Can large language models extract operative standards from narrative operative reports in rectal cancer?

Surgery 2026 Open access

Read full text
Authors: Karen Trang, Beiqun Zhao, Colleen P. Flanagan, Logan Pierce, Lindsay L. Welton, Melissa A. Gunderson, Genevieve B Melton, Elizabeth H. Wick
DOI: 10.1016/j.surg.2025.110037
Cited by: 1
References: 5

Abstract

While ascertaining critical steps to surgical procedures is essential for surgical quality improvement and research, the narrative format of operative reports makes automation of obtaining this information highly challenging. Synoptic operative notes are promising, but their adoption has been slow in practice, and manual extraction of narrative reports is prohibitively expensive.1 Large language models (LLMs), including commercial products that are widely available such as ChatGPT (https://chatgpt.com/), can perform a range of functions including text summarization, text analysis, and data extraction.

Fields of Study & Subjects

Digital Imaging in Medicine Multimodal Machine Learning Applications Artificial Intelligence in Healthcare and Education

Publication details

Journal / source
Surgery
Publisher
Elsevier BV
Volume
191
Pages
110037–110037
Publication date
6 January 2026
Language
EN