Chapel Hill, N.C.-based UNC Health has cut care gap chart review in half with Microsoft’s Fabric data platform.
Here are five things to know from a May 26 Microsoft news release:
1. The 20-hospital system deployed an AI framework called EASI (Extract, Analyze, Synthesize, and Integrate) to help close care gaps in population health.
2. EASI scans unstructured clinical documents — such as colonoscopy reports, mammograms, and eye exams — to determine whether patients received appropriate screenings, then surfaces that information into Epic.
3. The tool reduced time spent per patient chart by roughly 50%, or about three minutes per review, allowing staff to focus on additional care gaps.
4. Abstraction detection accuracy improved from 83% to 93% during a diabetic eye exam pilot, with human reviewers remaining the final checkpoint before any finding enters the patient record.
5. UNC Health is expanding EASI beyond diabetic eye exams to colorectal, cervical, and breast cancer screenings, and is also running a secure research environment called SHIRE that currently supports 25 active studies.
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.