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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lu, Yuxing, Fu, Gecheng, Wu, Wei, Zhao, Xukai, Goi, Sin Yee, Wang, Jinzhuo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910968556027904
author Lu, Yuxing
Fu, Gecheng
Wu, Wei
Zhao, Xukai
Goi, Sin Yee
Wang, Jinzhuo
author_facet Lu, Yuxing
Fu, Gecheng
Wu, Wei
Zhao, Xukai
Goi, Sin Yee
Wang, Jinzhuo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19538
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients
Lu, Yuxing
Fu, Gecheng
Wu, Wei
Zhao, Xukai
Goi, Sin Yee
Wang, Jinzhuo
Computation and Language
Artificial Intelligence
Computational Engineering, Finance, and Science
Information Retrieval
Multiagent Systems
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.
title DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients
topic Computation and Language
Artificial Intelligence
Computational Engineering, Finance, and Science
Information Retrieval
Multiagent Systems
url https://arxiv.org/abs/2505.19538