User Engagement and Feature Preferences in an AI-Powered mHealth Intervention for Diabetes Prevention: Secondary Analysis of a Randomized Controlled Trial.
JMIR Mhealth UhealthSep 2, 2026 (epub)
Clinical ResearchEndocrinology
Benjamin Lalani, Gabriela Siew, Yllka Valdez et al.
✦ AI-curated · Sources linked
In 30 seconds
This secondary analysis of a randomized controlled trial examined user engagement and feature preferences in an AI-powered mHealth intervention for diabetes prevention among 151 participants with prediabetes and obesity. Higher engagement was linked to improved diabetes risk reduction outcomes, with high engagement associated with an odds ratio of 2.59 for achieving composite outcomes compared to low engagement.
Key findings
- High engagement was associated with an odds ratio of 2.59 for achieving composite diabetes risk reduction outcomes.
- Participants with high engagement had an odds ratio of 3.31 for achieving ≥5% weight loss.
- An odds ratio of 3.57 was observed for achieving a ≥0.2 percentage point reduction in HbA1c with high engagement.
- Weight tracking, physical activity tracking, and digital body weight scale were the most valued features.
Why it matters
Understanding user engagement and feature preferences in mHealth interventions can inform the design of effective diabetes prevention programs, potentially leading to better health outcomes in at-risk populations.