ClinicalAgent: Clinical Trial Multi-Agent System with Large Language Model-based Reasoning
This work addresses the problem of limited external knowledge access in clinical trial applications for researchers and practitioners, representing an incremental advancement by combining existing methods in a novel domain-specific context.
The paper tackled the challenge of applying large language models and multi-agent systems to clinical trial tasks by proposing ClinicalAgent, which integrates GPT-4 with multi-agent architectures and reasoning technologies, achieving a PR-AUC of 0.7908 in clinical trial outcome prediction and a 0.3326 improvement over standard prompting methods.
Large Language Models (LLMs) and multi-agent systems have shown impressive capabilities in natural language tasks but face challenges in clinical trial applications, primarily due to limited access to external knowledge. Recognizing the potential of advanced clinical trial tools that aggregate and predict based on the latest medical data, we propose an integrated solution to enhance their accessibility and utility. We introduce Clinical Agent System (ClinicalAgent), a clinical multi-agent system designed for clinical trial tasks, leveraging GPT-4, multi-agent architectures, LEAST-TO-MOST, and ReAct reasoning technology. This integration not only boosts LLM performance in clinical contexts but also introduces novel functionalities. The proposed method achieves competitive predictive performance in clinical trial outcome prediction (0.7908 PR-AUC), obtaining a 0.3326 improvement over the standard prompt Method. Publicly available code can be found at https://anonymous.4open.science/r/ClinicalAgent-6671.