Foundation Models as a New Portable Standard in Local Risk Stratification for Emergency Surgery

Background: Surgical risk is locality-specific, and database infrastructure to support accurate preoperative risk stratification is limited globally.Objective: We aimed to evaluate the role of tabular foundation models in widening access to high-accuracy local risk stratification.Methods: We applied a transformer-based tabular pre-trained foundation (TabPFN) model with comparison to logistic regression and gradient boosting methods in our institutional data from the American College of Surgeons National Surgical Quality Improvement Program database of patients undergoing emergency surgery.We first compared performance overall, then at individual sites (n = 5), followed by comparison of the TabPFN model trained on site-level data against logistic regression and XGBoost models trained on all available multisite data not used for testing.Outcomes of interest were 30day mortality and morbidity.Results: Among 7281 emergency surgery patients (4.8% mortality, 30.2% morbidity), TabPFN achieved the highest area