Budget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients

Abstract The combination of machine learning (ML) and electronic health records (EHR) data may be able to improve outcomes of hospitalized COVID-19 patients through improved risk stratification and patient outcome prediction. However, in resource constrained environments the clinical utility of such...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sam Nguyen, Ryan Chan, Jose Cadena, Braden Soper, Paul Kiszka, Lucas Womack, Mark Work, Joan M. Duggan, Steven T. Haller, Jennifer A. Hanrahan, David J. Kennedy, Deepa Mukundan, Priyadip Ray
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/f84bcc357880499c918c1874c4e4b670
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f84bcc357880499c918c1874c4e4b670
record_format	dspace
spelling	oai:doaj.org-article:f84bcc357880499c918c1874c4e4b6702021-12-02T19:16:54ZBudget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients10.1038/s41598-021-98071-z2045-2322https://doaj.org/article/f84bcc357880499c918c1874c4e4b6702021-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-98071-zhttps://doaj.org/toc/2045-2322Abstract The combination of machine learning (ML) and electronic health records (EHR) data may be able to improve outcomes of hospitalized COVID-19 patients through improved risk stratification and patient outcome prediction. However, in resource constrained environments the clinical utility of such data-driven predictive tools may be limited by the cost or unavailability of certain laboratory tests. We leveraged EHR data to develop an ML-based tool for predicting adverse outcomes that optimizes clinical utility under a given cost structure. We further gained insights into the decision-making process of the ML models through an explainable AI tool. This cohort study was performed using deidentified EHR data from COVID-19 patients from ProMedica Health System in northwest Ohio and southeastern Michigan. We tested the performance of various ML approaches for predicting either increasing ventilatory support or mortality. We performed post hoc analysis to obtain optimal feature sets under various budget constraints. We demonstrate that it is possible to achieve a significant reduction in cost at the expense of a small reduction in predictive performance. For example, when predicting ventilation, it is possible to achieve a 43% reduction in cost with only a 3% reduction in performance. Similarly, when predicting mortality, it is possible to achieve a 50% reduction in cost with only a 1% reduction in performance. This study presents a quick, accurate, and cost-effective method to evaluate risk of deterioration for patients with SARS-CoV-2 infection at the time of clinical evaluation.Sam NguyenRyan ChanJose CadenaBraden SoperPaul KiszkaLucas WomackMark WorkJoan M. DugganSteven T. HallerJennifer A. HanrahanDavid J. KennedyDeepa MukundanPriyadip RayNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Sam Nguyen Ryan Chan Jose Cadena Braden Soper Paul Kiszka Lucas Womack Mark Work Joan M. Duggan Steven T. Haller Jennifer A. Hanrahan David J. Kennedy Deepa Mukundan Priyadip Ray Budget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients
description	Abstract The combination of machine learning (ML) and electronic health records (EHR) data may be able to improve outcomes of hospitalized COVID-19 patients through improved risk stratification and patient outcome prediction. However, in resource constrained environments the clinical utility of such data-driven predictive tools may be limited by the cost or unavailability of certain laboratory tests. We leveraged EHR data to develop an ML-based tool for predicting adverse outcomes that optimizes clinical utility under a given cost structure. We further gained insights into the decision-making process of the ML models through an explainable AI tool. This cohort study was performed using deidentified EHR data from COVID-19 patients from ProMedica Health System in northwest Ohio and southeastern Michigan. We tested the performance of various ML approaches for predicting either increasing ventilatory support or mortality. We performed post hoc analysis to obtain optimal feature sets under various budget constraints. We demonstrate that it is possible to achieve a significant reduction in cost at the expense of a small reduction in predictive performance. For example, when predicting ventilation, it is possible to achieve a 43% reduction in cost with only a 3% reduction in performance. Similarly, when predicting mortality, it is possible to achieve a 50% reduction in cost with only a 1% reduction in performance. This study presents a quick, accurate, and cost-effective method to evaluate risk of deterioration for patients with SARS-CoV-2 infection at the time of clinical evaluation.
format	article
author	Sam Nguyen Ryan Chan Jose Cadena Braden Soper Paul Kiszka Lucas Womack Mark Work Joan M. Duggan Steven T. Haller Jennifer A. Hanrahan David J. Kennedy Deepa Mukundan Priyadip Ray
author_facet	Sam Nguyen Ryan Chan Jose Cadena Braden Soper Paul Kiszka Lucas Womack Mark Work Joan M. Duggan Steven T. Haller Jennifer A. Hanrahan David J. Kennedy Deepa Mukundan Priyadip Ray
author_sort	Sam Nguyen
title	Budget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients
title_short	Budget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients
title_full	Budget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients
title_fullStr	Budget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients
title_full_unstemmed	Budget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients
title_sort	budget constrained machine learning for early prediction of adverse outcomes for covid-19 patients
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/f84bcc357880499c918c1874c4e4b670
work_keys_str_mv	AT samnguyen budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients AT ryanchan budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients AT josecadena budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients AT bradensoper budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients AT paulkiszka budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients AT lucaswomack budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients AT markwork budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients AT joanmduggan budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients AT steventhaller budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients AT jenniferahanrahan budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients AT davidjkennedy budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients AT deepamukundan budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients AT priyadipray budgetconstrainedmachinelearningforearlypredictionofadverseoutcomesforcovid19patients
_version_	1718376949789753344

Budget constrained machine learning for early prediction of adverse outcomes for COVID-19 patients

Ejemplares similares