Cargando…

K-Means Clustering for Shock Classification in Pediatric Intensive Care Units

Shock is described as an inadequate oxygen supply to the tissues and can be classified in multiple ways. In clinical practice still, old methods are used to discriminate these shock types. This article proposes the application of unsupervised classification methods for the stratification of these pa...

Descripción completa

Detalles Bibliográficos
Autores principales: Rollán-Martínez-Herrera, María, Kerexeta-Sarriegi, Jon, Gil-Antón, Javier, Pilar-Orive, Javier, Macía-Oliver, Iván
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9406631/
https://www.ncbi.nlm.nih.gov/pubmed/36010281
http://dx.doi.org/10.3390/diagnostics12081932
_version_ 1784774168010555392
author Rollán-Martínez-Herrera, María
Kerexeta-Sarriegi, Jon
Gil-Antón, Javier
Pilar-Orive, Javier
Macía-Oliver, Iván
author_facet Rollán-Martínez-Herrera, María
Kerexeta-Sarriegi, Jon
Gil-Antón, Javier
Pilar-Orive, Javier
Macía-Oliver, Iván
author_sort Rollán-Martínez-Herrera, María
collection PubMed
description Shock is described as an inadequate oxygen supply to the tissues and can be classified in multiple ways. In clinical practice still, old methods are used to discriminate these shock types. This article proposes the application of unsupervised classification methods for the stratification of these patients in order to treat them more appropriately. With a cohort of 90 patients admitted in pediatric intensive care units (PICU), the k-means algorithm was applied in the first 24 h data since admission (physiological and analytical variables and the need for devices), obtaining three main groups. Significant differences were found in variables used (e.g., mean diastolic arterial pressure p < 0.001, age p < 0.001) and not used for training (e.g., EtCO2 min p < 0.001, Troponin max p < 0.01), discharge diagnosis (p < 0.001) and outcomes (p < 0.05). Clustering classification equaled classical classification in its association with LOS (p = 0.01) and surpassed it in its association with mortality (p < 0.04 vs. p = 0.16). We have been able to classify shocked pediatric patients with higher outcome correlation than the clinical traditional method. These results support the utility of unsupervised learning algorithms for patient classification in PICU.
format Online
Article
Text
id pubmed-9406631
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-94066312022-08-26 K-Means Clustering for Shock Classification in Pediatric Intensive Care Units Rollán-Martínez-Herrera, María Kerexeta-Sarriegi, Jon Gil-Antón, Javier Pilar-Orive, Javier Macía-Oliver, Iván Diagnostics (Basel) Article Shock is described as an inadequate oxygen supply to the tissues and can be classified in multiple ways. In clinical practice still, old methods are used to discriminate these shock types. This article proposes the application of unsupervised classification methods for the stratification of these patients in order to treat them more appropriately. With a cohort of 90 patients admitted in pediatric intensive care units (PICU), the k-means algorithm was applied in the first 24 h data since admission (physiological and analytical variables and the need for devices), obtaining three main groups. Significant differences were found in variables used (e.g., mean diastolic arterial pressure p < 0.001, age p < 0.001) and not used for training (e.g., EtCO2 min p < 0.001, Troponin max p < 0.01), discharge diagnosis (p < 0.001) and outcomes (p < 0.05). Clustering classification equaled classical classification in its association with LOS (p = 0.01) and surpassed it in its association with mortality (p < 0.04 vs. p = 0.16). We have been able to classify shocked pediatric patients with higher outcome correlation than the clinical traditional method. These results support the utility of unsupervised learning algorithms for patient classification in PICU. MDPI 2022-08-10 /pmc/articles/PMC9406631/ /pubmed/36010281 http://dx.doi.org/10.3390/diagnostics12081932 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Rollán-Martínez-Herrera, María
Kerexeta-Sarriegi, Jon
Gil-Antón, Javier
Pilar-Orive, Javier
Macía-Oliver, Iván
K-Means Clustering for Shock Classification in Pediatric Intensive Care Units
title K-Means Clustering for Shock Classification in Pediatric Intensive Care Units
title_full K-Means Clustering for Shock Classification in Pediatric Intensive Care Units
title_fullStr K-Means Clustering for Shock Classification in Pediatric Intensive Care Units
title_full_unstemmed K-Means Clustering for Shock Classification in Pediatric Intensive Care Units
title_short K-Means Clustering for Shock Classification in Pediatric Intensive Care Units
title_sort k-means clustering for shock classification in pediatric intensive care units
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9406631/
https://www.ncbi.nlm.nih.gov/pubmed/36010281
http://dx.doi.org/10.3390/diagnostics12081932
work_keys_str_mv AT rollanmartinezherreramaria kmeansclusteringforshockclassificationinpediatricintensivecareunits
AT kerexetasarriegijon kmeansclusteringforshockclassificationinpediatricintensivecareunits
AT gilantonjavier kmeansclusteringforshockclassificationinpediatricintensivecareunits
AT pilarorivejavier kmeansclusteringforshockclassificationinpediatricintensivecareunits
AT maciaoliverivan kmeansclusteringforshockclassificationinpediatricintensivecareunits