EHR coding with hybrid attention and features propagation on disease knowledge graph

Tianhan Xu, Bin Li, Ling Chen

Abstract:

And sentences associated with these attributes and relationships have been neglected. in this paper We
propose an end-to-end model called Knowledge Graph Enhanced neural network (KGENet) to address the
above shortcomings. specifically We first construct a disease knowledge graph that focuses on the multiview disease attributes of ICD codes and the disease relationships between these codes. we also use a long
sequence encoder to get EHR document representation. most importantly KGENet leverages multi-view disease
attributes and structured disease relationships for knowledge enhancement through hybrid attention and graph
propagation Respectively. furthermore The above processes can provide attribute-aware and relationshipaugmented explainability for the model prediction results based on our disease knowledge graph. experiments
conducted on the MIMIC-III benchmark dataset show that KGENet outperforms state-of-the-art models in
both model effectiveness and explainability Electronic health record (EHR) coding assigns International
Classification of Diseases (ICD) codes to each EHR document. These standard medical codes represent diagnoses
or procedures and play a critical role in medical applications. However, EHR is a long medical text that
is difficult to represent, the ICD code label space is large, and the labels have an extremely unbalanced
distribution. These factors pose challenges to automatic EHR coding. Previous studies have not explored the
disease attributes (e.g., symptoms, tests, medications) of ICD codes and the disease relationships (e.g., causes,
risk factors, comorbidities) between them. In addition, the important roles of medical