MEDBRIDGE: AI-Driven Risk Stratification and Care Transition Intervention to Improve Diabetes Medication Management
University of Alabama at Birmingham
Summary
This study tests whether a support program led by a nurse case manager and community health worker can help patients with type 2 diabetes manage their medications after leaving the hospital. Many patients with diabetes take multiple medications, and changes to these medications during hospital stays can cause confusion and lead to missed doses or incorrect use. This is especially common in communities with limited access to healthcare. The study uses a computer-based tool called MEDBRIDGE (MEDication BRIDGE) to identify patients who may be at higher risk for problems after discharge, such as worsening blood sugar control or return visits to the emergency department. Patients identified as high-risk will receive 3 months of support from a nurse case manager and community health worker team, who will help with medication questions, coordinate with their doctor, and provide follow-up check-ins. The main goal is to find out whether this type of support program is practical to deliver and acceptable to patients. The study will also track changes in blood sugar levels and emergency department visits. Forty-five patients will be enrolled over 6 months at the University of Alabama at Birmingham and Cooper Green Mercy Health Services in Jefferson County, Alabama.
Description
This single-arm feasibility pilot evaluates a MEDBRIDGE-guided nurse case manager (NCM) and community health worker (CHW) post-discharge support intervention for high-risk patients with type 2 diabetes (T2D). MEDBRIDGE is an AI-driven risk stratification tool that integrates medication data, clinical factors, and social determinants of health from electronic health records to identify patients at elevated risk of HbA1c elevation, diabetes-related emergency department visits, and hospitalizations within 3 months post-discharge. The intervention follows a four-phase workflow: (1) Risk Assessmen…