HypeMed: Enhancing Medication Recommendations with Hypergraph-Based Patient Relationships

2026-03-18

AI Summary

Existing drug recommendation methods struggle to simultaneously model high-order combinatorial semantics within a single visit and dynamic dependencies across multiple visits, leading to inaccurate inference of patients’ clinical states. To address this limitation, this work proposes HypeMed—the first hypergraph-based two-stage framework. It first constructs a globally consistent embedding space via knowledge-aware contrastive pretraining (MedRep), then leverages a dynamic similarity retrieval module (SimMR) to integrate longitudinal medical history for refined recommendations within this space. HypeMed uniquely unifies intra-visit high-order relationships and inter-visit dynamic retrieval, incorporating hypergraph neural networks and drug–drug interaction (DDI)-aware prediction mechanisms. Experiments on real-world datasets demonstrate that HypeMed significantly improves recommendation accuracy while effectively reducing the risk of adverse drug interactions.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Medication recommendations aim to generate safe and effective medication sets from health records. However, accurately recommending medications hinges on inferring a patient's latent clinical condition from sparse and noisy observations, which requires both (i) preserving the visit-level combinatorial semantics of co-occurring entities and (ii) leveraging informative historical references through effective, visit-conditioned retrieval. Most existing methods fall short in one of both aspects: graph-based modeling often fragments higher-order intra-visit patterns into pairwise relations, while inter-visit augmentation methods commonly exhibit an imbalance between learning a globally stable representation space and performing dynamic retrieval within it. To address these limitations, this paper proposes HypeMed, a two-stage hypergraph-based framework unifying intra-visit coherence modeling and inter-visit augmentation. HypeMed consists of two core modules: MedRep for representation pre-training, and SimMR for similarity-enhanced recommendation. In the first stage, MedRep encodes clinical visits as hyperedges via knowledge-aware contrastive pre-training, creating a globally consistent, retrieval-friendly embedding space. In the second stage, SimMR performs dynamic retrieval within this space, fusing retrieved references with the patient's longitudinal data to refine medication prediction. Evaluation on real-world benchmarks shows that HypeMed outperforms state-of-the-art baselines in both recommendation precision and DDI reduction, simultaneously enhancing the effectiveness and safety of clinical decision support.

Problem

• medication recommendation
• hypergraph
• clinical decision support
• patient representation
• visit-level semantics

Innovation

• hypergraph
• medication recommendation
• contrastive pre-training
• dynamic retrieval
• clinical decision support