Deep neural network-estimated electrocardiographic age as a mortality predictor
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , , , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/247311 |
Resumo: | The electrocardiogram (ECG) is the most commonly used exam for the evaluation of cardiovascular diseases. Here we propose that the age predicted by artificial intelligence (AI) from the raw ECG (ECG-age) can be a measure of cardiovascular health. A deep neural network is trained to predict a patient’s age from the 12-lead ECG in the CODE study cohort (n = 1,558,415 patients). On a 15% hold-out split, patients with ECG-age more than 8 years greater than the chronological age have a higher mortality rate (hazard ratio (HR) 1.79, p < 0.001), whereas those with ECG-age more than 8 years smaller, have a lower mortality rate (HR 0.78, p < 0.001). Similar results are obtained in the external cohorts ELSA-Brasil (n = 14,236) and SaMi-Trop (n = 1,631). Moreover, even for apparent normal ECGs, the predicted ECG-age gap from the chronological age remains a statistically significant risk predictor. These results show that the AI-enabled analysis of the ECG can add prognostic information. |
id |
UFRGS-2_764df194118f3398b8d59a00d88bc2c1 |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/247311 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Lima, Emilly M.Ribeiro, Antônio H.Paixão, Gabriela Miana de MattosRibeiro, Manoel HortaPinto Filho, Marcelo MartinsGomes, Paulo R.Oliveira, Derick Matheus deSabino, Ester CerdeiraDuncan, Bruce BartholowGiatti, LuanaBarreto, Sandhi MariaMeira Junior, WagnerSchön, Thomas B.Ribeiro, Antônio Luiz Pinho2022-08-19T04:43:01Z20212041-1723http://hdl.handle.net/10183/247311001146455The electrocardiogram (ECG) is the most commonly used exam for the evaluation of cardiovascular diseases. Here we propose that the age predicted by artificial intelligence (AI) from the raw ECG (ECG-age) can be a measure of cardiovascular health. A deep neural network is trained to predict a patient’s age from the 12-lead ECG in the CODE study cohort (n = 1,558,415 patients). On a 15% hold-out split, patients with ECG-age more than 8 years greater than the chronological age have a higher mortality rate (hazard ratio (HR) 1.79, p < 0.001), whereas those with ECG-age more than 8 years smaller, have a lower mortality rate (HR 0.78, p < 0.001). Similar results are obtained in the external cohorts ELSA-Brasil (n = 14,236) and SaMi-Trop (n = 1,631). Moreover, even for apparent normal ECGs, the predicted ECG-age gap from the chronological age remains a statistically significant risk predictor. These results show that the AI-enabled analysis of the ECG can add prognostic information.application/pdfengNature communications. [London]. Vol. 12 (2021), 5117, [10 p.]EletrocardiografiaInteligência artificialDeep neural network-estimated electrocardiographic age as a mortality predictorEstrangeiroinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSTEXT001146455.pdf.txt001146455.pdf.txtExtracted Texttext/plain69220http://www.lume.ufrgs.br/bitstream/10183/247311/2/001146455.pdf.txt1efd115a7ff3d3135c92336d451060d4MD52ORIGINAL001146455.pdfTexto completo (inglês)application/pdf857866http://www.lume.ufrgs.br/bitstream/10183/247311/1/001146455.pdf1c94eb64bda3ad1a938ccfce658c4470MD5110183/2473112022-08-20 04:52:57.604779oai:www.lume.ufrgs.br:10183/247311Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2022-08-20T07:52:57Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Deep neural network-estimated electrocardiographic age as a mortality predictor |
title |
Deep neural network-estimated electrocardiographic age as a mortality predictor |
spellingShingle |
Deep neural network-estimated electrocardiographic age as a mortality predictor Lima, Emilly M. Eletrocardiografia Inteligência artificial |
title_short |
Deep neural network-estimated electrocardiographic age as a mortality predictor |
title_full |
Deep neural network-estimated electrocardiographic age as a mortality predictor |
title_fullStr |
Deep neural network-estimated electrocardiographic age as a mortality predictor |
title_full_unstemmed |
Deep neural network-estimated electrocardiographic age as a mortality predictor |
title_sort |
Deep neural network-estimated electrocardiographic age as a mortality predictor |
author |
Lima, Emilly M. |
author_facet |
Lima, Emilly M. Ribeiro, Antônio H. Paixão, Gabriela Miana de Mattos Ribeiro, Manoel Horta Pinto Filho, Marcelo Martins Gomes, Paulo R. Oliveira, Derick Matheus de Sabino, Ester Cerdeira Duncan, Bruce Bartholow Giatti, Luana Barreto, Sandhi Maria Meira Junior, Wagner Schön, Thomas B. Ribeiro, Antônio Luiz Pinho |
author_role |
author |
author2 |
Ribeiro, Antônio H. Paixão, Gabriela Miana de Mattos Ribeiro, Manoel Horta Pinto Filho, Marcelo Martins Gomes, Paulo R. Oliveira, Derick Matheus de Sabino, Ester Cerdeira Duncan, Bruce Bartholow Giatti, Luana Barreto, Sandhi Maria Meira Junior, Wagner Schön, Thomas B. Ribeiro, Antônio Luiz Pinho |
author2_role |
author author author author author author author author author author author author author |
dc.contributor.author.fl_str_mv |
Lima, Emilly M. Ribeiro, Antônio H. Paixão, Gabriela Miana de Mattos Ribeiro, Manoel Horta Pinto Filho, Marcelo Martins Gomes, Paulo R. Oliveira, Derick Matheus de Sabino, Ester Cerdeira Duncan, Bruce Bartholow Giatti, Luana Barreto, Sandhi Maria Meira Junior, Wagner Schön, Thomas B. Ribeiro, Antônio Luiz Pinho |
dc.subject.por.fl_str_mv |
Eletrocardiografia Inteligência artificial |
topic |
Eletrocardiografia Inteligência artificial |
description |
The electrocardiogram (ECG) is the most commonly used exam for the evaluation of cardiovascular diseases. Here we propose that the age predicted by artificial intelligence (AI) from the raw ECG (ECG-age) can be a measure of cardiovascular health. A deep neural network is trained to predict a patient’s age from the 12-lead ECG in the CODE study cohort (n = 1,558,415 patients). On a 15% hold-out split, patients with ECG-age more than 8 years greater than the chronological age have a higher mortality rate (hazard ratio (HR) 1.79, p < 0.001), whereas those with ECG-age more than 8 years smaller, have a lower mortality rate (HR 0.78, p < 0.001). Similar results are obtained in the external cohorts ELSA-Brasil (n = 14,236) and SaMi-Trop (n = 1,631). Moreover, even for apparent normal ECGs, the predicted ECG-age gap from the chronological age remains a statistically significant risk predictor. These results show that the AI-enabled analysis of the ECG can add prognostic information. |
publishDate |
2021 |
dc.date.issued.fl_str_mv |
2021 |
dc.date.accessioned.fl_str_mv |
2022-08-19T04:43:01Z |
dc.type.driver.fl_str_mv |
Estrangeiro info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10183/247311 |
dc.identifier.issn.pt_BR.fl_str_mv |
2041-1723 |
dc.identifier.nrb.pt_BR.fl_str_mv |
001146455 |
identifier_str_mv |
2041-1723 001146455 |
url |
http://hdl.handle.net/10183/247311 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
Nature communications. [London]. Vol. 12 (2021), 5117, [10 p.] |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/247311/2/001146455.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/247311/1/001146455.pdf |
bitstream.checksum.fl_str_mv |
1efd115a7ff3d3135c92336d451060d4 1c94eb64bda3ad1a938ccfce658c4470 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1801225065355804672 |