HiRef: Leveraging Hierarchical Ontology and Network Refinement for Robust Medication Recommendation

TL;DR

HiRef is a novel medication recommendation framework that leverages hierarchical medical ontologies and refined co-occurrence networks to improve robustness and generalizability, especially under conditions of missing or unseen medical codes.

Contribution

The paper introduces HiRef, which combines hyperbolic embedding of ontologies with a prior-guided graph refinement to enhance medication recommendation accuracy and robustness in real-world EHR data.

Findings

Achieves strong performance on MIMIC-III and MIMIC-IV benchmarks.

Maintains high accuracy under simulated unseen-code scenarios.

Demonstrates robustness and interpretability through ablation studies.

Abstract

Medication recommendation is a crucial task for assisting physicians in making timely decisions from longitudinal patient medical records. However, real-world EHR data present significant challenges due to the presence of rarely observed medical entities and incomplete records that may not fully capture the clinical ground truth. While data-driven models trained on longitudinal Electronic Health Records often achieve strong empirical performance, they struggle to generalize under missing or novel conditions, largely due to their reliance on observed co-occurrence patterns. To address these issues, we propose Hierarchical Ontology and Network Refinement for Robust Medication Recommendation (HiRef), a unified framework that combines two complementary structures: (i) the hierarchical semantics encoded in curated medical ontologies, and (ii) refined co-occurrence patterns derived from real-world EHRs. We embed ontology entities in hyperbolic space, which naturally captures tree-like relationships and enables knowledge transfer through shared ancestors, thereby improving generalizability to unseen codes. To further improve robustness, we introduce a prior-guided sparse regularization scheme that refines the EHR co-occurrence graph by suppressing spurious edges while preserving clinically meaningful associations. Our model achieves strong performance on EHR benchmarks (MIMIC-III and MIMIC-IV) and maintains high accuracy under simulated unseen-code settings. Extensive experiments with comprehensive ablation studies demonstrate HiRef's resilience to unseen medical codes, supported by in-depth analyses of the learned sparsified graph structure and medical code embeddings.