Medical Applications of Graph Convolutional Networks Using Electronic Health Records: A Survey

TL;DR

This survey reviews how Graph Convolutional Networks are applied to Electronic Health Records, highlighting their potential to improve medical decision-making by capturing complex patient data relationships.

Contribution

It provides a comprehensive overview of current GCN applications in EHRs, including key domains, tasks, datasets, and architectural patterns, and discusses future challenges.

Findings

GCNs effectively model complex relationships in EHR data.

Strong potential for GCNs to enhance medical decision support.

Identification of key datasets and architectural trends in the field.

Abstract

Graph Convolutional Networks (GCNs) have emerged as a promising approach to machine learning on Electronic Health Records (EHRs). By constructing a graph representation of patient data and performing convolutions on neighborhoods of nodes, GCNs can capture complex relationships and extract meaningful insights to support medical decision making. This survey provides an overview of the current research in applying GCNs to EHR data. We identify the key medical domains and prediction tasks where these models are being utilized, common benchmark datasets, and architectural patterns to provide a comprehensive survey of this field. While this is a nascent area of research, GCNs demonstrate strong potential to leverage the complex information hidden in EHRs. Challenges and opportunities for future work are also discussed.