Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jie, Wang, Wenxuan, Ma, Zizhan, Huang, Guolin, SU, Yihang, Chang, Kao-Jung, Chen, Wenting, Li, Haoliang, Shen, Linlin, Lyu, Michael
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917000261926912
author Liu, Jie
Wang, Wenxuan
Ma, Zizhan
Huang, Guolin
SU, Yihang
Chang, Kao-Jung
Chen, Wenting
Li, Haoliang
Shen, Linlin
Lyu, Michael
author_facet Liu, Jie
Wang, Wenxuan
Ma, Zizhan
Huang, Guolin
SU, Yihang
Chang, Kao-Jung
Chen, Wenting
Li, Haoliang
Shen, Linlin
Lyu, Michael
contents Clinical decision making (CDM) is a complex, dynamic process crucial to healthcare delivery, yet it remains a significant challenge for artificial intelligence systems. While Large Language Model (LLM)-based agents have been tested on general medical knowledge using licensing exams and knowledge question-answering tasks, their performance in the CDM in real-world scenarios is limited due to the lack of comprehensive testing datasets that mirror actual medical practice. To address this gap, we present MedChain, a dataset of 12,163 clinical cases that covers five key stages of clinical workflow. MedChain distinguishes itself from existing benchmarks with three key features of real-world clinical practice: personalization, interactivity, and sequentiality. Further, to tackle real-world CDM challenges, we also propose MedChain-Agent, an AI system that integrates a feedback mechanism and a MCase-RAG module to learn from previous cases and adapt its responses. MedChain-Agent demonstrates remarkable adaptability in gathering information dynamically and handling sequential clinical tasks, significantly outperforming existing approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2412_01605
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence
Liu, Jie
Wang, Wenxuan
Ma, Zizhan
Huang, Guolin
SU, Yihang
Chang, Kao-Jung
Chen, Wenting
Li, Haoliang
Shen, Linlin
Lyu, Michael
Computation and Language
Artificial Intelligence
Clinical decision making (CDM) is a complex, dynamic process crucial to healthcare delivery, yet it remains a significant challenge for artificial intelligence systems. While Large Language Model (LLM)-based agents have been tested on general medical knowledge using licensing exams and knowledge question-answering tasks, their performance in the CDM in real-world scenarios is limited due to the lack of comprehensive testing datasets that mirror actual medical practice. To address this gap, we present MedChain, a dataset of 12,163 clinical cases that covers five key stages of clinical workflow. MedChain distinguishes itself from existing benchmarks with three key features of real-world clinical practice: personalization, interactivity, and sequentiality. Further, to tackle real-world CDM challenges, we also propose MedChain-Agent, an AI system that integrates a feedback mechanism and a MCase-RAG module to learn from previous cases and adapt its responses. MedChain-Agent demonstrates remarkable adaptability in gathering information dynamically and handling sequential clinical tasks, significantly outperforming existing approaches.
title Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.01605