用临床协议指导大模型生成准确的医学报告结构
MedPAO: A Protocol-Driven Agent for Structuring Medical Reports
- 基于医疗协议设计计划-执行-观察循环，确保推理可验证
- 概念分类任务F1得分0.96，专家评分4.52/5高于基线模型
- 适合需高可靠性的医学报告自动化场景
将大型语言模型（LLMs）应用于临床数据结构化时，常因事实幻觉和无法遵循领域规则而受限。为此，我们提出MedPAO，一种新型代理框架，通过依托如胸部X光片分析的ABCDEF协议，确保操作的准确性与可验证性。MedPAO将报告结构化任务分解为由计划-执行-观察（PAO）循环和专用工具管理的透明流程。该协议驱动方法为不透明的单体模型提供了可验证替代方案。实验评估显示，该方法在关键子任务概念分类上达到0.96的F1分数。值得注意的是，放射科专家和临床医生对最终结构化输出的平均评分为4.52/5，表明其可靠性优于仅依赖大语言模型的基础方法。代码已公开：https://github.com/MiRL-IITM/medpao-agent。
原文摘要 · Abstract (English)
The deployment of Large Language Models (LLMs) for structuring clinical data is critically hindered by their tendency to hallucinate facts and their inability to follow domain-specific rules. To address this, we introduce MedPAO, a novel agentic framework that ensures accuracy and verifiable reasoning by grounding its operation in established clinical protocols such as the ABCDEF protocol for CXR analysis. MedPAO decomposes the report structuring task into a transparent process managed by a Plan-Act-Observe (PAO) loop and specialized tools. This protocol-driven method provides a verifiable alternative to opaque, monolithic models. The efficacy of our approach is demonstrated through rigorous evaluation: MedPAO achieves an F1-score of 0.96 on the critical sub-task of concept categorization. Notably, expert radiologists and clinicians rated the final structured outputs with an average score of 4.52 out of 5, indicating a level of reliability that surpasses baseline approaches relying solely on LLM-based foundation models. The code is available at: https://github.com/MiRL-IITM/medpao-agent
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。