Artificial intelligence for procedural coding in cardiac critical care: Evaluating large language models for current procedural terminology accuracy

Leon Fan, Sukethram Sivakumar, Ernesto Marin, Mingfeng Cao, Daniel Brodie, Glenn J.R. Whitman, Sung-Min ChoHERALD Team, Division of Cardiac Surgery, Department of Surgery, Johns Hopkins University School of Medicine, Division of Neuroscience Critical Care, Departments of Neurosurgery, Critical Care Medicine, The Johns Hopkins Hospital, Division of Pulmonary and Critical Care Medicine, Department of Medicine, The Johns Hopkins University School of Medicine, Department of Neurology, Johns Hopkins University School of Medicine

Perfusion

Published online on December 23, 2025

Abstract

Perfusion, Volume 41, Issue 5, Page 593-599, July 2026.
BackgroundAccurate procedural coding is essential for resource allocation, billing integrity, and quality reporting within critical care. Current Procedural Terminology (CPT) coding is largely manual and error-prone, especially in high-acuity environments ...