GraphRAG-ADR: a knowledge graph–enhanced approach for extracting Adverse Drug Reactions (ADRs) from patient narratives

Abstract

Adverse Drug Reaction (ADR) extraction from patient narratives is a challenging problem due to informal language, high lexical variability, and the gap between colloquial expressions and standardized medical terminology. Although large language models (LLMs) have improved extraction performance, they mainly rely on textual representations and don’t explicitly incorporate structured biomedical knowledge. In this work, we propose GraphRAG-ADR, a retrieval-augmented generation framework enhanced by a directed attributed knowledge graph. The proposed graph combines MedDRA hierarchical terminology, clinically validated drug–side-effect relationships from SIDER, and patient-reported ADR expressions from the CADEC dataset. This integration enables the representation of both formal medical concepts and real-world patient language. A hybrid retrieval mechanism selects and prioritizes relevant medical concepts using both semantic similarity and graph structure, and provides them as context to the LLM to improve the alignment between patient expressions and standardized ADR concepts. Experimental evaluation on the PsyTAR dataset shows that GraphRAG-ADR achieves a strict F1-score of 73.02% and a relaxed F1-score of 83.11%, outperforming existing approaches under the same evaluation settings. These results demonstrate that integrating structured biomedical knowledge with LLMs improves both accuracy and robustness.