CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks
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 co...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Springer
2024
|
| _version_ | 1826313823961743360 |
|---|---|
| author | Molaei, S Bousejin, NG Ghosheh, GO Thakur, A Chauhan, VK Zhu, T Clifton, DA |
| author_facet | Molaei, S Bousejin, NG Ghosheh, GO Thakur, A Chauhan, VK Zhu, T Clifton, DA |
| author_sort | Molaei, S |
| collection | OXFORD |
| description | 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. |
| first_indexed | 2024-09-25T04:22:38Z |
| format | Journal article |
| id | oxford-uuid:c1eb6d0b-bc5c-47d7-b2eb-536c33f3895c |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-09-25T04:22:38Z |
| publishDate | 2024 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:c1eb6d0b-bc5c-47d7-b2eb-536c33f3895c2024-08-08T19:41:19ZCliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural NetworksJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:c1eb6d0b-bc5c-47d7-b2eb-536c33f3895cEnglishJisc Publications RouterSpringer2024Molaei, SBousejin, NGGhosheh, GOThakur, AChauhan, VKZhu, TClifton, DAElectronic 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. |
| spellingShingle | Molaei, S Bousejin, NG Ghosheh, GO Thakur, A Chauhan, VK Zhu, T Clifton, DA CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks |
| title | CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks |
| title_full | CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks |
| title_fullStr | CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks |
| title_full_unstemmed | CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks |
| title_short | CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks |
| title_sort | cliquefluxnet unveiling ehr insights with stochastic edge fluxing and maximal clique utilisation using graph neural networks |
| work_keys_str_mv | AT molaeis cliquefluxnetunveilingehrinsightswithstochasticedgefluxingandmaximalcliqueutilisationusinggraphneuralnetworks AT bousejinng cliquefluxnetunveilingehrinsightswithstochasticedgefluxingandmaximalcliqueutilisationusinggraphneuralnetworks AT ghoshehgo cliquefluxnetunveilingehrinsightswithstochasticedgefluxingandmaximalcliqueutilisationusinggraphneuralnetworks AT thakura cliquefluxnetunveilingehrinsightswithstochasticedgefluxingandmaximalcliqueutilisationusinggraphneuralnetworks AT chauhanvk cliquefluxnetunveilingehrinsightswithstochasticedgefluxingandmaximalcliqueutilisationusinggraphneuralnetworks AT zhut cliquefluxnetunveilingehrinsightswithstochasticedgefluxingandmaximalcliqueutilisationusinggraphneuralnetworks AT cliftonda cliquefluxnetunveilingehrinsightswithstochasticedgefluxingandmaximalcliqueutilisationusinggraphneuralnetworks |