Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering

Abstract Critically ill patients constitute a highly heterogeneous population, with seemingly distinct patients having similar outcomes, and patients with the same admission diagnosis having opposite clinical trajectories. We aimed to develop a machine learning methodology that identifies and provid...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	José Castela Forte, Galiya Yeshmagambetova, Maureen L. van der Grinten, Bart Hiemstra, Thomas Kaufmann, Ruben J. Eck, Frederik Keus, Anne H. Epema, Marco A. Wiering, Iwan C. C. van der Horst
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/7e1247669dad4ed396c906d967f51c73
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7e1247669dad4ed396c906d967f51c73
record_format	dspace
spelling	oai:doaj.org-article:7e1247669dad4ed396c906d967f51c732021-12-02T14:59:29ZIdentifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering10.1038/s41598-021-91297-x2045-2322https://doaj.org/article/7e1247669dad4ed396c906d967f51c732021-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-91297-xhttps://doaj.org/toc/2045-2322Abstract Critically ill patients constitute a highly heterogeneous population, with seemingly distinct patients having similar outcomes, and patients with the same admission diagnosis having opposite clinical trajectories. We aimed to develop a machine learning methodology that identifies and provides better characterization of patient clusters at high risk of mortality and kidney injury. We analysed prospectively collected data including co-morbidities, clinical examination, and laboratory parameters from a minimally-selected population of 743 patients admitted to the ICU of a Dutch hospital between 2015 and 2017. We compared four clustering methodologies and trained a classifier to predict and validate cluster membership. The contribution of different variables to the predicted cluster membership was assessed using SHapley Additive exPlanations values. We found that deep embedded clustering yielded better results compared to the traditional clustering algorithms. The best cluster configuration was achieved for 6 clusters. All clusters were clinically recognizable, and differed in in-ICU, 30-day, and 90-day mortality, as well as incidence of acute kidney injury. We identified two high mortality risk clusters with at least 60%, 40%, and 30% increased. ICU, 30-day and 90-day mortality, and a low risk cluster with 25–56% lower mortality risk. This machine learning methodology combining deep embedded clustering and variable importance analysis, which we made publicly available, is a possible solution to challenges previously encountered by clustering analyses in heterogeneous patient populations and may help improve the characterization of risk groups in critical care.José Castela ForteGaliya YeshmagambetovaMaureen L. van der GrintenBart HiemstraThomas KaufmannRuben J. EckFrederik KeusAnne H. EpemaMarco A. WieringIwan C. C. van der HorstNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q José Castela Forte Galiya Yeshmagambetova Maureen L. van der Grinten Bart Hiemstra Thomas Kaufmann Ruben J. Eck Frederik Keus Anne H. Epema Marco A. Wiering Iwan C. C. van der Horst Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering
description	Abstract Critically ill patients constitute a highly heterogeneous population, with seemingly distinct patients having similar outcomes, and patients with the same admission diagnosis having opposite clinical trajectories. We aimed to develop a machine learning methodology that identifies and provides better characterization of patient clusters at high risk of mortality and kidney injury. We analysed prospectively collected data including co-morbidities, clinical examination, and laboratory parameters from a minimally-selected population of 743 patients admitted to the ICU of a Dutch hospital between 2015 and 2017. We compared four clustering methodologies and trained a classifier to predict and validate cluster membership. The contribution of different variables to the predicted cluster membership was assessed using SHapley Additive exPlanations values. We found that deep embedded clustering yielded better results compared to the traditional clustering algorithms. The best cluster configuration was achieved for 6 clusters. All clusters were clinically recognizable, and differed in in-ICU, 30-day, and 90-day mortality, as well as incidence of acute kidney injury. We identified two high mortality risk clusters with at least 60%, 40%, and 30% increased. ICU, 30-day and 90-day mortality, and a low risk cluster with 25–56% lower mortality risk. This machine learning methodology combining deep embedded clustering and variable importance analysis, which we made publicly available, is a possible solution to challenges previously encountered by clustering analyses in heterogeneous patient populations and may help improve the characterization of risk groups in critical care.
format	article
author	José Castela Forte Galiya Yeshmagambetova Maureen L. van der Grinten Bart Hiemstra Thomas Kaufmann Ruben J. Eck Frederik Keus Anne H. Epema Marco A. Wiering Iwan C. C. van der Horst
author_facet	José Castela Forte Galiya Yeshmagambetova Maureen L. van der Grinten Bart Hiemstra Thomas Kaufmann Ruben J. Eck Frederik Keus Anne H. Epema Marco A. Wiering Iwan C. C. van der Horst
author_sort	José Castela Forte
title	Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering
title_short	Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering
title_full	Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering
title_fullStr	Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering
title_full_unstemmed	Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering
title_sort	identifying and characterizing high-risk clusters in a heterogeneous icu population with deep embedded clustering
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/7e1247669dad4ed396c906d967f51c73
work_keys_str_mv	AT josecastelaforte identifyingandcharacterizinghighriskclustersinaheterogeneousicupopulationwithdeepembeddedclustering AT galiyayeshmagambetova identifyingandcharacterizinghighriskclustersinaheterogeneousicupopulationwithdeepembeddedclustering AT maureenlvandergrinten identifyingandcharacterizinghighriskclustersinaheterogeneousicupopulationwithdeepembeddedclustering AT barthiemstra identifyingandcharacterizinghighriskclustersinaheterogeneousicupopulationwithdeepembeddedclustering AT thomaskaufmann identifyingandcharacterizinghighriskclustersinaheterogeneousicupopulationwithdeepembeddedclustering AT rubenjeck identifyingandcharacterizinghighriskclustersinaheterogeneousicupopulationwithdeepembeddedclustering AT frederikkeus identifyingandcharacterizinghighriskclustersinaheterogeneousicupopulationwithdeepembeddedclustering AT annehepema identifyingandcharacterizinghighriskclustersinaheterogeneousicupopulationwithdeepembeddedclustering AT marcoawiering identifyingandcharacterizinghighriskclustersinaheterogeneousicupopulationwithdeepembeddedclustering AT iwanccvanderhorst identifyingandcharacterizinghighriskclustersinaheterogeneousicupopulationwithdeepembeddedclustering
_version_	1718389210497417216

Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering

Ejemplares similares