Enhancing Coronary Revascularization Decisions: The Promising Role of Large Language Models as a Decision-Support Tool for Multidisciplinary Heart Team
Circulation: Cardiovascular Interventions · 2024
DOI: 10.1161/circinterventions.124.014201 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Circulation: Cardiovascular Interventions, 2024. Verfasst von Karin Sudri und 11 weiteren Autor:innen. Beteiligte Einrichtung: ARC Innovation Center, Sagol Big Data and AI Hub (K.S., M.C.-S.), Sheba Medical Center, Tel Hashomer, Israel. Hauptthemen laut MEDLINE: Clinical Decision-Making, Patient Care Team, Decision Support Techniques, Coronary Angiography. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 32 Literaturangaben.
Abstract (Originalsprache)
BACKGROUND: While clinical practice guidelines advocate for multidisciplinary heart team (MDHT) discussions in coronary revascularization, variability in implementation across health care settings remains a challenge. This variability could potentially be addressed by language learning models like ChatGPT, offering decision-making support in diverse health care environments. Our study aims to critically evaluate the concordance between recommendations made by MDHT and those generated by language learning models in coronary revascularization decision-making. METHODS: From March 2023 to July 2023, consecutive coronary angiography cases (n=86) that were referred for revascularization (either percutaneous or surgical) were analyzed using both ChatGPT-3.5 and ChatGPT-4. Case presentation formats included demographics, medical background, detailed description of angiographic findings, and SYNTAX score (Synergy Between Percutaneous Coronary Intervention With Taxus and Cardiac Surgery; I and II), which were presented in 3 different formats. The recommendations of the models were compared with those of an MDHT. RESULTS: ChatGPT-4 showed high concordance with decisions made by the MDHT (accuracy 0.82, sensitivity 0.8, specificity 0.83, and kappa 0.59), while ChatGPT-3.5 (0.67, 0.27, 0.84, and 0.12, respectively) showed lower concordance. Entropy and Fleiss kappa of ChatGPT-4 were 0.09 and 0.9, respectively, indicating high reliability and repeatability. The best correlation between ChatGPT-4 and MDHT was achieved when clinical cases were presented in a detailed context. Specific subgroups of patients yielded high accuracy (>0.9) of ChatGPT-4, including those with left main disease, 3 vessel disease, and diabetic patients. CONCLUSIONS: The present study demonstrates that advanced language learning models like ChatGPT-4 may be able to predict clinical recommendations for coronary artery disease revascularization with reasonable accuracy, especially in specific patient groups, underscoring their potential role as a supportive tool in clinical decision-making.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- ARC Innovation Center, Sagol Big Data and AI Hub (K.S., M.C.-S.), Sheba Medical Center, Tel Hashomer, Israel.
- Sheba Education Authority (I.M.-F.), Sheba Medical Center, Tel Hashomer, Israel.
- The Graduate School of Business Administration (R.R.-G.), Bar-Ilan University, Ramat-Gan, Israel.
- Data Science Institute (R.R.-G.), Bar-Ilan University, Ramat-Gan, Israel.
- ARC Innovation Center (N.B.), Sheba Medical Center, Tel Hashomer, Israel.
- Software and Information Systems Engineering (N.B.), Ben-Gurion University of the Negev, Be'er Sheva, Israel.
ORCID-Profile: Karin Sudri, Noam Barda, Sergei Amunts, Zachi Itzhak Attia, Mohamad Alkhouli, Amitai Segev, Michal Cohen-Shelly, Israel Moshe Barbash
Zitieren
APA
Sudri, K., Motro-Feingold, I., Ramon-Gonen, R., Barda, N., Klang, E., Fefer, P., Amunts, S., Attia, Z. I., Alkhouli, M., Segev, A., Cohen-Shelly, M., & Barbash, I. M. (2024). Enhancing Coronary Revascularization Decisions: The Promising Role of Large Language Models as a Decision-Support Tool for Multidisciplinary Heart Team. Circulation: Cardiovascular Interventions. https://doi.org/10.1161/circinterventions.124.014201
Vancouver
Sudri K, Motro-Feingold I, Ramon-Gonen R, Barda N, Klang E, Fefer P, et al. Enhancing Coronary Revascularization Decisions: The Promising Role of Large Language Models as a Decision-Support Tool for Multidisciplinary Heart Team. Circulation: Cardiovascular Interventions. 2024. doi:10.1161/circinterventions.124.014201
BibTeX
@article{Sudri2024,
author = {Sudri, Karin and Motro-Feingold, Iris and Ramon-Gonen, Roni and Barda, Noam and Klang, Eyal and Fefer, Paul and Amunts, Sergei and Attia, Zachi Itzhak and Alkhouli, Mohamad and Segev, Amitai and Cohen-Shelly, Michal and Barbash, Israel Moshe},
title = {Enhancing Coronary Revascularization Decisions: The Promising Role of Large Language Models as a Decision-Support Tool for Multidisciplinary Heart Team},
journal = {Circulation: Cardiovascular Interventions},
year = {2024},
doi = {10.1161/circinterventions.124.014201}
}
EUVIMED