COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence

Autores
Dorr, Francisco; Chaves, Hernán; Serra, María Mercedes; Ramirez, Andres; Costa, Martín Elías; Seia, Joaquín Oscar; Cejas, Claudia; Castro, Marcelo; Eyheremendy, Eduardo; Fernández Slezak, Diego; Farez, Mauricio Franco
Año de publicación
2020
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
PurposeTo investigate the diagnostic performance of an Artificial Intelligence (AI) system for detection of COVID-19 in chest radiographs (CXR), and compare results to those of physicians working alone, or with AI support.Materials and methodsAn AI system was fine-tuned to discriminate confirmed COVID-19 pneumonia, from other viral and bacterial pneumonia and non-pneumonia patients and used to review 302 CXR images from adult patients retrospectively sourced from nine different databases. Fifty-four physicians blind to diagnosis, were invited to interpret images under identical conditions in a test set, and randomly assigned either to receive or not receive support from the AI system. Comparisons were then made between diagnostic performance of physicians working with and without AI support. AI system performance was evaluated using the area under the receiver operating characteristic (AUROC), and sensitivity and specificity of physician performance compared to that of the AI system.ResultsDiscrimination by the AI system of COVID-19 pneumonia showed an AUROC curve of 0.96 in the validation and 0.83 in the external test set, respectively. The AI system outperformed physicians in the AUROC overall (70% increase in sensitivity and 1% increase in specificity, p < 0.0001). When working with AI support, physicians increased their diagnostic sensitivity from 47% to 61% (p < 0.001), although specificity decreased from 79% to 75% (p = 0.007).ConclusionsOur results suggest interpreting chest radiographs (CXR) supported by AI, increases physician diagnostic sensitivity for COVID-19 detection. This approach involving a human-machine partnership may help expedite triaging efforts and improve resource allocation in the current crisis.
Fil: Dorr, Francisco. Entelai; Argentina
Fil: Chaves, Hernán. Entelai; Argentina. Fundación P/la Lucha C/enferm. neurológicas Infancia. Instituto de Neurociencias. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Neurociencias; Argentina
Fil: Serra, María Mercedes. Entelai; Argentina. Fundación P/la Lucha C/enferm. neurológicas Infancia. Instituto de Neurociencias. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Neurociencias; Argentina
Fil: Ramirez, Andres. Entelai; Argentina
Fil: Costa, Martín Elías. Entelai; Argentina
Fil: Seia, Joaquín Oscar. Entelai; Argentina
Fil: Cejas, Claudia. Fundación P/la Lucha C/enferm. neurológicas Infancia. Instituto de Neurociencias. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Neurociencias; Argentina
Fil: Castro, Marcelo. Departamento de Diagnóstico por Imágenes, Clínica Indisa ; Chile
Fil: Eyheremendy, Eduardo. Hospital Alemán; Argentina
Fil: Fernández Slezak, Diego. Entelai; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigación en Ciencias de la Computación; Argentina
Fil: Farez, Mauricio Franco. Entelai; Argentina. Fundación P/la Lucha C/enferm. neurológicas Infancia. Instituto de Neurociencias. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Neurociencias; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Materia
DEEP LEARNING
COVID
THORAX X-RAY
COVID-19
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/129095
Acceder
id CONICETDig_4b7e68a04435fad95a26d14a1dab48b1
oai_identifier_str oai:ri.conicet.gov.ar:11336/129095
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligenceDorr, FranciscoChaves, HernánSerra, María MercedesRamirez, AndresCosta, Martín ElíasSeia, Joaquín OscarCejas, ClaudiaCastro, MarceloEyheremendy, EduardoFernández Slezak, DiegoFarez, Mauricio FrancoDEEP LEARNINGCOVIDTHORAX X-RAYCOVID-19https://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1PurposeTo investigate the diagnostic performance of an Artificial Intelligence (AI) system for detection of COVID-19 in chest radiographs (CXR), and compare results to those of physicians working alone, or with AI support.Materials and methodsAn AI system was fine-tuned to discriminate confirmed COVID-19 pneumonia, from other viral and bacterial pneumonia and non-pneumonia patients and used to review 302 CXR images from adult patients retrospectively sourced from nine different databases. Fifty-four physicians blind to diagnosis, were invited to interpret images under identical conditions in a test set, and randomly assigned either to receive or not receive support from the AI system. Comparisons were then made between diagnostic performance of physicians working with and without AI support. AI system performance was evaluated using the area under the receiver operating characteristic (AUROC), and sensitivity and specificity of physician performance compared to that of the AI system.ResultsDiscrimination by the AI system of COVID-19 pneumonia showed an AUROC curve of 0.96 in the validation and 0.83 in the external test set, respectively. The AI system outperformed physicians in the AUROC overall (70% increase in sensitivity and 1% increase in specificity, p < 0.0001). When working with AI support, physicians increased their diagnostic sensitivity from 47% to 61% (p < 0.001), although specificity decreased from 79% to 75% (p = 0.007).ConclusionsOur results suggest interpreting chest radiographs (CXR) supported by AI, increases physician diagnostic sensitivity for COVID-19 detection. This approach involving a human-machine partnership may help expedite triaging efforts and improve resource allocation in the current crisis.Fil: Dorr, Francisco. Entelai; ArgentinaFil: Chaves, Hernán. Entelai; Argentina. Fundación P/la Lucha C/enferm. neurológicas Infancia. Instituto de Neurociencias. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Neurociencias; ArgentinaFil: Serra, María Mercedes. Entelai; Argentina. Fundación P/la Lucha C/enferm. neurológicas Infancia. Instituto de Neurociencias. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Neurociencias; ArgentinaFil: Ramirez, Andres. Entelai; ArgentinaFil: Costa, Martín Elías. Entelai; ArgentinaFil: Seia, Joaquín Oscar. Entelai; ArgentinaFil: Cejas, Claudia. Fundación P/la Lucha C/enferm. neurológicas Infancia. Instituto de Neurociencias. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Neurociencias; ArgentinaFil: Castro, Marcelo. Departamento de Diagnóstico por Imágenes, Clínica Indisa ; ChileFil: Eyheremendy, Eduardo. Hospital Alemán; ArgentinaFil: Fernández Slezak, Diego. Entelai; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigación en Ciencias de la Computación; ArgentinaFil: Farez, Mauricio Franco. Entelai; Argentina. Fundación P/la Lucha C/enferm. neurológicas Infancia. Instituto de Neurociencias. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Neurociencias; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaElsevier2020-12info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/129095Dorr, Francisco; Chaves, Hernán; Serra, María Mercedes; Ramirez, Andres; Costa, Martín Elías; et al.; COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence; Elsevier; Intelligence-Based Medicine; 3-4; 100014; 12-2020; 1-72666-5212CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/pii/S2666521220300144?via%3Dihubinfo:eu-repo/semantics/altIdentifier/doi/10.1016/j.ibmed.2020.100014info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-nd/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T09:38:36Zoai:ri.conicet.gov.ar:11336/129095instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 09:38:37.181CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence
title COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence
spellingShingle COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence
Dorr, Francisco
DEEP LEARNING
COVID
THORAX X-RAY
COVID-19
title_short COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence
title_full COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence
title_fullStr COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence
title_full_unstemmed COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence
title_sort COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence
dc.creator.none.fl_str_mv Dorr, Francisco
Chaves, Hernán
Serra, María Mercedes
Ramirez, Andres
Costa, Martín Elías
Seia, Joaquín Oscar
Cejas, Claudia
Castro, Marcelo
Eyheremendy, Eduardo
Fernández Slezak, Diego
Farez, Mauricio Franco
author Dorr, Francisco
author_facet Dorr, Francisco
Chaves, Hernán
Serra, María Mercedes
Ramirez, Andres
Costa, Martín Elías
Seia, Joaquín Oscar
Cejas, Claudia
Castro, Marcelo
Eyheremendy, Eduardo
Fernández Slezak, Diego
Farez, Mauricio Franco
author_role author
author2 Chaves, Hernán
Serra, María Mercedes
Ramirez, Andres
Costa, Martín Elías
Seia, Joaquín Oscar
Cejas, Claudia
Castro, Marcelo
Eyheremendy, Eduardo
Fernández Slezak, Diego
Farez, Mauricio Franco
author2_role author
author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv DEEP LEARNING
COVID
THORAX X-RAY
COVID-19
topic DEEP LEARNING
COVID
THORAX X-RAY
COVID-19
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv PurposeTo investigate the diagnostic performance of an Artificial Intelligence (AI) system for detection of COVID-19 in chest radiographs (CXR), and compare results to those of physicians working alone, or with AI support.Materials and methodsAn AI system was fine-tuned to discriminate confirmed COVID-19 pneumonia, from other viral and bacterial pneumonia and non-pneumonia patients and used to review 302 CXR images from adult patients retrospectively sourced from nine different databases. Fifty-four physicians blind to diagnosis, were invited to interpret images under identical conditions in a test set, and randomly assigned either to receive or not receive support from the AI system. Comparisons were then made between diagnostic performance of physicians working with and without AI support. AI system performance was evaluated using the area under the receiver operating characteristic (AUROC), and sensitivity and specificity of physician performance compared to that of the AI system.ResultsDiscrimination by the AI system of COVID-19 pneumonia showed an AUROC curve of 0.96 in the validation and 0.83 in the external test set, respectively. The AI system outperformed physicians in the AUROC overall (70% increase in sensitivity and 1% increase in specificity, p < 0.0001). When working with AI support, physicians increased their diagnostic sensitivity from 47% to 61% (p < 0.001), although specificity decreased from 79% to 75% (p = 0.007).ConclusionsOur results suggest interpreting chest radiographs (CXR) supported by AI, increases physician diagnostic sensitivity for COVID-19 detection. This approach involving a human-machine partnership may help expedite triaging efforts and improve resource allocation in the current crisis.
Fil: Dorr, Francisco. Entelai; Argentina
Fil: Chaves, Hernán. Entelai; Argentina. Fundación P/la Lucha C/enferm. neurológicas Infancia. Instituto de Neurociencias. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Neurociencias; Argentina
Fil: Serra, María Mercedes. Entelai; Argentina. Fundación P/la Lucha C/enferm. neurológicas Infancia. Instituto de Neurociencias. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Neurociencias; Argentina
Fil: Ramirez, Andres. Entelai; Argentina
Fil: Costa, Martín Elías. Entelai; Argentina
Fil: Seia, Joaquín Oscar. Entelai; Argentina
Fil: Cejas, Claudia. Fundación P/la Lucha C/enferm. neurológicas Infancia. Instituto de Neurociencias. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Neurociencias; Argentina
Fil: Castro, Marcelo. Departamento de Diagnóstico por Imágenes, Clínica Indisa ; Chile
Fil: Eyheremendy, Eduardo. Hospital Alemán; Argentina
Fil: Fernández Slezak, Diego. Entelai; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigación en Ciencias de la Computación; Argentina
Fil: Farez, Mauricio Franco. Entelai; Argentina. Fundación P/la Lucha C/enferm. neurológicas Infancia. Instituto de Neurociencias. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Neurociencias; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
description PurposeTo investigate the diagnostic performance of an Artificial Intelligence (AI) system for detection of COVID-19 in chest radiographs (CXR), and compare results to those of physicians working alone, or with AI support.Materials and methodsAn AI system was fine-tuned to discriminate confirmed COVID-19 pneumonia, from other viral and bacterial pneumonia and non-pneumonia patients and used to review 302 CXR images from adult patients retrospectively sourced from nine different databases. Fifty-four physicians blind to diagnosis, were invited to interpret images under identical conditions in a test set, and randomly assigned either to receive or not receive support from the AI system. Comparisons were then made between diagnostic performance of physicians working with and without AI support. AI system performance was evaluated using the area under the receiver operating characteristic (AUROC), and sensitivity and specificity of physician performance compared to that of the AI system.ResultsDiscrimination by the AI system of COVID-19 pneumonia showed an AUROC curve of 0.96 in the validation and 0.83 in the external test set, respectively. The AI system outperformed physicians in the AUROC overall (70% increase in sensitivity and 1% increase in specificity, p < 0.0001). When working with AI support, physicians increased their diagnostic sensitivity from 47% to 61% (p < 0.001), although specificity decreased from 79% to 75% (p = 0.007).ConclusionsOur results suggest interpreting chest radiographs (CXR) supported by AI, increases physician diagnostic sensitivity for COVID-19 detection. This approach involving a human-machine partnership may help expedite triaging efforts and improve resource allocation in the current crisis.
publishDate 2020
dc.date.none.fl_str_mv 2020-12
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/129095
Dorr, Francisco; Chaves, Hernán; Serra, María Mercedes; Ramirez, Andres; Costa, Martín Elías; et al.; COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence; Elsevier; Intelligence-Based Medicine; 3-4; 100014; 12-2020; 1-7
2666-5212
CONICET Digital
CONICET
url http://hdl.handle.net/11336/129095
identifier_str_mv Dorr, Francisco; Chaves, Hernán; Serra, María Mercedes; Ramirez, Andres; Costa, Martín Elías; et al.; COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence; Elsevier; Intelligence-Based Medicine; 3-4; 100014; 12-2020; 1-7
2666-5212
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/pii/S2666521220300144?via%3Dihub
info:eu-repo/semantics/altIdentifier/doi/10.1016/j.ibmed.2020.100014
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844613221018763264
score 13.070432

Publicaciones similares