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

TL;DR

MedChain introduces a comprehensive clinical dataset and an adaptive AI agent that enhances the performance of large language models in real-world clinical decision-making by emphasizing personalization, interactivity, and sequential reasoning.

Contribution

The paper presents MedChain, a new dataset of clinical cases, and MedChain-Agent, an AI system that improves LLM-based clinical decision-making through feedback and sequential learning.

Findings

MedChain-Agent outperforms existing approaches in clinical tasks.

The dataset covers five key stages of clinical workflow.

The system demonstrates adaptability in dynamic information gathering.

Abstract

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.