Assessing the Contribution of Self-Monitoring Through a Commercial Weight Loss App: Mediation and Predictive Modeling Study

Randomized Controlled Trials to Treat Obesity in Military Populations: A Systematic Review and Meta-Analysis

In recent years, overweight and obesity have reached an alarmingly high incidence and prevalence worldwide; they have also been steadily increasing in military populations. Military personnel, as an occupational group, are often exposed to stressful and harmful environments that represent a risk factor for disordered eating, with major repercussions on both physical and mental health. This study aims to explore the effectiveness of weight loss interventions and assess the significance of current obesity treatments for these populations. Three online databases (PubMed, PsycInfo, and Web of Science) were screened to identify randomized controlled trials (RCTs) aiming to treat obesity in active-duty military personnel and veterans. Random-effects meta-analyses were conducted for body weight (BW) and body mass index (BMI) values, both longitudinally comparing treatment groups from pre-to-post intervention and cross-sectionally comparing the treatment group to controls at the end of the intervention. A total of 21 studies were included: 16 cross-sectional (BW: n = 15; BMI: n = 12) and 16 longitudinal (BW: n = 15; BMI: n = 12) studies were meta-analyzed, and 5 studies were narratively synthesized. A significant small overall BW and BMI reduction from baseline to post-intervention was observed (BW: g = -0.10; p = 0.015; BMI: g = -0.32; p < 0.001), together with a decreased BMI (g = -0.16; p = 0.001) and nominally lower BW (g = -0.08; p = 0.178) in the intervention group compared to controls at the post-intervention time-point. Despite limitations, such as the heterogeneity across the included interventions and the follow-up duration, our findings highlight how current weight loss interventions are effective in terms of BW and BMI reductions in military populations and how a comprehensive approach with multiple therapeutic goals should be taken during the intervention.

An Explainable Artificial Intelligence Software Tool for Weight Management Experts (PRIMO): Mixed Methods Study

BACKGROUND

Predicting the likelihood of success of weight loss interventions using machine learning (ML) models may enhance intervention effectiveness by enabling timely and dynamic modification of intervention components for nonresponders to treatment. However, a lack of understanding and trust in these ML models impacts adoption among weight management experts. Recent advances in the field of explainable artificial intelligence enable the interpretation of ML models, yet it is unknown whether they enhance model understanding, trust, and adoption among weight management experts.

OBJECTIVE

This study aimed to build and evaluate an ML model that can predict 6-month weight loss success (ie, ≥7% weight loss) from 5 engagement and diet-related features collected over the initial 2 weeks of an intervention, to assess whether providing ML-based explanations increases weight management experts' agreement with ML model predictions, and to inform factors that influence the understanding and trust of ML models to advance explainability in early prediction of weight loss among weight management experts.

METHODS

We trained an ML model using the random forest (RF) algorithm and data from a 6-month weight loss intervention (N=419). We leveraged findings from existing explainability metrics to develop Prime Implicant Maintenance of Outcome (PRIMO), an interactive tool to understand predictions made by the RF model. We asked 14 weight management experts to predict hypothetical participants' weight loss success before and after using PRIMO. We compared PRIMO with 2 other explainability methods, one based on feature ranking and the other based on conditional probability. We used generalized linear mixed-effects models to evaluate participants' agreement with ML predictions and conducted likelihood ratio tests to examine the relationship between explainability methods and outcomes for nested models. We conducted guided interviews and thematic analysis to study the impact of our tool on experts' understanding and trust in the model.

RESULTS

Our RF model had 81% accuracy in the early prediction of weight loss success. Weight management experts were significantly more likely to agree with the model when using PRIMO (χ2=7.9; P=.02) compared with the other 2 methods with odds ratios of 2.52 (95% CI 0.91-7.69) and 3.95 (95% CI 1.50-11.76). From our study, we inferred that our software not only influenced experts' understanding and trust but also impacted decision-making. Several themes were identified through interviews: preference for multiple explanation types, need to visualize uncertainty in explanations provided by PRIMO, and need for model performance metrics on similar participant test instances.

CONCLUSIONS

Our results show the potential for weight management experts to agree with the ML-based early prediction of success in weight loss treatment programs, enabling timely and dynamic modification of intervention components to enhance intervention effectiveness. Our findings provide methods for advancing the understandability and trust of ML models among weight management experts.

Expert opinions on reducing dietary self-monitoring burden and maintaining efficacy in weight loss programs: A Delphi study

Objective

Dietary self-monitoring is consistently related to both short- and long-term weight loss, but typically declines over time. Adopting an abbreviated approach to self-monitoring might reduce burden and potentially increase engagement while maintaining efficacy.

Methods

Using a Delphi-type study, experts were queried about abbreviated self-monitoring approaches that might best balance efficacy and burden and asked to identify when these approaches might best be implemented within a behavioral weight loss program. Experts were surveyed three times until consensus was reached.

Results

Experts identified three main categories of promising strategies for abbreviated self-monitoring regardless of whether individuals have been successful with weight loss or full dietary self-monitoring: (1) self-weighing only, (2) reducing the foods/beverages self-monitored to those that are often less routine and higher in caloric density, and (3) reducing the number of days per week to engage in full dietary self-monitoring. Experts recommended transitioning to abbreviated self-monitoring after 2 weeks of no self-monitoring among individuals who were struggling and after reaching 5%-10% weight loss among successful individuals.

Conclusions

These expert opinions offer a foundation to experimentally manipulate promising strategies for reducing burden and increasing long-term engagement in self-monitoring, with a goal of enhancing long-term weight control.

Perspectives on the Form, Magnitude, Certainty, Target, and Frequency of Financial Incentives in a Weight Loss Program

PURPOSE

Financial incentives are a promising approach to enhance weight loss outcomes; however, little guidance exists on the optimal incentive structure.

DESIGN

Mixed methods.

SETTING

An online weight management trial, combining outcome (i.e., weight loss) and behavioral (i.e., self-weighing, dietary self-monitoring, and steps) incentives over 12 months (up to $665).

SUBJECTS

116 participants who completed the incentive preference assessment at the 18-month follow-up visit.

METHOD

Response distributions on the form, magnitude, certainty, and target of the incentives and content analysis of the qualitative responses.

RESULTS

Nearly all (96.6%) participants indicated they liked receiving electronic Amazon gift cards, more so than the alternatives presented. Most participants (81.0%) thought they would have lost a similar amount of weight if the incentives were smaller. Few (18.1%) indicated they would have preferred a lottery structure, but 50.8% indicated the variable incentive schedule was beneficial during the maintenance period. Most (77.6%) felt incentives were most helpful when starting to lose weight. In both phases, most participants (85.3% and 72.4%, respectively) indicated appropriate behaviors were incentivized. Participants had mixed views on whether outcome or behavioral incentives were most motivating.

CONCLUSION

There was notable variation in preferences for the magnitude, duration, and timing of incentives; it will be important to examine in future research whether incentive design should be tailored to individual preferences.

Assessing the Contribution of Self-Monitoring Through a Commercial Weight Loss App: Mediation and Predictive Modeling Study

Background

Electronic self-monitoring technology has the potential to provide unique insights into important behaviors for inducing weight loss.

Objective

The aim of this study is to investigate the effects of electronic self-monitoring behavior (using the commercial Lose It! app) and weight loss interventions (with differing amounts of counselor feedback and support) on 4- and 12-month weight loss.

Methods

In this secondary analysis of the Fit Blue study, we compared the results of two interventions of a randomized controlled trial. Counselor-initiated participants received consistent support from the interventionists, and self-paced participants received assistance upon request. The participants (N=191), who were active duty military personnel, were encouraged to self-monitor their diet and exercise with the Lose It! app or website. We examined the associations between intervention assignment and self-monitoring behaviors. We conducted a mediation analysis of the intervention assignment for weight loss through multiple mediators—app use (calculated from the first principal component [PC] of electronically collected variables), number of weigh-ins, and 4-month weight change. We used linear regression to predict weight loss at 4 and 12 months, and the accuracy was measured using cross-validation.

Results

On average, the counselor-initiated–treatment participants used the app more frequently than the self-paced–treatment participants. The first PC represented app use frequencies, the second represented calories recorded, and the third represented reported exercise frequency and exercise caloric expenditure. We found that 4-month weight loss was partially mediated through app use (ie, the first PC; 60.3%) and the number of weigh-ins (55.8%). However, the 12-month weight loss was almost fully mediated by 4-month weight loss (94.8%). Linear regression using app data from the first 8 weeks, the number of self–weigh-ins at 8 weeks, and baseline data explained approximately 30% of the variance in 4-month weight loss. App use frequency (first PC; P=.001), self-monitored caloric intake (second PC; P=.001), and the frequency of self-weighing at 8 weeks (P=.008) were important predictors of 4-month weight loss. Predictions for 12-month weight with the same variables produced an R² value of 5%; only the number of self–weigh-ins was a significant predictor of 12-month weight loss. The R² value using 4-month weight loss as a predictor was 31%. Self-reported exercise did not contribute to either model (4 months: P=.77; 12 months: P=.15).

Conclusions

We found that app use and daily reported caloric intake had a substantial impact on weight loss prediction at 4 months. Our analysis did not find evidence of an association between participant self-monitoring exercise information and weight loss. As 12-month weight loss was completely mediated by 4-month weight loss, intervention targets should focus on promoting early and frequent dietary intake self-monitoring and self-weighing to promote early weight loss, which leads to long-term success.

Trial Registration

ClinicalTrials.gov NCT02063178; https://clinicaltrials.gov/ct2/show/NCT02063178