Pretraining-based Relevance-aware Visit Similarity Network for Drug Recommendation

Drug recommendation based on electronic health records (EHR) relies heavily on precise patient modeling, which is more complex than conventional recommendation tasks as it requires both temporal modeling of disease progression and referencing similar patients' medication information. However, sparse visit records and vague patient similarity in EHR data pose significant challenges, often introducing noise and ambiguity. To address the above challenges, we propose RaVSNet (Relevance aware Visit Similarity Network), which improves drug recommendation by leveraging both longitudinal and transversal visit similarity and integrating medical relevance knowledge. RaVSNet utilizes multi-dimensional visit information similar to the patient's current visit as a reference, and employs a relevance-aware network to explicitly model the matching relationships between medical conditions and medications. Additionally, RaVSNet designs a general pretraining framework specifically for drug recommendation, including two tasks, Medication Sequence Reconstruction (MSR) and Causal Effect Inference (CEI), to discover the deep connections between medical information and medications. Experimental results on two public EHR datasets, MIMIC-III and MIMIC-IV demonstrate that the proposed algorithm outperforms state-of-the-art methods, yielding more accurate drug recommendation combinations, and the proposed general pretraining framework can be seamlessly integrated into most drug recommendation methods to achieve performance improvements. The implementation is available at: https://github.com/SCUT-CCNL/RaVSNet.