Disease Risk Prediction via Heterogeneous Graph Attention Networks

Disease risk prediction is an important component of clinical decision support systems. In order to predict disease risk, most studies attempt to extract features associated with disease risk from electronic health records (EHRs), however, the complex interactions between heterogeneous entities associated with disease risk (e.g., diseases, symptoms, medications, and other treatment items) are ignored, resulting in imprecise disease risk prediction. To tackle this issue, we propose a disease prediction method based on heterogeneous graph attention networks (HAN) in this paper. In our study, the EHRs are used to constructed the heterogeneous medical graph, in which the embedding vector of each node can be calculated via its directly connected neighbors’ features. The heterogeneous medical graph contains different types of nodes and links, and in our proposed model, the attention mechanism is adopted, which is used to learn the importance between a node and its meta-path connected neighboring nodes. The proposed method is good at mining the potential information of the electronic medical records. Experiment results on real datasets show that the performance of the poposed methods outperforms that of the baseline methods.