or both (8 interventions). The meta-analysis showed a moderate positive effect on lifestyle behavior outcomes (standardized difference in means [SDM] 0.663, 95% CI 0.228 to 1.10). A meta-regression model including source of data found that interventions that used system-captured data for personalization were associated with higher effectiveness than those that used user-reported data (SDM 1.48, 95% CI 0.76 to 2.19). In summary, the field is in its infancy, with preliminary evidence of the potential efficacy of personalization in improving lifestyle behaviors. Source of data for personalization might be important in determining intervention effectiveness. To fully exploit the potential of personalization, future high-quality studies should investigate the integration of multiple data from different sources and include personalized features other than content.

Identifying behavioral types of dietary lapse from a mobile weight loss program: Preliminary investigation from a secondary data analysis

Success in behavioral weight loss (BWL) programs depends on adherence to the recommended diet to reduce caloric intake. Dietary lapses (i.e., deviations from the BWL diet) occur frequently and can adversely affect weight loss outcomes. Research indicates that lapse behavior is heterogenous; there are many eating behaviors that could constitute a dietary lapse, but they are rarely studied as distinct contributors to weight outcomes. This secondary analysis aims to evaluate six behavioral lapse types during a 10-week mobile BWL program (eating a large portion, eating when not intended, eating an off-plan food, planned lapse, being unaware of caloric content, and endorsing multiple types of lapse). Associations between weekly behavioral lapse type frequency and weekly weight loss were investigated, and predictive contextual characteristics (psychological, behavioral, and environmental triggers for lapse) and individual difference (e.g., age, gender) factors were examined across lapse types. Participants (N = 121) with overweight/obesity (M_BMI = 34.51; 84.3% female; 69.4% White) used a mobile BWL program for 10 weeks, self-weighed weekly using Bluetooth scales, completed daily ecological momentary assessment of lapse behavior and contextual characteristics, and completed a baseline demographics questionnaire. Linear mixed models revealed significant negative associations between unplanned lapses and percent weight loss. Unplanned lapses from eating a large portion, eating when not intended, and having multiple "types" were significantly negatively associated with weekly percent weight loss. A lasso regression showed that behavioral lapse types share many similar stable factors, with other factors being unique to specific lapse types. Results add to the prior literature on lapses and weight loss in BWL and provide preliminary evidence that behavioral lapse types could aid in understanding adherence behavior and developing precision medicine tools to improve dietary adherence.

The potential of artificial intelligence in enhancing adult weight loss: a scoping review

OBJECTIVE

To present an overview of how artificial intelligence (AI) could be used to regulate eating and dietary behaviours, exercise behaviours and weight loss.

DESIGN

A scoping review of global literature published from inception to 15 December 2020 was conducted according to Arksey and O'Malley's five-step framework. Eight databases (CINAHL, Cochrane-Central, Embase, IEEE Xplore, PsycINFO, PubMed, Scopus and Web of Science) were searched. Included studies were independently screened for eligibility by two reviewers with good interrater reliability (k = 0·96).

RESULTS

Sixty-six out of 5573 potential studies were included, representing more than 2031 participants. Three tenets of self-regulation were identified - self-monitoring (n 66, 100 %), optimisation of goal setting (n 10, 15·2 %) and self-control (n 10, 15·2 %). Articles were also categorised into three AI applications, namely machine perception (n 50), predictive analytics only (n 6) and real-time analytics with personalised micro-interventions (n 10). Machine perception focused on recognising food items, eating behaviours, physical activities and estimating energy balance. Predictive analytics focused on predicting weight loss, intervention adherence, dietary lapses and emotional eating. Studies on the last theme focused on evaluating AI-assisted weight management interventions that instantaneously collected behavioural data, optimised prediction models for behavioural lapse events and enhance behavioural self-control through adaptive and personalised nudges/prompts. Only six studies reported average weight losses (2·4-4·7 %) of which two were statistically significant.

CONCLUSION

The use of AI for weight loss is still undeveloped. Based on the current study findings, we proposed a framework on the applicability of AI for weight loss but cautioned its contingency upon engagement and contextualisation.

Development of a Digital Lifestyle Modification Intervention for Use after Transient Ischaemic Attack or Minor Stroke: A Person-Based Approach

This paper describes the development of the ‘Brain-Fit’ app, a digital secondary prevention intervention designed for use in the early phase after transient ischaemic attack (TIA) or minor stroke. The aim of the study was to explore perceptions on usability and relevance of the app in order to maximise user engagement and sustainability. Using the theory- and evidence-informed person-based approach, initial planning included a scoping review of qualitative evidence to identify barriers and facilitators to use of digital interventions in people with cardiovascular conditions and two focus groups exploring experiences and support needs of people (N = 32) with a history of TIA or minor stroke. The scoping review and focus group data were analysed thematically and findings were used to produce guiding principles, a behavioural analysis and explanatory logic model for the intervention. Optimisation included an additional focus group (N = 12) and individual think-aloud interviews (N = 8) to explore perspectives on content and usability of a prototype app. Overall, thematic analysis highlighted uncertainty about increasing physical activity and concerns that fatigue might limit participation. Realistic goals and progressive increases in activity were seen as important to improving self-confidence and personal control. The app was seen as a useful and flexible resource. Participant feedback from the optimisation phase was used to make modifications to the app to maximise engagement, including simplification of the goal setting and daily data entry sections. Further studies are required to examine efficacy and cost-effectiveness of this novel digital intervention.

Slip Buddy App for Weight Management: Randomized Feasibility Trial of a Dietary Lapse Tracking App

BACKGROUND

Although calorie tracking is one of the strongest predictors of weight loss in behavioral weight loss interventions, low rates of adherence are common.

OBJECTIVE

This study aims to examine the feasibility and acceptability of using the Slip Buddy app during a 12-week web-based weight loss program.

METHODS

We conducted a randomized pilot trial to evaluate the feasibility and acceptability of using the Slip Buddy app compared with a popular commercial calorie tracking app during a counselor-led, web-based behavioral weight loss intervention. Adults who were overweight or obese were recruited on the web and randomized into a 12-week web-based weight loss intervention that included either the Slip Buddy app or a commercial calorie tracking app. Feasibility outcomes included retention, app use, usability, slips reported, and contextual factors reported at slips. Acceptability outcomes included ratings of how helpful, tedious, taxing, time consuming, and burdensome using the assigned app was. We described weight change from baseline to 12 weeks in both groups as an exploratory outcome. Participants using the Slip Buddy app provided feedback on how to improve it during the postintervention focus groups.

RESULTS

A total of 75% (48/64) of the participants were female and, on average, 39.8 (SD 11.0) years old with a mean BMI of 34.2 (SD 4.9) kg/m2. Retention was high in both conditions, with 97% (31/32) retained in the Slip Buddy condition and 94% (30/32) retained in the calorie tracking condition. On average, participants used the Slip Buddy app on 53.8% (SD 31.3%) of days, which was not significantly different from those using the calorie tracking app (mean 57.5%, SD 28.4% of days), and participants who recorded slips (30/32, 94%) logged on average 17.9 (SD 14.4) slips in 12 weeks. The most common slips occurred during snack times (220/538, 40.9%). Slips most often occurred at home (297/538, 55.2%), while working (153/538, 28.4%), while socializing (130/538, 24.2%), or during screen time (123/538, 22.9%). The conditions did not differ in participants' ratings of how their assigned app was tedious, taxing, or time consuming (all values of P>.05), but the calorie tracking condition gave their app higher helpfulness and usability ratings (all values of P<.05). Technical issues were the most common type of negative feedback, whereas simplicity was the most common type of positive feedback. Weight losses of ≥5% of baseline weight were achieved by 31% (10/32) of Slip Buddy participants and 34% (11/32) of calorie tracking participants.

CONCLUSIONS

Self-monitoring of dietary lapses and the contextual factors associated with them may be an alternative for people who do not prefer calorie tracking. Future research should examine patient characteristics associated with adherence to different forms of dietary self-monitoring.

TRIAL REGISTRATION

ClinicalTrials.gov NCT02615171; https://clinicaltrials.gov/ct2/show/NCT02615171.

Predictors and Outcomes of Digital Weighing and Activity Tracking Lapses Among Young Adults During Weight Gain Prevention

OBJECTIVES

Self-monitoring is critical for weight management, but little is known about lapses in the use of digital self-monitoring. The objectives of this study were to examine whether lapses in self-weighing and wearing activity trackers are associated with weight and activity outcomes and to identify objective predictors of lapses.

METHODS

Participants (N = 160, BMI = 25.5 ± 3.3 kg/m2 , 33.1 ± 4.6 years old) were drawn from a sample of young adults in the Study of Novel Approaches to Prevention-Extension (SNAP-E) weight gain prevention trial. Analyses evaluated associations between weighing and tracker lapses and changes in weight and steps/day during the first 90 days after receiving a smart scale and activity tracker.

RESULTS

On average, participants self-weighed 49.6% of days and wore activity trackers 75.2% of days. Every 1-day increase in a weighing lapse was associated with a 0.06-lb gain. Lapses in tracker wear were not associated with changes in steps/day or weight between wear days. Weight gain predicted a higher likelihood of starting a lapse in weighing and tracker wear, whereas lower steps predicted a higher likelihood of a tracker lapse.

CONCLUSIONS

Weight gain may discourage adherence to self-monitoring. Future research could examine just-in-time supports to anticipate and reduce the frequency or length of self-monitoring lapses.