Hypergraph Convolutional Networks for Fine-grained ICU Patient Similarity Analysis and Risk Prediction

TL;DR

This paper introduces a hypergraph convolutional network that models complex relationships among diagnosis codes to improve patient similarity measurement and mortality risk prediction in ICUs.

Contribution

The paper presents a novel hypergraph convolutional network that captures higher-order relationships among diagnosis codes for enhanced ICU patient risk prediction.

Findings

Outperforms state-of-the-art models in mortality risk prediction

Effectively captures complex relationships among diagnosis codes

Demonstrates robustness through case studies

Abstract

The Intensive Care Unit (ICU) is one of the most important parts of a hospital, which admits critically ill patients and provides continuous monitoring and treatment. Various patient outcome prediction methods have been attempted to assist healthcare professionals in clinical decision-making. Existing methods focus on measuring the similarity between patients using deep neural networks to capture the hidden feature structures. However, the higher-order relationships are ignored, such as patient characteristics (e.g., diagnosis codes) and their causal effects on downstream clinical predictions. In this paper, we propose a novel Hypergraph Convolutional Network that allows the representation of non-pairwise relationships among diagnosis codes in a hypergraph to capture the hidden feature structures so that fine-grained patient similarity can be calculated for personalized mortality risk prediction. Evaluation using a publicly available eICU Collaborative Research Database indicates that our method achieves superior performance over the state-of-the-art models on mortality risk prediction. Moreover, the results of several case studies demonstrated the effectiveness and robustness of the model decisions.