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

2025-08-14

AI Summary

To address the insufficient robustness of drug recommendation in electronic health record (EHR) data—caused by rare diseases and incomplete clinical documentation—this paper proposes a novel method integrating medical ontology semantics with real-world clinical co-occurrence patterns. We innovatively model ontology hierarchies in hyperspherical space and introduce a prior-guided sparse regularized graph optimization to jointly constrain the EHR co-occurrence network, effectively suppressing spurious associations and enabling cross-code knowledge transfer. The framework unifies semantic priors with data-driven signals, significantly improving generalization to unseen medical codes on MIMIC-III and MIMIC-IV; it outperforms state-of-the-art methods across key metrics. Ablation studies confirm the substantial contributions of each component to overall robustness. This work establishes a new paradigm for trustworthy drug recommendation in sparse, long-tail clinical settings.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Data Mining & Knowledge Management: Recommender Systems
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

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.

Problem

• Addresses rarely observed medical entities in EHR data
• Improves generalization under missing or novel conditions
• Refines EHR co-occurrence graphs for robust recommendations

Innovation

• Hierarchical ontology in hyperbolic space
• Prior-guided sparse regularization scheme
• Refined EHR co-occurrence graph structure