Predictive Modeling with Temporal Graphical Representation on Electronic Health Records

TL;DR

This paper introduces a novel temporal heterogeneous graph model and a transformer-based approach to improve predictive modeling using electronic health records by capturing both temporal and structural information.

Contribution

It proposes a new temporal heterogeneous graph representation and a temporal graph transformer (TRANS) that effectively integrate temporal and structural data from EHRs.

Findings

Achieves state-of-the-art performance on three real-world datasets.

Effectively captures both temporal and structural information in EHRs.

Outperforms existing sequential and graphical representation methods.

Abstract

Deep learning-based predictive models, leveraging Electronic Health Records (EHR), are receiving increasing attention in healthcare. An effective representation of a patient's EHR should hierarchically encompass both the temporal relationships between historical visits and medical events, and the inherent structural information within these elements. Existing patient representation methods can be roughly categorized into sequential representation and graphical representation. The sequential representation methods focus only on the temporal relationships among longitudinal visits. On the other hand, the graphical representation approaches, while adept at extracting the graph-structured relationships between various medical events, fall short in effectively integrate temporal information. To capture both types of information, we model a patient's EHR as a novel temporal heterogeneous graph. This graph includes historical visits nodes and medical events nodes. It propagates structured information from medical event nodes to visit nodes and utilizes time-aware visit nodes to capture changes in the patient's health status. Furthermore, we introduce a novel temporal graph transformer (TRANS) that integrates temporal edge features, global positional encoding, and local structural encoding into heterogeneous graph convolution, capturing both temporal and structural information. We validate the effectiveness of TRANS through extensive experiments on three real-world datasets. The results show that our proposed approach achieves state-of-the-art performance.