SurgeryLLM: a retrieval-augmented generation large language model framework for surgical decision support and workflow enhancement

Chin Siang Ong; Nicholas T Obey; Yanan Zheng; Arman Cohan; Eric B Schneider

doi:10.1038/s41746-024-01391-3

SurgeryLLM: a retrieval-augmented generation large language model framework for surgical decision support and workflow enhancement

NPJ Digit Med. 2024 Dec 18;7(1):364. doi: 10.1038/s41746-024-01391-3.

Authors

Chin Siang Ong^{1

2}, Nicholas T Obey³, Yanan Zheng⁴, Arman Cohan^{4

5}, Eric B Schneider³

Affiliations

¹ Department of Surgery, Yale School of Medicine, New Haven, CT, USA. [email protected].
² Harvard T.H. Chan School of Public Health, Boston, MA, USA. [email protected].
³ Department of Surgery, Yale School of Medicine, New Haven, CT, USA.
⁴ Department of Computer Science, Yale University, New Haven, CT, USA.
⁵ Wu Tsai Institute, Yale University, New Haven, CT, USA.

Abstract

SurgeryLLM, a large language model framework using Retrieval Augmented Generation demonstrably incorporated domain-specific knowledge from current evidence-based surgical guidelines when presented with patient-specific data. The successful incorporation of guideline-based information represents a substantial step toward enabling greater surgeon efficiency, improving patient safety, and optimizing surgical outcomes.