Aims Type 2 diabetes mellitus (T2DM) remains a major global health burden, with many patients failing to achieve optimal glycemic control despite pharmacological and behavioral interventions. Family support is associated with improved diabetes self-management, yet evidence for scalable, family-based mobile health (mHealth) interventions remains limited. We evaluated the feasibility, acceptability, and preliminary metabolic and behavioral outcomes of an AI-enabled mHealth intervention incorporating family engagement.
Methods This prospective 6-month pre–post study enrolled patients with T2DM (most recent HbA1c ≥7.0%) and a family member. Patients used a smartwatch-integrated mobile app featuring AI-enabled personalized nudges, smart logging, and diabetes education alongside usual care. Family members accessed a dedicated module with shared activity logs, educational resources, in-app communication, and collaborative goal setting functions. Primary outcomes were feasibility and acceptability. Secondary outcomes included HbA1c, medication adherence (Voils), moderate-to-vigorous physical activity (MVPA) minutes, Family and Friend Involvement in Adults’ Diabetes (FIAD), and Important Other Climate Questionnaire (IOCQ). Semi-structured interviews informed implementation evaluation.
Results Fifty patient–family dyads (n=100) were enrolled; 58% of patients were male, and 60% of family members were females, with 72% spouses. Retention at 6 months was 99%. Mean HbA1c and medication adherence showed numerical improvement from baseline, though changes were not statistically significant (HbA1c p=0.318; adherence p=0.177). FIAD helpful involvement scores decreased post-intervention (p=0.024), while IOCQ scores increased (mean 5.93 vs 6.42; p=0.002), indicating enhanced autonomy-supportive engagement. In adjusted analyses, higher baseline HbA1c was associated with greater HbA1c reduction at 6 months (β=0.315, SE=0.124, p=0.015). Participants achieved a mean of 157.8 MVPA minutes/week (95% CI 121–194). Qualitative findings indicated high acceptability of AI-driven nudges for dietary self-management and perceived value of timely family support. Barriers included competing daily commitments, occasional patient–family tensions, and limited health literacy.
Conclusion This AI-enabled, family-engaged mHealth intervention demonstrated high feasibility and acceptability in adults with T2DM, with signals suggesting benefit for self-management and glycemic outcomes. Findings support further refinement and evaluation in a randomized trial to determine clinical effectiveness and scalability.
*Unless otherwise noted, all abstracts presented at ENDO must not be released to the press or the public until the date and time of presentation. For oral presentations, the abstracts are embargoed until the session begins. The Endocrine Society reserves the right to lift the embargo on specific abstracts that are selected for promotion prior to or during ENDO.*
.jpg)
.jpg)