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

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.