EGNet: explainable graph neural network with similarity explanation for medication recommendation

Abstract

Giving medication recommendations is a crucial step in improving patient well-being and reducing adverse events. However, existing methods usually fail to capture the complex and dynamic relationships between patient health records, medication efficacy, safety, and drug-drug interactions (DDI), yielding inexplicable outcomes. In this study, we propose an innovative approach that uses graph convolution networks (GCN) with extra external knowledge graphs, attention modules, and an explanation to support prescription recommendations. While the attention system can determine the patient depiction in extended data, GCN can efficiently integrate the external information with the DDI graph into a low-dimensional embedding. We then evaluate our approach using the MIMIC-III and MIMIC-IV datasets, demonstrating that it outperforms several benchmarks in recommendation precision and Drug-Drug Interaction (DDI) prevention. Additionally, we include an explanation stage to illustrate the results and their significant potential impact on industrial applications. The findings confirm that EANet can deliver unparalleled performance while requiring less computational resources and providing enhanced interpretability.