Heterogeneous Similarity Graph Neural Network on Electronic Health Records

TL;DR

This paper introduces HSGNN, a novel heterogeneous graph neural network that processes EHRs by normalizing and splitting them into homogeneous graphs, effectively capturing complex medical data for improved diagnosis prediction.

Contribution

The paper proposes a new heterogeneous GNN framework with a preprocessing step to handle EHR heterogeneity and hub nodes, enhancing diagnosis prediction accuracy.

Findings

HSGNN outperforms baseline models in diagnosis prediction

The preprocessing method effectively normalizes edges and splits EHR graphs

Fusion of homogeneous graphs improves predictive performance

Abstract

Mining Electronic Health Records (EHRs) becomes a promising topic because of the rich information they contain. By learning from EHRs, machine learning models can be built to help human experts to make medical decisions and thus improve healthcare quality. Recently, many models based on sequential or graph models are proposed to achieve this goal. EHRs contain multiple entities and relations and can be viewed as a heterogeneous graph. However, previous studies ignore the heterogeneity in EHRs. On the other hand, current heterogeneous graph neural networks cannot be simply used on an EHR graph because of the existence of hub nodes in it. To address this issue, we propose Heterogeneous Similarity Graph Neural Network (HSGNN) analyze EHRs with a novel heterogeneous GNN. Our framework consists of two parts: one is a preprocessing method and the other is an end-to-end GNN. The preprocessing method normalizes edges and splits the EHR graph into multiple homogeneous graphs while each homogeneous graph contains partial information of the original EHR graph. The GNN takes all homogeneous graphs as input and fuses all of them into one graph to make a prediction. Experimental results show that HSGNN outperforms other baselines in the diagnosis prediction task.