Consistent engagement across education, food tracking, reminders, and medication tracking on a digital platform was significantly associated with greater weight reduction (r=0.12-0.15, p<0.05).
Observational (n=2,487)
Does consistent engagement with a digital health platform improve weight loss in adults with obesity and cardiometabolic conditions?
Sustained self-monitoring and consistent engagement with a digital health platform are significantly associated with greater weight loss in a real-world cardiometabolic population.
Effect estimate: r=0.12-0.15
p-value: p=<0.05
Introduction and Objective: Digital health platforms generate rich engagement data, yet real world evidence remains limited on which behaviors are most strongly associated with meaningful weight loss among individuals with obesity. This study used data from the Dario digital health platform to identify engagement features associated with weight loss using feature engineering and machine-learning methods in a real-world population with obesity. Methods: A retrospective analysis of adults using Dario platform in 2025 with a baseline body mass index (BMI) ≥30 kg/m² was conducted. Engagement data were extracted across multiple app domains, including weight monitoring, education, reminders, and food tracking. A feature-engineering pipeline derived metrics capturing engagement trends, timing (early vs late), consistency, and frequency. Pearson correlations were calculated between engagement features and weight decrease. A random forest model with 500 trees was used to predict weight reduction and assess feature importance. Results: Among 2,487 users managing cardiometabolic conditions (46% self-reported Type 2 or Prediabetes) with ≥2 months of weight data, engagement consistency across education, food tracking, reminders and medications tracking was significantly associated with greater weight reduction (r=0.12-0.15, p0.05). These effects are clinically meaningful in a real-world population, where consistent behaviors translate into population-level impact and actionable personalization. Random forest analysis confirmed total engagement consistency as the strongest predictor. Conclusion: These findings indicate that sustained self-monitoring and consistent engagement, rather than a single interaction, are strongly associated with weight loss and can inform personalization and optimization of digital weight-management programs for cardiometabolic populations. Disclosure Y.F. Hershcovitz: Employee; Current; DarioHealth Corp. I. Breuer Asher: Employee; Current; DarioHealth Corp. O. Manejwala: Employee; Current; DarioHealth Corp. Stock/Shareholder; Current; DarioHealth Corp.
Hershcovitz et al. (Fri,) conducted a observational in Obesity and cardiometabolic conditions (n=2,487). Digital platform engagement consistency was evaluated on Weight reduction (r=0.12-0.15, p=<0.05). Consistent engagement across education, food tracking, reminders, and medication tracking on a digital platform was significantly associated with greater weight reduction (r=0.12-0.15, p<0.05).