Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs.

Detalhes bibliográficos
Autor(a) principal: Alves, Marcos Antonio
Data de Publicação: 2021
Outros Autores: Castro, Giulia Zanon de, Oliveira, Bruno Alberto Soares, Ferreira, Leonardo Augusto, Ramírez, Jaime Arturo, Silva, Rodrigo César Pedrosa, Guimarães, Frederico Gadelha
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UFOP
Texto Completo: http://www.repositorio.ufop.br/jspui/handle/123456789/15797
https://doi.org/10.1016/j.compbiomed.2021.104335
Resumo: The sudden outbreak of coronavirus disease 2019 (COVID-19) revealed the need for fast and reliable automatic tools to help health teams. This paper aims to present understandable solutions based on Machine Learning (ML) techniques to deal with COVID-19 screening in routine blood tests. We tested different ML classifiers in a public dataset from the Hospital Albert Einstein, São Paulo, Brazil. After cleaning and pre-processing the data has 608 patients, of which 84 are positive for COVID-19 confirmed by RT-PCR. To understand the model decisions, we introduce (i) a local Decision Tree Explainer (DTX) for local explanation and (ii) a Criteria Graph to aggregate these explanations and portrait a global picture of the results. Random Forest (RF) classifier achieved the best results (accuracy 0.88, F1–score 0.76, sensitivity 0.66, specificity 0.91, and AUROC 0.86). By using DTX and Criteria Graph for cases confirmed by the RF, it was possible to find some patterns among the individuals able to aid the clinicians to understand the interconnection among the blood parameters either globally or on a case-by- case basis. The results are in accordance with the literature and the proposed methodology may be embedded in an electronic health record system.
id UFOP_ae76b8ddea924569005f483abf10f2c3
oai_identifier_str oai:repositorio.ufop.br:123456789/15797
network_acronym_str UFOP
network_name_str Repositório Institucional da UFOP
repository_id_str 3233
spelling Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs.Explainable artificial intelligenceThe sudden outbreak of coronavirus disease 2019 (COVID-19) revealed the need for fast and reliable automatic tools to help health teams. This paper aims to present understandable solutions based on Machine Learning (ML) techniques to deal with COVID-19 screening in routine blood tests. We tested different ML classifiers in a public dataset from the Hospital Albert Einstein, São Paulo, Brazil. After cleaning and pre-processing the data has 608 patients, of which 84 are positive for COVID-19 confirmed by RT-PCR. To understand the model decisions, we introduce (i) a local Decision Tree Explainer (DTX) for local explanation and (ii) a Criteria Graph to aggregate these explanations and portrait a global picture of the results. Random Forest (RF) classifier achieved the best results (accuracy 0.88, F1–score 0.76, sensitivity 0.66, specificity 0.91, and AUROC 0.86). By using DTX and Criteria Graph for cases confirmed by the RF, it was possible to find some patterns among the individuals able to aid the clinicians to understand the interconnection among the blood parameters either globally or on a case-by- case basis. The results are in accordance with the literature and the proposed methodology may be embedded in an electronic health record system.2022-11-10T21:00:20Z2022-11-10T21:00:20Z2021info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfALVES, M. A. et al. Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs. Computers in Biology and Medicine, v. 132, artigo 104335, 2021. Disponível em: <https://www.sciencedirect.com/science/article/pii/S0010482521001293>. Acesso em: 06 jul. 2022.0010-4825http://www.repositorio.ufop.br/jspui/handle/123456789/15797https://doi.org/10.1016/j.compbiomed.2021.104335This article is made available under the Elsevier license (http://www.elsevier.com/open-access/userlicense/1.0/). Fonte: o PDF do artigo.info:eu-repo/semantics/openAccessAlves, Marcos AntonioCastro, Giulia Zanon deOliveira, Bruno Alberto SoaresFerreira, Leonardo AugustoRamírez, Jaime ArturoSilva, Rodrigo César PedrosaGuimarães, Frederico Gadelhaengreponame:Repositório Institucional da UFOPinstname:Universidade Federal de Ouro Preto (UFOP)instacron:UFOP2022-11-10T21:00:27Zoai:repositorio.ufop.br:123456789/15797Repositório InstitucionalPUBhttp://www.repositorio.ufop.br/oai/requestrepositorio@ufop.edu.bropendoar:32332022-11-10T21:00:27Repositório Institucional da UFOP - Universidade Federal de Ouro Preto (UFOP)false
dc.title.none.fl_str_mv Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs.
title Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs.
spellingShingle Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs.
Alves, Marcos Antonio
Explainable artificial intelligence
title_short Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs.
title_full Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs.
title_fullStr Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs.
title_full_unstemmed Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs.
title_sort Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs.
author Alves, Marcos Antonio
author_facet Alves, Marcos Antonio
Castro, Giulia Zanon de
Oliveira, Bruno Alberto Soares
Ferreira, Leonardo Augusto
Ramírez, Jaime Arturo
Silva, Rodrigo César Pedrosa
Guimarães, Frederico Gadelha
author_role author
author2 Castro, Giulia Zanon de
Oliveira, Bruno Alberto Soares
Ferreira, Leonardo Augusto
Ramírez, Jaime Arturo
Silva, Rodrigo César Pedrosa
Guimarães, Frederico Gadelha
author2_role author
author
author
author
author
author
dc.contributor.author.fl_str_mv Alves, Marcos Antonio
Castro, Giulia Zanon de
Oliveira, Bruno Alberto Soares
Ferreira, Leonardo Augusto
Ramírez, Jaime Arturo
Silva, Rodrigo César Pedrosa
Guimarães, Frederico Gadelha
dc.subject.por.fl_str_mv Explainable artificial intelligence
topic Explainable artificial intelligence
description The sudden outbreak of coronavirus disease 2019 (COVID-19) revealed the need for fast and reliable automatic tools to help health teams. This paper aims to present understandable solutions based on Machine Learning (ML) techniques to deal with COVID-19 screening in routine blood tests. We tested different ML classifiers in a public dataset from the Hospital Albert Einstein, São Paulo, Brazil. After cleaning and pre-processing the data has 608 patients, of which 84 are positive for COVID-19 confirmed by RT-PCR. To understand the model decisions, we introduce (i) a local Decision Tree Explainer (DTX) for local explanation and (ii) a Criteria Graph to aggregate these explanations and portrait a global picture of the results. Random Forest (RF) classifier achieved the best results (accuracy 0.88, F1–score 0.76, sensitivity 0.66, specificity 0.91, and AUROC 0.86). By using DTX and Criteria Graph for cases confirmed by the RF, it was possible to find some patterns among the individuals able to aid the clinicians to understand the interconnection among the blood parameters either globally or on a case-by- case basis. The results are in accordance with the literature and the proposed methodology may be embedded in an electronic health record system.
publishDate 2021
dc.date.none.fl_str_mv 2021
2022-11-10T21:00:20Z
2022-11-10T21:00:20Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv ALVES, M. A. et al. Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs. Computers in Biology and Medicine, v. 132, artigo 104335, 2021. Disponível em: <https://www.sciencedirect.com/science/article/pii/S0010482521001293>. Acesso em: 06 jul. 2022.
0010-4825
http://www.repositorio.ufop.br/jspui/handle/123456789/15797
https://doi.org/10.1016/j.compbiomed.2021.104335
identifier_str_mv ALVES, M. A. et al. Explaining machine learning based diagnosis of COVID-19 from routine blood tests with decision trees and criteria graphs. Computers in Biology and Medicine, v. 132, artigo 104335, 2021. Disponível em: <https://www.sciencedirect.com/science/article/pii/S0010482521001293>. Acesso em: 06 jul. 2022.
0010-4825
url http://www.repositorio.ufop.br/jspui/handle/123456789/15797
https://doi.org/10.1016/j.compbiomed.2021.104335
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Institucional da UFOP
instname:Universidade Federal de Ouro Preto (UFOP)
instacron:UFOP
instname_str Universidade Federal de Ouro Preto (UFOP)
instacron_str UFOP
institution UFOP
reponame_str Repositório Institucional da UFOP
collection Repositório Institucional da UFOP
repository.name.fl_str_mv Repositório Institucional da UFOP - Universidade Federal de Ouro Preto (UFOP)
repository.mail.fl_str_mv repositorio@ufop.edu.br
_version_ 1813002858202660864