Machine learning-based digital health application integrating wearable data and behavioral patterns improves metabolic health

preprint OA: closed
View at publisher

Abstract

Abstract Lifestyle interventions aimed at reducing caloric intake and increasing physical activity have the potential to prevent Type 2 Diabetes (T2D). The use of new technologies may enhance the success of lifestyle interventions, improve metabolic health, and prevent T2D. 2,217 participants, ranging from normoglycemic to T2D, were enrolled in the Season-of-Me Program in which glucose patterns were captured over 28 consecutive days via continuous glucose monitoring (CGM). Food intake, activity, and body weight were logged by participants and integrated with wearables data using a smartphone-based app which continuously provided insights to participants, including overlaying daily glucose patterns with activity and food intake, as well as summarizing macronutrient breakdown, glycemic index (GI), glycemic load, and activity measures. The mobile app also used machine learning to provide personalized recommendations based on users’ preferences, including their adherence to recommendations, their personal goals, and their glycemic patterns. Users had the option to continue interacting with the mobile app without CGM for an additional two months. Results demonstrated significant improvements in hyperglycemia, glucose variability, and hypoglycemia (particularly in those who were not diabetic at baseline). Body weight decreased in all groups, particularly in the most overweight/obese. Healthy eating habits improved significantly, with reduced daily caloric intake and proportion of carbohydrates-to-calories; and increased intake of protein, fiber, and healthy fats (relative to calories). These results suggest that integration of behavior logging and CGM data with AI-based personalized lifestyle recommendations can improve the metabolic health of both nondiabetic and T2D individuals via healthier lifestyle choices. This technology thus serves as an important tool to enhance current approaches to T2D prevention and treatment.

My notes (saved in your browser only)

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. The paper's references may be in our DB but unresolved to ``paper_id`` (resolution happens at ingest when the cited DOI matches a row we already have). Run the cross-source citation reconcile pass to retry.

Source provenance

europepmc
last seen: 2026-05-19T01:45:01.086888+00:00