CliqueFluxNet : unveiling EHR insights with stochastic edge fluxing and maximal clique utilisation using graph neural networks

Tools

Molaei, Soheila and Bousejin, Nima Ghanbari and Ghosheh, Ghadeer O. and Thakur, Anshul and Chauhan, Vinod Kumar and Zhu, Tingting and Clifton, David A. (2024) CliqueFluxNet : unveiling EHR insights with stochastic edge fluxing and maximal clique utilisation using graph neural networks. Journal of Healthcare Informatics Research, 8 (3). pp. 555-575. ISSN 2509-498X (https://doi.org/10.1007/s41666-024-00169-2)

[thumbnail of Molaei-etal-JHIR-2024-CliqueFluxNet-unveiling-EHR-insights-with-stochastic-edge-fluxing-and]
Preview
 Text. Filename: Molaei-etal-JHIR-2024-CliqueFluxNet-unveiling-EHR-insights-with-stochastic-edge-fluxing-and.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (1MB)| Preview

Abstract

Electronic Health Records (EHRs) play a crucial role in shaping predictive are models, yet they encounter challenges such as significant data gaps and class imbalances. Traditional Graph Neural Network (GNN) approaches have limitations in fully leveraging neighbourhood data or demanding intensive computational requirements for regularisation. To address this challenge, we introduce CliqueFluxNet, a novel framework that innovatively constructs a patient similarity graph to maximise cliques, thereby highlighting strong inter-patient connections. At the heart of CliqueFluxNet lies its stochastic edge fluxing strategy — a dynamic process involving random edge addition and removal during training. This strategy aims to enhance the model’s generalisability and mitigate overfitting. Our empirical analysis, conducted on MIMIC-III and eICU datasets, focuses on the tasks of mortality and readmission prediction. It demonstrates significant progress in representation learning, particularly in scenarios with limited data availability. Qualitative assessments further underscore CliqueFluxNet’s effectiveness in extracting meaningful EHR representations, solidifying its potential for advancing GNN applications in healthcare analytics.

ORCID iDs

Molaei, Soheila, Bousejin, Nima Ghanbari, Ghosheh, Ghadeer O., Thakur, Anshul, Chauhan, Vinod Kumar ORCID logoORCID: https://orcid.org/0000-0001-8195-548X, Zhu, Tingting and Clifton, David A.;
CORE (COnnecting REpositories)