Traceable Drug Recommendation over Medical Knowledge Graphs

2025-10-31

AI Summary

Current drug recommendation systems lack interpretability, limiting their applicability in high-stakes clinical decision-making. To address this, we propose TraceDR—a novel framework that jointly generates drug recommendations and explanatory evidence chains for the first time. TraceDR leverages a medical knowledge graph to implement a multi-task learning model that simultaneously predicts optimal drugs and their supporting biomedical rationales (e.g., disease–symptom–drug paths). It incorporates an entity linking module and a path reasoning module to ensure traceability and justification of recommendations. Furthermore, we introduce an automated patient health record generator and release DrugRec—the first large-scale, explainable drug recommendation benchmark. Extensive experiments demonstrate that TraceDR significantly improves both recommendation accuracy and transparency on DrugRec, achieves broader coverage of disease–drug associations, and delivers clinically actionable, verifiable, and trustworthy decision support.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Drug recommendation (DR) systems aim to support healthcare professionals in selecting appropriate medications based on patients' medical conditions. State-of-the-art approaches utilize deep learning techniques for improving DR, but fall short in providing any insights on the derivation process of recommendations -- a critical limitation in such high-stake applications. We propose TraceDR, a novel DR system operating over a medical knowledge graph (MKG), which ensures access to large-scale and high-quality information. TraceDR simultaneously predicts drug recommendations and related evidence within a multi-task learning framework, enabling traceability of medication recommendations. For covering a more diverse set of diseases and drugs than existing works, we devise a framework for automatically constructing patient health records and release DrugRec, a new large-scale testbed for DR.

Problem

• Predicting drug recommendations using medical knowledge graphs
• Providing traceable evidence for medication decision processes
• Automating health record construction for diverse disease coverage

Innovation

• Uses medical knowledge graphs for drug recommendation
• Multi-task learning predicts drugs and evidence simultaneously
• Automatically constructs patient records for diverse disease coverage