Application of machine learning approaches to administrative claims data to predict clinical outcomes in medical and surgical patient populations.

<h4>Objective</h4>This study aimed to develop and validate a claims-based, machine learning algorithm to predict clinical outcomes across both medical and surgical patient populations.<h4>Methods</h4>This retrospective, observational cohort study, used a random 5% sample of 7...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Emily J MacKay, Michael D Stubna, Corey Chivers, Michael E Draugelis, William J Hanson, Nimesh D Desai, Peter W Groeneveld
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/b2295f0e621845f6a4c02939fd0215ec
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b2295f0e621845f6a4c02939fd0215ec
record_format	dspace
spelling	oai:doaj.org-article:b2295f0e621845f6a4c02939fd0215ec2021-12-02T20:11:07ZApplication of machine learning approaches to administrative claims data to predict clinical outcomes in medical and surgical patient populations.1932-620310.1371/journal.pone.0252585https://doaj.org/article/b2295f0e621845f6a4c02939fd0215ec2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0252585https://doaj.org/toc/1932-6203<h4>Objective</h4>This study aimed to develop and validate a claims-based, machine learning algorithm to predict clinical outcomes across both medical and surgical patient populations.<h4>Methods</h4>This retrospective, observational cohort study, used a random 5% sample of 770,777 fee-for-service Medicare beneficiaries with an inpatient hospitalization between 2009-2011. The machine learning algorithms tested included: support vector machine, random forest, multilayer perceptron, extreme gradient boosted tree, and logistic regression. The extreme gradient boosted tree algorithm outperformed the alternatives and was the machine learning method used for the final risk model. Primary outcome was 30-day mortality. Secondary outcomes were: rehospitalization, and any of 23 adverse clinical events occurring within 30 days of the index admission date.<h4>Results</h4>The machine learning algorithm performance was evaluated by both the area under the receiver operating curve (AUROC) and Brier Score. The risk model demonstrated high performance for prediction of: 30-day mortality (AUROC = 0.88; Brier Score = 0.06), and 17 of the 23 adverse events (AUROC range: 0.80-0.86; Brier Score range: 0.01-0.05). The risk model demonstrated moderate performance for prediction of: rehospitalization within 30 days (AUROC = 0.73; Brier Score: = 0.07) and six of the 23 adverse events (AUROC range: 0.74-0.79; Brier Score range: 0.01-0.02). The machine learning risk model performed comparably on a second, independent validation dataset, confirming that the risk model was not overfit.<h4>Conclusions and relevance</h4>We have developed and validated a robust, claims-based, machine learning risk model that is applicable to both medical and surgical patient populations and demonstrates comparable predictive accuracy to existing risk models.Emily J MacKayMichael D StubnaCorey ChiversMichael E DraugelisWilliam J HansonNimesh D DesaiPeter W GroeneveldPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 6, p e0252585 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Emily J MacKay Michael D Stubna Corey Chivers Michael E Draugelis William J Hanson Nimesh D Desai Peter W Groeneveld Application of machine learning approaches to administrative claims data to predict clinical outcomes in medical and surgical patient populations.
description	<h4>Objective</h4>This study aimed to develop and validate a claims-based, machine learning algorithm to predict clinical outcomes across both medical and surgical patient populations.<h4>Methods</h4>This retrospective, observational cohort study, used a random 5% sample of 770,777 fee-for-service Medicare beneficiaries with an inpatient hospitalization between 2009-2011. The machine learning algorithms tested included: support vector machine, random forest, multilayer perceptron, extreme gradient boosted tree, and logistic regression. The extreme gradient boosted tree algorithm outperformed the alternatives and was the machine learning method used for the final risk model. Primary outcome was 30-day mortality. Secondary outcomes were: rehospitalization, and any of 23 adverse clinical events occurring within 30 days of the index admission date.<h4>Results</h4>The machine learning algorithm performance was evaluated by both the area under the receiver operating curve (AUROC) and Brier Score. The risk model demonstrated high performance for prediction of: 30-day mortality (AUROC = 0.88; Brier Score = 0.06), and 17 of the 23 adverse events (AUROC range: 0.80-0.86; Brier Score range: 0.01-0.05). The risk model demonstrated moderate performance for prediction of: rehospitalization within 30 days (AUROC = 0.73; Brier Score: = 0.07) and six of the 23 adverse events (AUROC range: 0.74-0.79; Brier Score range: 0.01-0.02). The machine learning risk model performed comparably on a second, independent validation dataset, confirming that the risk model was not overfit.<h4>Conclusions and relevance</h4>We have developed and validated a robust, claims-based, machine learning risk model that is applicable to both medical and surgical patient populations and demonstrates comparable predictive accuracy to existing risk models.
format	article
author	Emily J MacKay Michael D Stubna Corey Chivers Michael E Draugelis William J Hanson Nimesh D Desai Peter W Groeneveld
author_facet	Emily J MacKay Michael D Stubna Corey Chivers Michael E Draugelis William J Hanson Nimesh D Desai Peter W Groeneveld
author_sort	Emily J MacKay
title	Application of machine learning approaches to administrative claims data to predict clinical outcomes in medical and surgical patient populations.
title_short	Application of machine learning approaches to administrative claims data to predict clinical outcomes in medical and surgical patient populations.
title_full	Application of machine learning approaches to administrative claims data to predict clinical outcomes in medical and surgical patient populations.
title_fullStr	Application of machine learning approaches to administrative claims data to predict clinical outcomes in medical and surgical patient populations.
title_full_unstemmed	Application of machine learning approaches to administrative claims data to predict clinical outcomes in medical and surgical patient populations.
title_sort	application of machine learning approaches to administrative claims data to predict clinical outcomes in medical and surgical patient populations.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/b2295f0e621845f6a4c02939fd0215ec
work_keys_str_mv	AT emilyjmackay applicationofmachinelearningapproachestoadministrativeclaimsdatatopredictclinicaloutcomesinmedicalandsurgicalpatientpopulations AT michaeldstubna applicationofmachinelearningapproachestoadministrativeclaimsdatatopredictclinicaloutcomesinmedicalandsurgicalpatientpopulations AT coreychivers applicationofmachinelearningapproachestoadministrativeclaimsdatatopredictclinicaloutcomesinmedicalandsurgicalpatientpopulations AT michaeledraugelis applicationofmachinelearningapproachestoadministrativeclaimsdatatopredictclinicaloutcomesinmedicalandsurgicalpatientpopulations AT williamjhanson applicationofmachinelearningapproachestoadministrativeclaimsdatatopredictclinicaloutcomesinmedicalandsurgicalpatientpopulations AT nimeshddesai applicationofmachinelearningapproachestoadministrativeclaimsdatatopredictclinicaloutcomesinmedicalandsurgicalpatientpopulations AT peterwgroeneveld applicationofmachinelearningapproachestoadministrativeclaimsdatatopredictclinicaloutcomesinmedicalandsurgicalpatientpopulations
_version_	1718374967547002880

Application of machine learning approaches to administrative claims data to predict clinical outcomes in medical and surgical patient populations.

Ejemplares similares