用医学检索标准重构查询，让AI更准找病历证据
PICOs-RAG: PICO-supported Query Rewriting for Retrieval-Augmented Generation in Evidence-Based Medicine
- 将用户提问转为符合PICO标准的专业格式
- 在真实临床查询中提升检索相关性达8.8%
- 适合需要精准医疗证据的医生或研究者
循证医学研究至关重要，需为医患需求提供可靠的理论支持以减少医疗事故。传统依赖人工检索文献效率低且主观性强。现有检索增强生成（RAG）方法在复杂临床查询中表现不佳，尤其当问题信息缺失或表述模糊时，易召回无关文献并生成无效回答。为此，本文提出PICOs-RAG，通过PICO框架（患者、干预、对照、结局）将原始查询扩展并规范化，提取关键检索要素。该方法显著提升检索效率与相关性，在实验中相较基线最高提升8.8%。有效增强大模型在循证医学场景下的可靠性，使其成为可信的医疗辅助工具。
原文摘要 · Abstract (English)
Evidence-based medicine (EBM) research has always been of paramount importance. It is important to find appropriate medical theoretical support for the needs from physicians or patients to reduce the occurrence of medical accidents. This process is often carried out by human querying relevant literature databases, which lacks objectivity and efficiency. Therefore, researchers utilize retrieval-augmented generation (RAG) to search for evidence and generate responses automatically. However, current RAG methods struggle to handle complex queries in real-world clinical scenarios. For example, when queries lack certain information or use imprecise language, the model may retrieve irrelevant evidence and generate unhelpful answers. To address this issue, we present the PICOs-RAG to expand the user queries into a better format. Our method can expand and normalize the queries into professional ones and use the PICO format, a search strategy tool present in EBM, to extract the most important information used for retrieval. This approach significantly enhances retrieval efficiency and relevance, resulting in up to an 8.8\% improvement compared to the baseline evaluated by our method. Thereby the PICOs-RAG improves the performance of the large language models into a helpful and reliable medical assistant in EBM.
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。