Dual-Pathway Fusion of EHRs and Knowledge Graphs for Predicting Unseen Drug-Drug Interactions

TL;DR

This paper presents a novel dual-pathway fusion system combining electronic health records and knowledge graphs to predict unseen drug-drug interactions with high precision and interpretability, enabling zero-shot inference.

Contribution

It introduces a system that conditions knowledge graph relation scoring on patient EHRs and distills this into an EHR-only model for zero-shot drug interaction prediction.

Findings

Maintains high precision across multi-institution data

Produces mechanism-specific, clinically consistent predictions

Reduces false alerts while preserving overall detection performance

Abstract

Drug-drug interactions (DDIs) remain a major source of preventable harm, and many clinically important mechanisms are still unknown. Existing models either rely on pharmacologic knowledge graphs (KGs), which fail on unseen drugs, or on electronic health records (EHRs), which are noisy, temporal, and site-dependent. We introduce, to our knowledge, the first system that conditions KG relation scoring on patient-level EHR context and distills that reasoning into an EHR-only model for zero-shot inference. A fusion "Teacher" learns mechanism-specific relations for drug pairs represented in both sources, while a distilled "Student" generalizes to new or rarely used drugs without KG access at inference. Both operate under a shared ontology (set) of pharmacologic mechanisms (drug relations) to produce interpretable, auditable alerts rather than opaque risk scores. Trained on a multi-institution EHR corpus paired with a curated DrugBank DDI graph, and evaluated using a clinically aligned, decision-focused protocol with leakage-safe negatives that avoid artificially easy pairs, the system maintains precision across multi-institutuion test data, produces mechanism-specific, clinically consistent predictions, reduces false alerts (higher precision) at comparable overall detection performance (F1), and misses fewer true interactions compared to prior methods. Case studies further show zero-shot identification of clinically recognized CYP-mediated and pharmacodynamic mechanisms for drugs absent from the KG, supporting real-world use in clinical decision support and pharmacovigilance.