Evolution of a Large Language Model for Preoperative Assessment Based on the Japanese Circulation Society 2022 Guideline on Perioperative Cardiovascular Assessment and Management for Non-Cardiac Surgery

Takahiro Kamihara; Masanori Tabuchi; Takuya Omura; Yumi Suzuki; Tsukasa Aritake; Akihiro Hirashiki; Manabu Kokubo; Atsuya Shimizu

doi:10.1253/circrep.CR-24-0019

Rapid Communications

Evolution of a Large Language Model for Preoperative Assessment Based on the Japanese Circulation Society 2022 Guideline on Perioperative Cardiovascular Assessment and Management for Non-Cardiac Surgery

Takahiro Kamihara ^† , Masanori Tabuchi ^†, Takuya Omura, Yumi Suzuki, Tsukasa Aritake, Akihiro Hirashiki, Manabu Kokubo, Atsuya Shimizu

Author information

Takahiro Kamihara ^† Corresponding author
Department of Cardiology, National Center for Geriatrics and Gerontology [Japan]
Masanori Tabuchi ^†
Department of Nursing, National Center for Geriatrics and Gerontology [Japan]
Takuya Omura
Department of Metabolism, National Center for Geriatrics and Gerontology [Japan]
Yumi Suzuki
Department of Surgery, National Center for Geriatrics and Gerontology [Japan]
Tsukasa Aritake
Department of Surgery, National Center for Geriatrics and Gerontology [Japan]
Akihiro Hirashiki
Department of Cardiology, National Center for Geriatrics and Gerontology [Japan]
Manabu Kokubo
Department of Cardiology, National Center for Geriatrics and Gerontology [Japan]
Atsuya Shimizu
Department of Cardiology, National Center for Geriatrics and Gerontology [Japan]
Author contributions

†These authors contributed equally: Takahiro Kamihara, Masanori Tabuchi

Keywords: Guidelines, Large language model, Virtual scenarios

JOURNAL OPEN ACCESS FULL-TEXT HTML

2024 Volume 6 Issue 4 Pages 142-148

DOI https://doi.org/10.1253/circrep.CR-24-0019

Browse “Advance online publication” version

Details

Abstract

Background: The Japanese Circulation Society 2022 Guideline on Perioperative Cardiovascular Assessment and Management for Non-Cardiac Surgery standardizes preoperative cardiovascular assessments. The present study investigated the efficacy of a large language model (LLM) in providing accurate responses meeting the JCS 2022 Guideline.

Methods and Results: Data on consultation requests, physicians’ cardiovascular records, and patients’ response content were analyzed. Virtual scenarios were created using real-world clinical data, and a LLM was then consulted for such scenarios.

Conclusions: Google BARD could accurately provide responses in accordance with the JCS 2022 Guideline in low-risk cases. Google Gemini has significantly improved its accuracy in intermediate- and high-risk cases.

Corresponding author

Register with J-STAGE for free!