Enhancing Drug Recommendations via Heterogeneous Graph Representation Learning in EHR Networks

Haijun Zhang, Xian Yang, Liang Bai, Jiye Liang

Research output: Contribution to journalArticlepeer-review

44 Downloads (Pure)


Electronic health records (EHRs) contain vast medical information like diagnosis, medication, and procedures, enabling personalized drug recommendations and treatment adjustments. However, current drug recommendation methods only model patients' health conditions from EHR data, neglecting the rich relationships within the data. This paper seeks to utilize a heterogeneous information network (HIN) to represent EHR and develop a graph representation learning method for medication recommendation. However, three critical issues need to be investigated: (1) co-occurrence of diagnosis and drug for the same patient does not imply their relevance; (2) patients' directly associated information may not be sufficient to reflect their health conditions; and (3) the cold start problem exists when patients have no historical EHRs. To tackle these challenges, we develop a bi-channel heterogeneous local structural encoder to decouple and extract the diverse information in HIN. Additionally, a global information capture and fusion module, aggregating meta-paths to form a global representation, is introduced to fill the information gaps in records. A longitudinal model using rich structural information available in EHR data is proposed for drug recommendations to new patients. Experimental results on real-world EHR data demonstrate significant improvements over existing approaches.

Original languageEnglish
Pages (from-to)1-12
Number of pages12
JournalIEEE Transactions on Knowledge and Data Engineering
Publication statusPublished - 31 Oct 2023


  • Data models
  • Drug Recommendation
  • Drugs
  • Electronic Health Records
  • Heterogeneous Graph Representation Learning
  • Heterogeneous networks
  • Medical diagnostic imaging
  • Medical services
  • Representation learning
  • Semantics


Dive into the research topics of 'Enhancing Drug Recommendations via Heterogeneous Graph Representation Learning in EHR Networks'. Together they form a unique fingerprint.

Cite this