Electronic Health Record-Based Machine Learning Models for Predicting Revascularization, Amputation, and Cardiovascular Mortality in At-Risk Patients
This study demonstrates that machine learning models trained on harmonized electronic health record data from nearly 179,000 patients effectively predict revascularization and amputation with high accuracy, while showing more modest performance for cardiovascular mortality, thereby supporting the utility of EHR-based risk stratification for at-risk vascular patients.