Deep forest model for diagnosing COVID-19 from routine blood tests

Abstract The Coronavirus Disease 2019 (COVID-19) global pandemic has threatened the lives of people worldwide and posed considerable challenges. Early and accurate screening of infected people is vital for combating the disease. To help with the limited quantity of swab tests, we propose a machine l...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Maryam AlJame, Ayyub Imtiaz, Imtiaz Ahmad, Ameer Mohammed
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/7fd5830ff5df43808a84ed305b31fa46
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7fd5830ff5df43808a84ed305b31fa46
record_format	dspace
spelling	oai:doaj.org-article:7fd5830ff5df43808a84ed305b31fa462021-12-02T17:08:23ZDeep forest model for diagnosing COVID-19 from routine blood tests10.1038/s41598-021-95957-w2045-2322https://doaj.org/article/7fd5830ff5df43808a84ed305b31fa462021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-95957-whttps://doaj.org/toc/2045-2322Abstract The Coronavirus Disease 2019 (COVID-19) global pandemic has threatened the lives of people worldwide and posed considerable challenges. Early and accurate screening of infected people is vital for combating the disease. To help with the limited quantity of swab tests, we propose a machine learning prediction model to accurately diagnose COVID-19 from clinical and/or routine laboratory data. The model exploits a new ensemble-based method called the deep forest (DF), where multiple classifiers in multiple layers are used to encourage diversity and improve performance. The cascade level employs the layer-by-layer processing and is constructed from three different classifiers: extra trees, XGBoost, and LightGBM. The prediction model was trained and evaluated on two publicly available datasets. Experimental results show that the proposed DF model has an accuracy of 99.5%, sensitivity of 95.28%, and specificity of 99.96%. These performance metrics are comparable to other well-established machine learning techniques, and hence DF model can serve as a fast screening tool for COVID-19 patients at places where testing is scarce.Maryam AlJameAyyub ImtiazImtiaz AhmadAmeer MohammedNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Maryam AlJame Ayyub Imtiaz Imtiaz Ahmad Ameer Mohammed Deep forest model for diagnosing COVID-19 from routine blood tests
description	Abstract The Coronavirus Disease 2019 (COVID-19) global pandemic has threatened the lives of people worldwide and posed considerable challenges. Early and accurate screening of infected people is vital for combating the disease. To help with the limited quantity of swab tests, we propose a machine learning prediction model to accurately diagnose COVID-19 from clinical and/or routine laboratory data. The model exploits a new ensemble-based method called the deep forest (DF), where multiple classifiers in multiple layers are used to encourage diversity and improve performance. The cascade level employs the layer-by-layer processing and is constructed from three different classifiers: extra trees, XGBoost, and LightGBM. The prediction model was trained and evaluated on two publicly available datasets. Experimental results show that the proposed DF model has an accuracy of 99.5%, sensitivity of 95.28%, and specificity of 99.96%. These performance metrics are comparable to other well-established machine learning techniques, and hence DF model can serve as a fast screening tool for COVID-19 patients at places where testing is scarce.
format	article
author	Maryam AlJame Ayyub Imtiaz Imtiaz Ahmad Ameer Mohammed
author_facet	Maryam AlJame Ayyub Imtiaz Imtiaz Ahmad Ameer Mohammed
author_sort	Maryam AlJame
title	Deep forest model for diagnosing COVID-19 from routine blood tests
title_short	Deep forest model for diagnosing COVID-19 from routine blood tests
title_full	Deep forest model for diagnosing COVID-19 from routine blood tests
title_fullStr	Deep forest model for diagnosing COVID-19 from routine blood tests
title_full_unstemmed	Deep forest model for diagnosing COVID-19 from routine blood tests
title_sort	deep forest model for diagnosing covid-19 from routine blood tests
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/7fd5830ff5df43808a84ed305b31fa46
work_keys_str_mv	AT maryamaljame deepforestmodelfordiagnosingcovid19fromroutinebloodtests AT ayyubimtiaz deepforestmodelfordiagnosingcovid19fromroutinebloodtests AT imtiazahmad deepforestmodelfordiagnosingcovid19fromroutinebloodtests AT ameermohammed deepforestmodelfordiagnosingcovid19fromroutinebloodtests
_version_	1718381562800635904

Deep forest model for diagnosing COVID-19 from routine blood tests

Ejemplares similares