Health AI Central
Peer-Reviewed Publication
J Am Coll Surg2026October 1, 2026Journal Article

Matching Surgical Datasets to Prediction Tasks: NSQIP and Non-NSQIP Artificial Intelligence Models Across Specialties.

Divya Kewalramani1,2, Justin Benton1,2, Zack Barta1,2, Lily Wushanley1,2, Amanda Teichman1, Joseph Hanna1, Amin Madani3, Philip S Barie4, Tyler Loftus5, Mayur Narayan1,2
1Division of Acute Care Surgery, Department of Surgery, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ (Kewalramani, Benton, Barta, Wushanley, Teichman, Hanna, Narayan).
2Artificial Intelligence for Comprehensive Care, Equity, and Sustainability in Surgery (AiCCESS), Rutgers Acute Care Surgery Research Laboratory, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ (Kewalramani, Benton, Barta, Wushanley, Narayan).
3Surgical Artificial Intelligence Research Academy, University Health Network, and Department of Surgery, University of Toronto, Toronto, ON, Canada (Madani).
4Division of Trauma, Burns, Acute and Critical Care, Weill Cornell Medicine, New York, NY (Barie).
5Department of Surgery, University of Florida Health, Gainesville, FL (Loftus).
PubMed DOI

Abstract

BACKGROUND: Surgical artificial intelligence models depend on training data that may not capture predictors required for specific outcomes. We compared discrimination of models derived from the American College of Surgeons National Surgical Quality Improvement Program (NSQIP) with models using non-NSQIP datasets across surgical specialties and prediction tasks. STUDY DESIGN: Structured searches o…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.