COVID-19 diagnosis by routine blood tests using machine learning

Abstract Physicians taking care of patients with COVID-19 have described different changes in routine blood parameters. However, these changes hinder them from performing COVID-19 diagnoses. We constructed a machine learning model for COVID-19 diagnosis that was based and cross-validated on the rout...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Matjaž Kukar, Gregor Gunčar, Tomaž Vovko, Simon Podnar, Peter Černelč, Miran Brvar, Mateja Zalaznik, Mateja Notar, Sašo Moškon, Marko Notar
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/5e6c746d9f7d42ca988860072ce91764
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:5e6c746d9f7d42ca988860072ce91764
record_format dspace
spelling oai:doaj.org-article:5e6c746d9f7d42ca988860072ce917642021-12-02T14:47:31ZCOVID-19 diagnosis by routine blood tests using machine learning10.1038/s41598-021-90265-92045-2322https://doaj.org/article/5e6c746d9f7d42ca988860072ce917642021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-90265-9https://doaj.org/toc/2045-2322Abstract Physicians taking care of patients with COVID-19 have described different changes in routine blood parameters. However, these changes hinder them from performing COVID-19 diagnoses. We constructed a machine learning model for COVID-19 diagnosis that was based and cross-validated on the routine blood tests of 5333 patients with various bacterial and viral infections, and 160 COVID-19-positive patients. We selected the operational ROC point at a sensitivity of 81.9% and a specificity of 97.9%. The cross-validated AUC was 0.97. The five most useful routine blood parameters for COVID-19 diagnosis according to the feature importance scoring of the XGBoost algorithm were: MCHC, eosinophil count, albumin, INR, and prothrombin activity percentage. t-SNE visualization showed that the blood parameters of the patients with a severe COVID-19 course are more like the parameters of a bacterial than a viral infection. The reported diagnostic accuracy is at least comparable and probably complementary to RT-PCR and chest CT studies. Patients with fever, cough, myalgia, and other symptoms can now have initial routine blood tests assessed by our diagnostic tool. All patients with a positive COVID-19 prediction would then undergo standard RT-PCR studies to confirm the diagnosis. We believe that our results represent a significant contribution to improvements in COVID-19 diagnosis.Matjaž KukarGregor GunčarTomaž VovkoSimon PodnarPeter ČernelčMiran BrvarMateja ZalaznikMateja NotarSašo MoškonMarko NotarNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Matjaž Kukar
Gregor Gunčar
Tomaž Vovko
Simon Podnar
Peter Černelč
Miran Brvar
Mateja Zalaznik
Mateja Notar
Sašo Moškon
Marko Notar
COVID-19 diagnosis by routine blood tests using machine learning
description Abstract Physicians taking care of patients with COVID-19 have described different changes in routine blood parameters. However, these changes hinder them from performing COVID-19 diagnoses. We constructed a machine learning model for COVID-19 diagnosis that was based and cross-validated on the routine blood tests of 5333 patients with various bacterial and viral infections, and 160 COVID-19-positive patients. We selected the operational ROC point at a sensitivity of 81.9% and a specificity of 97.9%. The cross-validated AUC was 0.97. The five most useful routine blood parameters for COVID-19 diagnosis according to the feature importance scoring of the XGBoost algorithm were: MCHC, eosinophil count, albumin, INR, and prothrombin activity percentage. t-SNE visualization showed that the blood parameters of the patients with a severe COVID-19 course are more like the parameters of a bacterial than a viral infection. The reported diagnostic accuracy is at least comparable and probably complementary to RT-PCR and chest CT studies. Patients with fever, cough, myalgia, and other symptoms can now have initial routine blood tests assessed by our diagnostic tool. All patients with a positive COVID-19 prediction would then undergo standard RT-PCR studies to confirm the diagnosis. We believe that our results represent a significant contribution to improvements in COVID-19 diagnosis.
format article
author Matjaž Kukar
Gregor Gunčar
Tomaž Vovko
Simon Podnar
Peter Černelč
Miran Brvar
Mateja Zalaznik
Mateja Notar
Sašo Moškon
Marko Notar
author_facet Matjaž Kukar
Gregor Gunčar
Tomaž Vovko
Simon Podnar
Peter Černelč
Miran Brvar
Mateja Zalaznik
Mateja Notar
Sašo Moškon
Marko Notar
author_sort Matjaž Kukar
title COVID-19 diagnosis by routine blood tests using machine learning
title_short COVID-19 diagnosis by routine blood tests using machine learning
title_full COVID-19 diagnosis by routine blood tests using machine learning
title_fullStr COVID-19 diagnosis by routine blood tests using machine learning
title_full_unstemmed COVID-19 diagnosis by routine blood tests using machine learning
title_sort covid-19 diagnosis by routine blood tests using machine learning
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/5e6c746d9f7d42ca988860072ce91764
work_keys_str_mv AT matjazkukar covid19diagnosisbyroutinebloodtestsusingmachinelearning
AT gregorguncar covid19diagnosisbyroutinebloodtestsusingmachinelearning
AT tomazvovko covid19diagnosisbyroutinebloodtestsusingmachinelearning
AT simonpodnar covid19diagnosisbyroutinebloodtestsusingmachinelearning
AT petercernelc covid19diagnosisbyroutinebloodtestsusingmachinelearning
AT miranbrvar covid19diagnosisbyroutinebloodtestsusingmachinelearning
AT matejazalaznik covid19diagnosisbyroutinebloodtestsusingmachinelearning
AT matejanotar covid19diagnosisbyroutinebloodtestsusingmachinelearning
AT sasomoskon covid19diagnosisbyroutinebloodtestsusingmachinelearning
AT markonotar covid19diagnosisbyroutinebloodtestsusingmachinelearning
_version_ 1718389510491865088