DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients
This addresses the need for more doctor-like reasoning in medical AI systems, though it is incremental as it builds on existing RAG frameworks.
The paper tackles the problem of medical RAG systems lacking experiential knowledge from patient cases by proposing DoctorRAG, which integrates clinical knowledge and case-based experience, resulting in significant performance improvements over baseline models on multilingual, multitask datasets.
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.