Cargando…

Comparison of machine learning techniques to handle imbalanced COVID-19 CBC datasets

The Coronavirus pandemic caused by the novel SARS-CoV-2 has significantly impacted human health and the economy, especially in countries struggling with financial resources for medical testing and treatment, such as Brazil’s case, the third most affected country by the pandemic. In this scenario, ma...

Descripción completa

Detalles Bibliográficos
Autores principales: Dorn, Marcio, Grisci, Bruno Iochins, Narloch, Pedro Henrique, Feltes, Bruno César, Avila, Eduardo, Kahmann, Alessandro, Alho, Clarice Sampaio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8372002/
https://www.ncbi.nlm.nih.gov/pubmed/34458574
http://dx.doi.org/10.7717/peerj-cs.670
_version_ 1783739751283556352
author Dorn, Marcio
Grisci, Bruno Iochins
Narloch, Pedro Henrique
Feltes, Bruno César
Avila, Eduardo
Kahmann, Alessandro
Alho, Clarice Sampaio
author_facet Dorn, Marcio
Grisci, Bruno Iochins
Narloch, Pedro Henrique
Feltes, Bruno César
Avila, Eduardo
Kahmann, Alessandro
Alho, Clarice Sampaio
author_sort Dorn, Marcio
collection PubMed
description The Coronavirus pandemic caused by the novel SARS-CoV-2 has significantly impacted human health and the economy, especially in countries struggling with financial resources for medical testing and treatment, such as Brazil’s case, the third most affected country by the pandemic. In this scenario, machine learning techniques have been heavily employed to analyze different types of medical data, and aid decision making, offering a low-cost alternative. Due to the urgency to fight the pandemic, a massive amount of works are applying machine learning approaches to clinical data, including complete blood count (CBC) tests, which are among the most widely available medical tests. In this work, we review the most employed machine learning classifiers for CBC data, together with popular sampling methods to deal with the class imbalance. Additionally, we describe and critically analyze three publicly available Brazilian COVID-19 CBC datasets and evaluate the performance of eight classifiers and five sampling techniques on the selected datasets. Our work provides a panorama of which classifier and sampling methods provide the best results for different relevant metrics and discuss their impact on future analyses. The metrics and algorithms are introduced in a way to aid newcomers to the field. Finally, the panorama discussed here can significantly benefit the comparison of the results of new ML algorithms.
format Online
Article
Text
id pubmed-8372002
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-83720022021-08-26 Comparison of machine learning techniques to handle imbalanced COVID-19 CBC datasets Dorn, Marcio Grisci, Bruno Iochins Narloch, Pedro Henrique Feltes, Bruno César Avila, Eduardo Kahmann, Alessandro Alho, Clarice Sampaio PeerJ Comput Sci Bioinformatics The Coronavirus pandemic caused by the novel SARS-CoV-2 has significantly impacted human health and the economy, especially in countries struggling with financial resources for medical testing and treatment, such as Brazil’s case, the third most affected country by the pandemic. In this scenario, machine learning techniques have been heavily employed to analyze different types of medical data, and aid decision making, offering a low-cost alternative. Due to the urgency to fight the pandemic, a massive amount of works are applying machine learning approaches to clinical data, including complete blood count (CBC) tests, which are among the most widely available medical tests. In this work, we review the most employed machine learning classifiers for CBC data, together with popular sampling methods to deal with the class imbalance. Additionally, we describe and critically analyze three publicly available Brazilian COVID-19 CBC datasets and evaluate the performance of eight classifiers and five sampling techniques on the selected datasets. Our work provides a panorama of which classifier and sampling methods provide the best results for different relevant metrics and discuss their impact on future analyses. The metrics and algorithms are introduced in a way to aid newcomers to the field. Finally, the panorama discussed here can significantly benefit the comparison of the results of new ML algorithms. PeerJ Inc. 2021-08-12 /pmc/articles/PMC8372002/ /pubmed/34458574 http://dx.doi.org/10.7717/peerj-cs.670 Text en © 2021 Dorn et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Bioinformatics
Dorn, Marcio
Grisci, Bruno Iochins
Narloch, Pedro Henrique
Feltes, Bruno César
Avila, Eduardo
Kahmann, Alessandro
Alho, Clarice Sampaio
Comparison of machine learning techniques to handle imbalanced COVID-19 CBC datasets
title Comparison of machine learning techniques to handle imbalanced COVID-19 CBC datasets
title_full Comparison of machine learning techniques to handle imbalanced COVID-19 CBC datasets
title_fullStr Comparison of machine learning techniques to handle imbalanced COVID-19 CBC datasets
title_full_unstemmed Comparison of machine learning techniques to handle imbalanced COVID-19 CBC datasets
title_short Comparison of machine learning techniques to handle imbalanced COVID-19 CBC datasets
title_sort comparison of machine learning techniques to handle imbalanced covid-19 cbc datasets
topic Bioinformatics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8372002/
https://www.ncbi.nlm.nih.gov/pubmed/34458574
http://dx.doi.org/10.7717/peerj-cs.670
work_keys_str_mv AT dornmarcio comparisonofmachinelearningtechniquestohandleimbalancedcovid19cbcdatasets
AT griscibrunoiochins comparisonofmachinelearningtechniquestohandleimbalancedcovid19cbcdatasets
AT narlochpedrohenrique comparisonofmachinelearningtechniquestohandleimbalancedcovid19cbcdatasets
AT feltesbrunocesar comparisonofmachinelearningtechniquestohandleimbalancedcovid19cbcdatasets
AT avilaeduardo comparisonofmachinelearningtechniquestohandleimbalancedcovid19cbcdatasets
AT kahmannalessandro comparisonofmachinelearningtechniquestohandleimbalancedcovid19cbcdatasets
AT alhoclaricesampaio comparisonofmachinelearningtechniquestohandleimbalancedcovid19cbcdatasets