From Evidence-Based Medicine to Knowledge Graph: Retrieval-Augmented Generation for Sports Rehabilitation and a Domain Benchmark

TL;DR

This paper introduces SR-RAG, a novel framework that integrates evidence-based medicine principles into knowledge graph retrieval for sports rehabilitation, significantly improving evidence retrieval accuracy and relevance.

Contribution

It presents SR-RAG, combining PICO-aligned knowledge graph retrieval with Bayesian Evidence Tier Reranking, tailored for medical domains, and provides a new benchmark dataset.

Findings

Achieved high evidence recall and answer faithfulness scores.

Outperformed five baseline methods in evidence retrieval.

Clinicians rated the system highly on a Likert scale.

Abstract

Current medical retrieval-augmented generation (RAG) approaches overlook evidence-based medicine (EBM) principles, leading to two key gaps: (1) the lack of PICO alignment between queries and retrieved evidence, and (2) the absence of evidence hierarchy considerations during reranking. We present SR-RAG, an EBM-adapted GraphRAG framework that integrates the PICO framework into knowledge graph construction and retrieval, and proposes Bayesian Evidence Tier Reranking (BETR) to calibrate ranking scores by evidence grade without predefined weights. Validated in sports rehabilitation, we release a knowledge graph (357,844 nodes, 371,226 edges) and a benchmark of 1,637 QA pairs. SR-RAG achieves 0.812 evidence recall@10, 0.830 nugget coverage, 0.819 answer faithfulness, 0.882 semantic similarity, and 0.788 PICOT match accuracy, substantially outperforming five baselines. Five expert clinicians rated the system 4.66--4.84 on a 5-point Likert scale, and system rankings are preserved on a human-verified gold subset (n=80).