DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients

TL;DR

DoctorRAG is a novel retrieval-augmented generation framework that combines explicit medical knowledge with patient case experience using textual gradients, aiming to emulate human-like clinical reasoning.

Contribution

It introduces a hybrid retrieval mechanism and a Med-TextGrad module to integrate knowledge and case experience, improving medical response accuracy.

Findings

Outperforms baseline RAG models on multilingual, multitask datasets.

Achieves more accurate and relevant medical responses.

Demonstrates the effectiveness of textual gradients in medical reasoning.

Abstract

Existing medical RAG systems mainly leverage knowledge from medical knowledge bases, neglecting the crucial role of experiential knowledge derived from similar patient cases -- a key component of human clinical reasoning. To bridge this gap, we propose DoctorRAG, a RAG framework that emulates doctor-like reasoning by integrating both explicit clinical knowledge and implicit case-based experience. DoctorRAG enhances retrieval precision by first allocating conceptual tags for queries and knowledge sources, together with a hybrid retrieval mechanism from both relevant knowledge and patient. In addition, a Med-TextGrad module using multi-agent textual gradients is integrated to ensure that the final output adheres to the retrieved knowledge and patient query. Comprehensive experiments on multilingual, multitask datasets demonstrate that DoctorRAG significantly outperforms strong baseline RAG models and gains improvements from iterative refinements. Our approach generates more accurate, relevant, and comprehensive responses, taking a step towards more doctor-like medical reasoning systems.