BLUEmed: 基于检索增强的多智能体辩论用于临床错误检测
BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection
AI总结：
提出BLUEmed框架，结合混合检索增强生成与多智能体辩论，通过分解临床笔记、检索证据、专家辩论及安全层过滤，在术语替换错误检测中达到最优性能。
摘要：
临床笔记中的术语替换错误（即一个医学术语被一个语言上有效但临床不同的术语替换）对医疗保健中的自动错误检测构成了持续挑战。我们引入了BLUEmed，一个多智能体辩论框架，增强有混合检索增强生成（RAG），该框架结合了基于证据的推理和多视角验证用于临床错误检测。BLUEmed将每个临床笔记分解为聚焦的子查询，通过密集、稀疏和在线检索检索来源分区的证据，并分配两个具有不同知识库的领域专家智能体以产生独立分析；当专家意见不一致时，一轮结构化的反论证和跨来源裁决解决冲突，随后是一个级联安全层，过滤常见的假阳性模式。我们在一个临床术语替换检测基准上评估BLUEmed，在零样本和少样本提示下，使用多个骨干模型（涵盖专有和开源系列）。实验结果表明，在少样本提示下，BLUEmed达到了最佳准确率（69.13%）、ROC-AUC（74.45%）和PR-AUC（72.44%），优于单智能体RAG和仅辩论基线。跨六个骨干模型和两种提示策略的进一步分析证实，检索增强和结构化辩论是互补的，并且该框架从具有足够指令遵循和临床语言理解的模型中受益最大。
英文摘要：
Terminology substitution errors in clinical notes, where one medical term is replaced by a linguistically valid but clinically different term, pose a persistent challenge for automated error detection in healthcare. We introduce BLUEmed, a multi-agent debate framework augmented with hybrid Retrieval-Augmented Generation (RAG) that combines evidence-grounded reasoning with multi-perspective verification for clinical error detection. BLUEmed decomposes each clinical note into focused sub-queries, retrieves source-partitioned evidence through dense, sparse, and online retrieval, and assigns two domain expert agents distinct knowledge bases to produce independent analyses; when the experts disagree, a structured counter-argumentation round and cross-source adjudication resolve the conflict, followed by a cascading safety layer that filters common false-positive patterns. We evaluate BLUEmed on a clinical terminology substitution detection benchmark under both zero-shot and few-shot prompting with multiple backbone models spanning proprietary and open-source families. Experimental results show that BLUEmed achieves the best accuracy (69.13%), ROC-AUC (74.45%), and PR-AUC (72.44%) under few-shot prompting, outperforming both single-agent RAG and debate-only baselines. Further analyses across six backbone models and two prompting strategies confirm that retrieval augmentation and structured debate are complementary, and that the framework benefits most from models with sufficient instruction-following and clinical language understanding.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
