Hypergraph Convolutional Networks for Fine-Grained lCU Patient Similarity Analysis and Risk Prediction

Yuxi Liu, Zhenhao Zhang, Shaowen Qin, Flora D. Salim, Antonio Jimeno-Yepes, Jun Shen, Jiang Bian

Abstract

The Intensive Care Unit (ICU) is an important part of a hospital that provides care for critically ill patients with continuous monitoring and treatment. Various patient outcome prediction methods have been proposed 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, such as patient characteristics (e.g., diagnosis codes) and their causal effects on downstream clinical predictions, are often ignored. This paper presents a novel Hypergraph Convolutional Network that allows the rep-resentation 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 elCU 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 robustness of the model decisions.
BibTeX
@inproceedings{liu2024hypergraph,
  author = {Yuxi Liu and Zhenhao Zhang and Shaowen Qin and Flora D. Salim and Antonio Jimeno-Yepes and Jun Shen and Jiang Bian},
  title = {{Hypergraph Convolutional Networks for Fine-Grained lCU Patient Similarity Analysis and Risk Prediction}},
  booktitle = {ICHI},
  year = {2024},
  doi = {10.1109/ichi61247.2024.00023},
}
Figure