PICOs-RAG: PICO-supported Query Rewriting for Retrieval-Augmented Generation in Evidence-Based Medicine

TL;DR

This paper introduces PICOs-RAG, a query rewriting method that uses PICO format to improve retrieval accuracy and efficiency in evidence-based medicine, enhancing large language models' medical assistance capabilities.

Contribution

The paper proposes a novel PICO-supported query rewriting approach that significantly improves retrieval relevance and efficiency in clinical scenarios for evidence-based medicine.

Findings

Up to 8.8% improvement in retrieval relevance.

Enhanced performance of large language models in medical query answering.

More accurate and reliable medical information retrieval.

Abstract

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.