A multipurpose machine learning approach to predict COVID-19 negative prognosis in São Paulo, Brazil

Abstract The new coronavirus disease (COVID-19) is a challenge for clinical decision-making and the effective allocation of healthcare resources. An accurate prognostic assessment is necessary to improve survival of patients, especially in developing countries. This study proposes to predict the ris...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Fernando Timoteo Fernandes, Tiago Almeida de Oliveira, Cristiane Esteves Teixeira, Andre Filipe de Moraes Batista, Gabriel Dalla Costa, Alexandre Dias Porto Chiavegatto Filho
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/66f01b49c2e04bd0b657561542dabf2c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:66f01b49c2e04bd0b657561542dabf2c
record_format	dspace
spelling	oai:doaj.org-article:66f01b49c2e04bd0b657561542dabf2c2021-12-02T14:26:54ZA multipurpose machine learning approach to predict COVID-19 negative prognosis in São Paulo, Brazil10.1038/s41598-021-82885-y2045-2322https://doaj.org/article/66f01b49c2e04bd0b657561542dabf2c2021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-82885-yhttps://doaj.org/toc/2045-2322Abstract The new coronavirus disease (COVID-19) is a challenge for clinical decision-making and the effective allocation of healthcare resources. An accurate prognostic assessment is necessary to improve survival of patients, especially in developing countries. This study proposes to predict the risk of developing critical conditions in COVID-19 patients by training multipurpose algorithms. We followed a total of 1040 patients with a positive RT-PCR diagnosis for COVID-19 from a large hospital from São Paulo, Brazil, from March to June 2020, of which 288 (28%) presented a severe prognosis, i.e. Intensive Care Unit (ICU) admission, use of mechanical ventilation or death. We used routinely-collected laboratory, clinical and demographic data to train five machine learning algorithms (artificial neural networks, extra trees, random forests, catboost, and extreme gradient boosting). We used a random sample of 70% of patients to train the algorithms and 30% were left for performance assessment, simulating new unseen data. In order to assess if the algorithms could capture general severe prognostic patterns, each model was trained by combining two out of three outcomes to predict the other. All algorithms presented very high predictive performance (average AUROC of 0.92, sensitivity of 0.92, and specificity of 0.82). The three most important variables for the multipurpose algorithms were ratio of lymphocyte per C-reactive protein, C-reactive protein and Braden Scale. The results highlight the possibility that machine learning algorithms are able to predict unspecific negative COVID-19 outcomes from routinely-collected data.Fernando Timoteo FernandesTiago Almeida de OliveiraCristiane Esteves TeixeiraAndre Filipe de Moraes BatistaGabriel Dalla CostaAlexandre Dias Porto Chiavegatto FilhoNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-7 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Fernando Timoteo Fernandes Tiago Almeida de Oliveira Cristiane Esteves Teixeira Andre Filipe de Moraes Batista Gabriel Dalla Costa Alexandre Dias Porto Chiavegatto Filho A multipurpose machine learning approach to predict COVID-19 negative prognosis in São Paulo, Brazil
description	Abstract The new coronavirus disease (COVID-19) is a challenge for clinical decision-making and the effective allocation of healthcare resources. An accurate prognostic assessment is necessary to improve survival of patients, especially in developing countries. This study proposes to predict the risk of developing critical conditions in COVID-19 patients by training multipurpose algorithms. We followed a total of 1040 patients with a positive RT-PCR diagnosis for COVID-19 from a large hospital from São Paulo, Brazil, from March to June 2020, of which 288 (28%) presented a severe prognosis, i.e. Intensive Care Unit (ICU) admission, use of mechanical ventilation or death. We used routinely-collected laboratory, clinical and demographic data to train five machine learning algorithms (artificial neural networks, extra trees, random forests, catboost, and extreme gradient boosting). We used a random sample of 70% of patients to train the algorithms and 30% were left for performance assessment, simulating new unseen data. In order to assess if the algorithms could capture general severe prognostic patterns, each model was trained by combining two out of three outcomes to predict the other. All algorithms presented very high predictive performance (average AUROC of 0.92, sensitivity of 0.92, and specificity of 0.82). The three most important variables for the multipurpose algorithms were ratio of lymphocyte per C-reactive protein, C-reactive protein and Braden Scale. The results highlight the possibility that machine learning algorithms are able to predict unspecific negative COVID-19 outcomes from routinely-collected data.
format	article
author	Fernando Timoteo Fernandes Tiago Almeida de Oliveira Cristiane Esteves Teixeira Andre Filipe de Moraes Batista Gabriel Dalla Costa Alexandre Dias Porto Chiavegatto Filho
author_facet	Fernando Timoteo Fernandes Tiago Almeida de Oliveira Cristiane Esteves Teixeira Andre Filipe de Moraes Batista Gabriel Dalla Costa Alexandre Dias Porto Chiavegatto Filho
author_sort	Fernando Timoteo Fernandes
title	A multipurpose machine learning approach to predict COVID-19 negative prognosis in São Paulo, Brazil
title_short	A multipurpose machine learning approach to predict COVID-19 negative prognosis in São Paulo, Brazil
title_full	A multipurpose machine learning approach to predict COVID-19 negative prognosis in São Paulo, Brazil
title_fullStr	A multipurpose machine learning approach to predict COVID-19 negative prognosis in São Paulo, Brazil
title_full_unstemmed	A multipurpose machine learning approach to predict COVID-19 negative prognosis in São Paulo, Brazil
title_sort	multipurpose machine learning approach to predict covid-19 negative prognosis in são paulo, brazil
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/66f01b49c2e04bd0b657561542dabf2c
work_keys_str_mv	AT fernandotimoteofernandes amultipurposemachinelearningapproachtopredictcovid19negativeprognosisinsaopaulobrazil AT tiagoalmeidadeoliveira amultipurposemachinelearningapproachtopredictcovid19negativeprognosisinsaopaulobrazil AT cristianeestevesteixeira amultipurposemachinelearningapproachtopredictcovid19negativeprognosisinsaopaulobrazil AT andrefilipedemoraesbatista amultipurposemachinelearningapproachtopredictcovid19negativeprognosisinsaopaulobrazil AT gabrieldallacosta amultipurposemachinelearningapproachtopredictcovid19negativeprognosisinsaopaulobrazil AT alexandrediasportochiavegattofilho amultipurposemachinelearningapproachtopredictcovid19negativeprognosisinsaopaulobrazil AT fernandotimoteofernandes multipurposemachinelearningapproachtopredictcovid19negativeprognosisinsaopaulobrazil AT tiagoalmeidadeoliveira multipurposemachinelearningapproachtopredictcovid19negativeprognosisinsaopaulobrazil AT cristianeestevesteixeira multipurposemachinelearningapproachtopredictcovid19negativeprognosisinsaopaulobrazil AT andrefilipedemoraesbatista multipurposemachinelearningapproachtopredictcovid19negativeprognosisinsaopaulobrazil AT gabrieldallacosta multipurposemachinelearningapproachtopredictcovid19negativeprognosisinsaopaulobrazil AT alexandrediasportochiavegattofilho multipurposemachinelearningapproachtopredictcovid19negativeprognosisinsaopaulobrazil
_version_	1718391314041536512

A multipurpose machine learning approach to predict COVID-19 negative prognosis in São Paulo, Brazil

Ejemplares similares