Longitudinal Wearable Monitoring to Predict Diabetic Burnout in Type 1 Diabetes

Diabetic burnout affects up to 44% of individuals with Type 1 diabetes, significantly impacting mental health and self-management.

Burnout often coincides with disruptions in sleep and physical activity, creating a feedback loop that worsens distress.

Wearable devices offer a unique opportunity to track these behaviours in real-time, providing valuable data for early detection.

This project will explore if multi-sensor data of sleep, physical activity, and glucose levels in individuals with Type 1 diabetes can be used to build predictive models for timely detection of diabetic burnout and fatigue. Using advanced machine learning techniques, we aim to model how changes in these factors predict burnout risk.