多轮诊断检索增强生成框架：模拟临床推理
The Multi-Round Diagnostic RAG Framework for Emulating Clinical Reasoning
AI总结：
提出MRD-RAG框架，结合构建的DiagnosGraph知识图谱，通过多轮对话模拟临床推理，在四个医学基准上提升LLM诊断准确性。
摘要：
近年来，准确且快速地部署医疗大型语言模型（LLMs）已成为一种趋势。其中，检索增强生成（RAG）因其快速部署和隐私保护而受到关注。然而，阻碍RAG在医疗诊断中实际部署的挑战在于：患者口语化描述与医学知识库中的专业术语之间存在语义鸿沟。我们尝试从数据角度和方法角度解决这一挑战。首先，为解决现有知识库中的语义鸿沟，我们构建了DiagnosGraph，一个涵盖现代医学和中医的通才知识图谱。它包含876种常见疾病，图谱拥有7,997个节点和37,201条三元组。为弥合口语化患者叙述与学术医学知识之间的鸿沟，DiagnosGraph还引入了1,908份病历，通过形式化患者主诉并提出医学诊断。其次，我们提出了多轮诊断检索增强生成（MRD-RAG）框架。它利用多轮对话来细化诊断可能性，模拟医生的临床推理。在四个医学基准上进行的实验，并由人类医生进行评估，表明MRD-RAG增强了LLMs的诊断性能，突显了其使自动诊断更准确且更符合人类期望的潜力。
英文摘要：
In recent years, accurately and quickly deploying medical large language models (LLMs) has become a trend. Among these, retrieval-augmented generation (RAG) has garnered attention due to rapid deployment and privacy protection. However, the challenge hinder the practical deployment of RAG for medical diagnosis: the semantic gap between colloquial patient descriptions and the professional terminology within medical knowledge bases. We try to address the challenge from the data perspective and the method perspective. First, to address the semantic gap in existing knowledge bases, we construct DiagnosGraph, a generalist knowledge graph covering both modern medicine and Traditional Chinese Medicine. It contains 876 common diseases with the graph of 7,997 nodes and 37,201 triples. To bridge the gap between colloquial patient narratives and academic medical knowledge, DiagnosGraph also introduces $1,908$ medical record by formalizing the patient chief complaint and proposing a medical diagnosis. Second, we introduce the Multi-Round Diagnostic RAG (MRD-RAG) framework. It utilizes a multi-round dialogue to refine diagnostic possibilities, emulating the clinical reasoning of a physician. Experiments conducted on four medical benchmarks, with evaluations by human physicians, demonstrate that MRD-RAG enhances the diagnostic performance of LLMs, highlighting its potential to make automated diagnosis more accurate and human-aligned.
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。
