Machine learning algorithm approach to complete blood count can be used as early predictor of COVID-19 outcome
Journal of Leukocyte Biology · 2025
DOI: 10.1093/jleuko/qiae223 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Leukocyte Biology, 2025. Verfasst von Cecília Horta Ramalho-Pinto und 15 weiteren Autor:innen. Beteiligte Einrichtung: Departamento de Bioquímica e Imunologia, Instituto de Ciências Biológicas, Universidade Federal de Minas Gerais, Av. Pres. Antônio Carlos, 6627, 3127…. Hauptthemen laut MEDLINE: COVID-19, Machine Learning, SARS-CoV-2. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Merck Sharp & Dohme, Conselho Nacional de Desenvolvimento Científico e Tecnológico, Coordenação de Aperfeiçoamento de Pessoal de Ensino Superior.
Abstract (Originalsprache)
Although the SARS-CoV-2 infection has established risk groups, identifying biomarkers for disease outcomes is still crucial to stratify patient risk and enhance clinical management. Optimal efficacy of COVID-19 antiviral medications relies on early administration within the initial 5 d of symptoms, assisting high-risk patients in avoiding hospitalization and improving survival chances. The complete blood count (CBC) can be an efficient and affordable option to find biomarkers that predict the COVID-19 prognosis due to infection-induced alterations in various blood parameters. This study aimed to associate hematological parameters with different COVID-19 clinical forms and utilizes them as disease outcome predictors. We performed a CBC in blood samples from 297 individuals with COVID-19 from Belo Horizonte, Brazil. Statistical analysis, as well as ROC Curves and machine learning Decision Tree algorithms were used to identify correlations, and their accuracy, between blood parameters and disease severity. In the initial 4 d of infection, traditional hematological COVID-19 alterations, such as lymphopenia, were not yet apparent. However, the monocyte percentage and granulocyte-to-lymphocyte ratio (GLR) proved to be reliable predictors for hospitalization, even in cases where patients exhibited mild symptoms that later progressed to hospitalization. Thus, our findings demonstrate that COVID-19 patients with monocyte percentages lower than 7.7% and a GLR higher than 8.75 are assigned to the hospitalized group with a precision of 86%. This suggests that these variables can serve as important biomarkers in predicting disease outcomes and could be used to differentiate patients at hospital admission for managing therapeutic interventions, including early antiviral administration. Moreover, they are simple parameters that can be useful in minimally equipped health care units.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Departamento de Bioquímica e Imunologia, Instituto de Ciências Biológicas, Universidade Federal de Minas Gerais, Av. Pres. Antônio Carlos, 6627, 31270-901, Belo Horizonte, Brazil.
- Departamento de Medicina, Universidade Federal de Juiz de Fora, Av. Doutor Raimundo Monteiro Resende, 330, 35010-177, Governador Valadares, Brazil.
- Instituto de Biotecnologia, Universidade Federal de Uberlândia, R. Padre Pavoni, 290, 38701-002, Patos de Minas, Brazil.
- Departamento de Clínica Médica, Faculdade de Medicina, Universidade Federal de Minas Gerais, Av. Alfredo Balena, 190, 30130-100, Belo Horizonte, Brazil.
- Hospital Universitário Risoleta Tolentino Neves, R. das Gabirobas, 1, 31744-012, Belo Horizonte, Brazil.
- Instituto de Pesquisa René Rachou, Fundação Oswaldo Cruz - MG, Av. Augusto de Lima, 1715, 30190-002, Belo Horizonte, Brazil.
ORCID-Profile: Cecília Horta Ramalho-Pinto, Lucas Haniel Araújo Ventura, Giovanna Caliman Camatta, Gabriela Silveira-Nunes, Hugo Itaru Sato, Henrique Cerqueira Guimarães, Rafael Calvão Barbuto, Santuza Maria Ribeiro Teixeira, Unaí Tupinambás, Andrea Teixeira-Carvalho, Ana Maria Caetano Faria
Förderung
- Merck Sharp & Dohme
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- Coordenação de Aperfeiçoamento de Pessoal de Ensino Superior
- CNPq, Brazil
Zitieren
APA
Ramalho-Pinto, C. H., Ventura, L. H. A., Camatta, G. C., Silveira-Nunes, G., Gomes, M. S., Sato, H. I., Costa, M. S., Guimarães, H. C., Barbuto, R. C., Martins-Filho, O. A., Amaral, L. R., Bertarini, P. L. L., Teixeira, S. M. R., Tupinambás, U., Teixeira-Carvalho, A., & Faria, A. M. C. (2025). Machine learning algorithm approach to complete blood count can be used as early predictor of COVID-19 outcome. Journal of Leukocyte Biology. https://doi.org/10.1093/jleuko/qiae223
Vancouver
Ramalho-Pinto CH, Ventura LHA, Camatta GC, Silveira-Nunes G, Gomes MS, Sato HI, et al. Machine learning algorithm approach to complete blood count can be used as early predictor of COVID-19 outcome. Journal of Leukocyte Biology. 2025. doi:10.1093/jleuko/qiae223
BibTeX
@article{RamalhoPinto2025,
author = {Ramalho-Pinto, Cecília Horta and Ventura, Lucas Haniel Araújo and Camatta, Giovanna Caliman and Silveira-Nunes, Gabriela and Gomes, Matheus Souza and Sato, Hugo Itaru and Costa, Murilo Soares and Guimarães, Henrique Cerqueira and Barbuto, Rafael Calvão and Martins-Filho, Olindo Assis and Amaral, Laurence Rodrigues and Bertarini, Pedro Luiz Lima and Teixeira, Santuza Maria Ribeiro and Tupinambás, Unaí and Teixeira-Carvalho, Andrea and Faria, Ana Maria Caetano},
title = {Machine learning algorithm approach to complete blood count can be used as early predictor of COVID-19 outcome},
journal = {Journal of Leukocyte Biology},
year = {2025},
doi = {10.1093/jleuko/qiae223}
}
EUVIMED