.png){kind=icon}
.png){kind=icon}
Return
Safe and personalized drug recommendation via heterogeneous graph learning: integrating graphSAGE representations with DDI-aware cross-attention
.png){kind=icon}
PRE
AI
K
S
DOI：10.1007/s13748-026-00437-9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Personalized medication recommendation must ensure both efficacy and safety, particularly by avoiding drug-drug interactions (DDIs), a major cause of preventable adverse events. We introduce a heterogeneous graph learning framework that unifies electronic health records (EHRs) using explicit patient-diagnosis, patient-drug, and diagnosis-drug edges together with curated DDI interaction edges. Patient- and diagnosis-specific embeddings are learned inductively via GraphSAGE, while pharmacological risk is modeled through a graph convolutional network (GCN) on the DDI subgraph. A DDI-aware cross-attention mechanism fuses these representations, aligning patient context with safety signals and penalizing unsafe co-prescriptions during training. Evaluation on the MIMIC-III dataset demonstrates that our model consistently outperforms strong baselines, achieving superior predictive accuracy (Jaccard 0.5281, F1 0.6701, PR-AUC 0.7754) while reducing unsafe recommendations (DDI Rate 0.0581). All improvements are statistically significant (p < 0.05). By integrating inductive heterogeneous graph embeddings with safety-aware attention, our framework bridges predictive accuracy and pharmacological safety, generalizes to unseen patients, and avoids clinically hazardous combinations.
Keywords:
Personalized drug recommendation
Electronic Health Records (EHRs)
Graph neural networks (GNNs)
Drug-drug interactions (DDIs)
Cross-attention fusion
Journal
P
IF:
2.4
Papers:
44
Citations:
0
Organization
Cited Papers