Patient clustering for vital organ failure using ICD code with graph attention
<i>Objective:</i> Heart failure, respiratory failure and kidney failure are three severe organ failures (OF) that have high mortalities and are most prevalent in intensive care units. The objective of this work is to offer insights into OF clustering from the aspects of graph neural netw...
| Principais autores: | , , , , , |
|---|---|
| Formato: | Journal article |
| Idioma: | English |
| Publicado em: |
IEEE
2023
|
| _version_ | 1826311036273164288 |
|---|---|
| author | Liu, Z Hu, Y Wu, X Mertes, G Yang, Y Clifton, DA |
| author_facet | Liu, Z Hu, Y Wu, X Mertes, G Yang, Y Clifton, DA |
| author_sort | Liu, Z |
| collection | OXFORD |
| description | <i>Objective:</i> Heart failure, respiratory failure and kidney failure are three severe organ failures (OF) that have high mortalities and are most prevalent in intensive care units. The objective of this work is to offer insights into OF clustering from the aspects of graph neural networks and diagnosis history. <i>Methods:</i> This paper proposes a neural network-based pipeline to cluster three types of organ failure patients by incorporating embedding pre-train using an ontology graph of the International Classification of Diseases (ICD) codes. We employ an autoencoder-based deep clustering architecture jointly trained with a K-means loss, and a non-linear dimension reduction is performed to obtain patient clusters on the MIMIC-III dataset. <i>Results:</i> The clustering pipeline shows superior performance on a public-domain image dataset. On the MIMIC-III dataset, it discovers two distinct clusters that exhibit different comorbidity spectra which can be related to the severity of diseases. The proposed pipeline is compared with several other clustering models and shows superiority. <i>Conclusion:</i> Our proposed pipeline gives stable clusters, however, they do not correspond to the type of OF which indicates these OF share significant hidden characteristics in diagnosis. These clusters can be used to signal possible complications and severity of illness and aid personalised treatment. <i>Significance:</i> We are the first to apply an unsupervised approach to offer insights from a biomedical engineering perspective on these three types of organ failure, and publish the pre-trained embeddings for future transfer learning. |
| first_indexed | 2024-03-07T08:00:48Z |
| format | Journal article |
| id | oxford-uuid:a6cb49cd-349a-4443-b049-3264078e8536 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T08:00:48Z |
| publishDate | 2023 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:a6cb49cd-349a-4443-b049-3264078e85362023-09-29T09:53:54ZPatient clustering for vital organ failure using ICD code with graph attentionJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:a6cb49cd-349a-4443-b049-3264078e8536EnglishSymplectic ElementsIEEE2023Liu, ZHu, YWu, XMertes, GYang, YClifton, DA<i>Objective:</i> Heart failure, respiratory failure and kidney failure are three severe organ failures (OF) that have high mortalities and are most prevalent in intensive care units. The objective of this work is to offer insights into OF clustering from the aspects of graph neural networks and diagnosis history. <i>Methods:</i> This paper proposes a neural network-based pipeline to cluster three types of organ failure patients by incorporating embedding pre-train using an ontology graph of the International Classification of Diseases (ICD) codes. We employ an autoencoder-based deep clustering architecture jointly trained with a K-means loss, and a non-linear dimension reduction is performed to obtain patient clusters on the MIMIC-III dataset. <i>Results:</i> The clustering pipeline shows superior performance on a public-domain image dataset. On the MIMIC-III dataset, it discovers two distinct clusters that exhibit different comorbidity spectra which can be related to the severity of diseases. The proposed pipeline is compared with several other clustering models and shows superiority. <i>Conclusion:</i> Our proposed pipeline gives stable clusters, however, they do not correspond to the type of OF which indicates these OF share significant hidden characteristics in diagnosis. These clusters can be used to signal possible complications and severity of illness and aid personalised treatment. <i>Significance:</i> We are the first to apply an unsupervised approach to offer insights from a biomedical engineering perspective on these three types of organ failure, and publish the pre-trained embeddings for future transfer learning. |
| spellingShingle | Liu, Z Hu, Y Wu, X Mertes, G Yang, Y Clifton, DA Patient clustering for vital organ failure using ICD code with graph attention |
| title | Patient clustering for vital organ failure using ICD code with graph attention |
| title_full | Patient clustering for vital organ failure using ICD code with graph attention |
| title_fullStr | Patient clustering for vital organ failure using ICD code with graph attention |
| title_full_unstemmed | Patient clustering for vital organ failure using ICD code with graph attention |
| title_short | Patient clustering for vital organ failure using ICD code with graph attention |
| title_sort | patient clustering for vital organ failure using icd code with graph attention |
| work_keys_str_mv | AT liuz patientclusteringforvitalorganfailureusingicdcodewithgraphattention AT huy patientclusteringforvitalorganfailureusingicdcodewithgraphattention AT wux patientclusteringforvitalorganfailureusingicdcodewithgraphattention AT mertesg patientclusteringforvitalorganfailureusingicdcodewithgraphattention AT yangy patientclusteringforvitalorganfailureusingicdcodewithgraphattention AT cliftonda patientclusteringforvitalorganfailureusingicdcodewithgraphattention |