Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark

Abstract The COVID-19 pandemic has put massive strains on hospitals, and tools to guide hospital planners in resource allocation during the ebbs and flows of the pandemic are urgently needed. We investigate whether machine learning (ML) can be used for predictions of intensive care requirements a fi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Stephan Sloth Lorenzen, Mads Nielsen, Espen Jimenez-Solem, Tonny Studsgaard Petersen, Anders Perner, Hans-Christian Thorsen-Meyer, Christian Igel, Martin Sillesen
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/26af521884ea431b92de430cf87dfbb3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:26af521884ea431b92de430cf87dfbb3
record_format	dspace
spelling	oai:doaj.org-article:26af521884ea431b92de430cf87dfbb32021-12-02T18:48:09ZUsing machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark10.1038/s41598-021-98617-12045-2322https://doaj.org/article/26af521884ea431b92de430cf87dfbb32021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-98617-1https://doaj.org/toc/2045-2322Abstract The COVID-19 pandemic has put massive strains on hospitals, and tools to guide hospital planners in resource allocation during the ebbs and flows of the pandemic are urgently needed. We investigate whether machine learning (ML) can be used for predictions of intensive care requirements a fixed number of days into the future. Retrospective design where health Records from 42,526 SARS-CoV-2 positive patients in Denmark was extracted. Random Forest (RF) models were trained to predict risk of ICU admission and use of mechanical ventilation after n days (n = 1, 2, …, 15). An extended analysis was provided for n = 5 and n = 10. Models predicted n-day risk of ICU admission with an area under the receiver operator characteristic curve (ROC-AUC) between 0.981 and 0.995, and n-day risk of use of ventilation with an ROC-AUC between 0.982 and 0.997. The corresponding n-day forecasting models predicted the needed ICU capacity with a coefficient of determination (R2) between 0.334 and 0.989 and use of ventilation with an R2 between 0.446 and 0.973. The forecasting models performed worst, when forecasting many days into the future (for large n). For n = 5, ICU capacity was predicted with ROC-AUC 0.990 and R2 0.928, and use of ventilator was predicted with ROC-AUC 0.994 and R2 0.854. Random Forest-based modelling can be used for accurate n-day forecasting predictions of ICU resource requirements, when n is not too large.Stephan Sloth LorenzenMads NielsenEspen Jimenez-SolemTonny Studsgaard PetersenAnders PernerHans-Christian Thorsen-MeyerChristian IgelMartin SillesenNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Stephan Sloth Lorenzen Mads Nielsen Espen Jimenez-Solem Tonny Studsgaard Petersen Anders Perner Hans-Christian Thorsen-Meyer Christian Igel Martin Sillesen Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark
description	Abstract The COVID-19 pandemic has put massive strains on hospitals, and tools to guide hospital planners in resource allocation during the ebbs and flows of the pandemic are urgently needed. We investigate whether machine learning (ML) can be used for predictions of intensive care requirements a fixed number of days into the future. Retrospective design where health Records from 42,526 SARS-CoV-2 positive patients in Denmark was extracted. Random Forest (RF) models were trained to predict risk of ICU admission and use of mechanical ventilation after n days (n = 1, 2, …, 15). An extended analysis was provided for n = 5 and n = 10. Models predicted n-day risk of ICU admission with an area under the receiver operator characteristic curve (ROC-AUC) between 0.981 and 0.995, and n-day risk of use of ventilation with an ROC-AUC between 0.982 and 0.997. The corresponding n-day forecasting models predicted the needed ICU capacity with a coefficient of determination (R2) between 0.334 and 0.989 and use of ventilation with an R2 between 0.446 and 0.973. The forecasting models performed worst, when forecasting many days into the future (for large n). For n = 5, ICU capacity was predicted with ROC-AUC 0.990 and R2 0.928, and use of ventilator was predicted with ROC-AUC 0.994 and R2 0.854. Random Forest-based modelling can be used for accurate n-day forecasting predictions of ICU resource requirements, when n is not too large.
format	article
author	Stephan Sloth Lorenzen Mads Nielsen Espen Jimenez-Solem Tonny Studsgaard Petersen Anders Perner Hans-Christian Thorsen-Meyer Christian Igel Martin Sillesen
author_facet	Stephan Sloth Lorenzen Mads Nielsen Espen Jimenez-Solem Tonny Studsgaard Petersen Anders Perner Hans-Christian Thorsen-Meyer Christian Igel Martin Sillesen
author_sort	Stephan Sloth Lorenzen
title	Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark
title_short	Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark
title_full	Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark
title_fullStr	Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark
title_full_unstemmed	Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark
title_sort	using machine learning for predicting intensive care unit resource use during the covid-19 pandemic in denmark
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/26af521884ea431b92de430cf87dfbb3
work_keys_str_mv	AT stephanslothlorenzen usingmachinelearningforpredictingintensivecareunitresourceuseduringthecovid19pandemicindenmark AT madsnielsen usingmachinelearningforpredictingintensivecareunitresourceuseduringthecovid19pandemicindenmark AT espenjimenezsolem usingmachinelearningforpredictingintensivecareunitresourceuseduringthecovid19pandemicindenmark AT tonnystudsgaardpetersen usingmachinelearningforpredictingintensivecareunitresourceuseduringthecovid19pandemicindenmark AT andersperner usingmachinelearningforpredictingintensivecareunitresourceuseduringthecovid19pandemicindenmark AT hanschristianthorsenmeyer usingmachinelearningforpredictingintensivecareunitresourceuseduringthecovid19pandemicindenmark AT christianigel usingmachinelearningforpredictingintensivecareunitresourceuseduringthecovid19pandemicindenmark AT martinsillesen usingmachinelearningforpredictingintensivecareunitresourceuseduringthecovid19pandemicindenmark
_version_	1718377610868686848

Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark

Ejemplares similares