oRetrieval Augmented Generation for 10 Large Language Models and its Generalizability in Assessing Medical Fitness

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ke, Yu He, Jin, Liyuan, Elangovan, Kabilan, Abdullah, Hairil Rizal, Liu, Nan, Sia, Alex Tiong Heng, Soh, Chai Rick, Tung, Joshua Yi Min, Ong, Jasmine Chiat Ling, Kuo, Chang-Fu, Wu, Shao-Chun, Kovacheva, Vesela P., Ting, Daniel Shu Wei
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913541762580480
author Ke, Yu He
Jin, Liyuan
Elangovan, Kabilan
Abdullah, Hairil Rizal
Liu, Nan
Sia, Alex Tiong Heng
Soh, Chai Rick
Tung, Joshua Yi Min
Ong, Jasmine Chiat Ling
Kuo, Chang-Fu
Wu, Shao-Chun
Kovacheva, Vesela P.
Ting, Daniel Shu Wei
author_facet Ke, Yu He
Jin, Liyuan
Elangovan, Kabilan
Abdullah, Hairil Rizal
Liu, Nan
Sia, Alex Tiong Heng
Soh, Chai Rick
Tung, Joshua Yi Min
Ong, Jasmine Chiat Ling
Kuo, Chang-Fu
Wu, Shao-Chun
Kovacheva, Vesela P.
Ting, Daniel Shu Wei
contents Large Language Models (LLMs) show potential for medical applications but often lack specialized clinical knowledge. Retrieval Augmented Generation (RAG) allows customization with domain-specific information, making it suitable for healthcare. This study evaluates the accuracy, consistency, and safety of RAG models in determining fitness for surgery and providing preoperative instructions. We developed LLM-RAG models using 35 local and 23 international preoperative guidelines and tested them against human-generated responses. A total of 3,682 responses were evaluated. Clinical documents were processed using Llamaindex, and 10 LLMs, including GPT3.5, GPT4, and Claude-3, were assessed. Fourteen clinical scenarios were analyzed, focusing on seven aspects of preoperative instructions. Established guidelines and expert judgment were used to determine correct responses, with human-generated answers serving as comparisons. The LLM-RAG models generated responses within 20 seconds, significantly faster than clinicians (10 minutes). The GPT4 LLM-RAG model achieved the highest accuracy (96.4% vs. 86.6%, p=0.016), with no hallucinations and producing correct instructions comparable to clinicians. Results were consistent across both local and international guidelines. This study demonstrates the potential of LLM-RAG models for preoperative healthcare tasks, highlighting their efficiency, scalability, and reliability.
format Preprint
id arxiv_https___arxiv_org_abs_2410_08431
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle oRetrieval Augmented Generation for 10 Large Language Models and its Generalizability in Assessing Medical Fitness
Ke, Yu He
Jin, Liyuan
Elangovan, Kabilan
Abdullah, Hairil Rizal
Liu, Nan
Sia, Alex Tiong Heng
Soh, Chai Rick
Tung, Joshua Yi Min
Ong, Jasmine Chiat Ling
Kuo, Chang-Fu
Wu, Shao-Chun
Kovacheva, Vesela P.
Ting, Daniel Shu Wei
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) show potential for medical applications but often lack specialized clinical knowledge. Retrieval Augmented Generation (RAG) allows customization with domain-specific information, making it suitable for healthcare. This study evaluates the accuracy, consistency, and safety of RAG models in determining fitness for surgery and providing preoperative instructions. We developed LLM-RAG models using 35 local and 23 international preoperative guidelines and tested them against human-generated responses. A total of 3,682 responses were evaluated. Clinical documents were processed using Llamaindex, and 10 LLMs, including GPT3.5, GPT4, and Claude-3, were assessed. Fourteen clinical scenarios were analyzed, focusing on seven aspects of preoperative instructions. Established guidelines and expert judgment were used to determine correct responses, with human-generated answers serving as comparisons. The LLM-RAG models generated responses within 20 seconds, significantly faster than clinicians (10 minutes). The GPT4 LLM-RAG model achieved the highest accuracy (96.4% vs. 86.6%, p=0.016), with no hallucinations and producing correct instructions comparable to clinicians. Results were consistent across both local and international guidelines. This study demonstrates the potential of LLM-RAG models for preoperative healthcare tasks, highlighting their efficiency, scalability, and reliability.
title oRetrieval Augmented Generation for 10 Large Language Models and its Generalizability in Assessing Medical Fitness
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.08431