Personalized Mental Health Subtyping in Diabetes Using Digital Twin Technology to Improve Treatment

What this Trial Is About

Researchers are investigating mental health conditions such as distress, depression, anxiety, and eating disorders in people with diabetes. This study aims to use a personalized approach called precision mental health to identify subgroups of people with diabetes who share common patterns in the relationships between glucose levels and psychosocial factors. The goal is to develop a digital twin, a virtual model that can simulate and predict the course of mental health and blood sugar control to help guide more tailored diabetes care. Participants include over 1,800 people with type 1, type 2, or other specific types of diabetes. They continuously complete ecological momentary assessments EMA, which involve daily surveys about stress, mood, and diabetes distress, along with questionnaires every six months. Glucose levels are measured using continuous glucose monitoring CGM devices, and clinical interviews diagnose mental health disorders. Data on medication, complications, diet, physical activity, and metabolic measures like HbA1c are also collected to build comprehensive profiles. During the study, participants undergo repeated assessments every six months over a two-year period, including EMA, questionnaires, CGM data collection, and diagnostic interviews in a subset. Researchers analyze the complex interactions between metabolic, behavioral, and psychological data using machine learning to identify subgroups and validate the digital twins predictions. The main outcomes measured include the incidence and remission of mental disorders, diabetes distress, and glycemic control. This observational study will provide insights to support personalized mental health care in diabetes.

Precision Subclassification of Mental Health in Diabetes: Digital Twins for Precision Mental Health to Track Subgroups