HADRec: A Hierarchy-Aware Drug Recommendation Framework by Fusing Molecular Knowledge and Electronic Health Record

2026-09-30

AI Summary

This study addresses the limitations of existing medication recommendation systems that overlook molecular structures and fail to leverage the hierarchical logic of the Anatomical Therapeutic Chemical (ATC) classification. To this end, we propose a hierarchy-aware multimodal framework that integrates LLaMA-7B and ChemBERTa to encode electronic health records and molecular features, respectively, facilitating cross-modal interaction via a cross-attention mechanism. Furthermore, we introduce a novel hierarchical predictor combining a molecular knowledge graph with an ATC consistency constraint loss, ensuring that recommendations strictly adhere to pharmacological taxonomies. Extensive experiments on the MIMIC dataset demonstrate that the proposed method achieves state-of-the-art performance while exhibiting strong generalization capability, favorable calibration, and clinical interpretability.

Abstract

Accurate medication recommendation is central to clinical decision-making, directly determining therapeutic efficacy and patient safety. However, existing methods suffer from two key limitations: drugs are often abstracted as discrete tokens, ignoring their molecular structures and pharmacological mechanisms, and the commonly used "flat" recommendation paradigm fails to leverage the hierarchical logic of the internationally standardized Anatomical Therapeutic Chemical (ATC) classification system. To address these issues, we propose HADRec, a Hierarchy-Aware Drug Recommendation framework that integrates molecular knowledge with electronic health records (EHRs). HADRec employs LLaMA-7B to encode clinical notes for rich patient representations and ChemBERTa to encode drug Simplified Molecular Input Line Entry System strings, building a global molecular knowledge base. A cross-attention mechanism then performs deep multimodal fusion between patient states and drug features. The framework further incorporates a hierarchical predictor and a novel consistency constraint loss to enforce strict adherence to ATC logical dependencies. Extensive experiments on MIMIC-III demonstrate that HADRec achieves state-of-the-art performance across Jaccard, F1, and PR-AUC. External validation on MIMIC-IV confirms strong generalization under distribution shifts, and calibration analysis shows well-calibrated predictive confidence on MIMIC-IV with ECE = 0.04, and Brier = 0.06. Counterfactual evaluation reveals clinically aligned reasoning, disentangling disease-specific treatments from general care. Together, these results establish HADRec as a high-performance, interpretable, and clinically grounded pathway toward safe and reliable AI-driven medication recommendation.

Problem

• Drug Recommendation
• Molecular Knowledge
• Electronic Health Records
• ATC Classification
• Hierarchical Modeling

Innovation

• Hierarchy-Aware Recommendation
• Multimodal Fusion
• Molecular Knowledge
• Large Language Models
• Consistency Constraint Loss