Development of a prediction score for in-hospital mortality in COVID-19 patients with acute kidney injury: a machine learning approach
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1038/s41598-021-03894-5 http://hdl.handle.net/11449/230191 |
Resumo: | Acute kidney injury (AKI) is frequently associated with COVID-19 and it is considered an indicator of disease severity. This study aimed to develop a prognostic score for predicting in-hospital mortality in COVID-19 patients with AKI (AKI-COV score). This was a cross-sectional multicentre prospective cohort study in the Latin America AKI COVID-19 Registry. A total of 870 COVID-19 patients with AKI defined according to the KDIGO were included between 1 May 2020 and 31 December 2020. We evaluated four categories of predictor variables that were available at the time of the diagnosis of AKI: (1) demographic data; (2) comorbidities and conditions at admission; (3) laboratory exams within 24 h; and (4) characteristics and causes of AKI. We used a machine learning approach to fit models in the training set using tenfold cross-validation and validated the accuracy using the area under the receiver operating characteristic curve (AUC-ROC). The coefficients of the best model (Elastic Net) were used to build the predictive AKI-COV score. The AKI-COV score had an AUC-ROC of 0.823 (95% CI 0.761–0.885) in the validation cohort. The use of the AKI-COV score may assist healthcare workers in identifying hospitalized COVID-19 patients with AKI that may require more intensive monitoring and can be used for resource allocation. |
id |
UNSP_9ac3caea678c482a0ed8a5300c5e332f |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/230191 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Development of a prediction score for in-hospital mortality in COVID-19 patients with acute kidney injury: a machine learning approachAcute kidney injury (AKI) is frequently associated with COVID-19 and it is considered an indicator of disease severity. This study aimed to develop a prognostic score for predicting in-hospital mortality in COVID-19 patients with AKI (AKI-COV score). This was a cross-sectional multicentre prospective cohort study in the Latin America AKI COVID-19 Registry. A total of 870 COVID-19 patients with AKI defined according to the KDIGO were included between 1 May 2020 and 31 December 2020. We evaluated four categories of predictor variables that were available at the time of the diagnosis of AKI: (1) demographic data; (2) comorbidities and conditions at admission; (3) laboratory exams within 24 h; and (4) characteristics and causes of AKI. We used a machine learning approach to fit models in the training set using tenfold cross-validation and validated the accuracy using the area under the receiver operating characteristic curve (AUC-ROC). The coefficients of the best model (Elastic Net) were used to build the predictive AKI-COV score. The AKI-COV score had an AUC-ROC of 0.823 (95% CI 0.761–0.885) in the validation cohort. The use of the AKI-COV score may assist healthcare workers in identifying hospitalized COVID-19 patients with AKI that may require more intensive monitoring and can be used for resource allocation.Department of Internal Medicine Botucatu Medical School University of São Paulo State–UNESP, Avenida Professor Mario Rubens MontenegroDivision of Nephrology Hospital Obrero No. 2 − CNS Universidad Mayor de San Simon School of MedicineDivision of Nephrology School of Medicine Universidad de La RepúblicaDepartment of Internal Medicine Botucatu Medical School University of São Paulo State–UNESP, Avenida Professor Mario Rubens MontenegroUniversidade Estadual Paulista (UNESP)School of MedicineUniversidad de La RepúblicaPonce, Daniela [UNESP]de Andrade, Luís Gustavo Modelli [UNESP]Granado, Rolando Claure-DelFerreiro-Fuentes, AlejandroLombardi, Raul2022-04-29T08:38:19Z2022-04-29T08:38:19Z2021-12-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1038/s41598-021-03894-5Scientific Reports, v. 11, n. 1, 2021.2045-2322http://hdl.handle.net/11449/23019110.1038/s41598-021-03894-52-s2.0-85122537958Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengScientific Reportsinfo:eu-repo/semantics/openAccess2022-04-29T08:38:19Zoai:repositorio.unesp.br:11449/230191Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462022-04-29T08:38:19Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Development of a prediction score for in-hospital mortality in COVID-19 patients with acute kidney injury: a machine learning approach |
title |
Development of a prediction score for in-hospital mortality in COVID-19 patients with acute kidney injury: a machine learning approach |
spellingShingle |
Development of a prediction score for in-hospital mortality in COVID-19 patients with acute kidney injury: a machine learning approach Ponce, Daniela [UNESP] |
title_short |
Development of a prediction score for in-hospital mortality in COVID-19 patients with acute kidney injury: a machine learning approach |
title_full |
Development of a prediction score for in-hospital mortality in COVID-19 patients with acute kidney injury: a machine learning approach |
title_fullStr |
Development of a prediction score for in-hospital mortality in COVID-19 patients with acute kidney injury: a machine learning approach |
title_full_unstemmed |
Development of a prediction score for in-hospital mortality in COVID-19 patients with acute kidney injury: a machine learning approach |
title_sort |
Development of a prediction score for in-hospital mortality in COVID-19 patients with acute kidney injury: a machine learning approach |
author |
Ponce, Daniela [UNESP] |
author_facet |
Ponce, Daniela [UNESP] de Andrade, Luís Gustavo Modelli [UNESP] Granado, Rolando Claure-Del Ferreiro-Fuentes, Alejandro Lombardi, Raul |
author_role |
author |
author2 |
de Andrade, Luís Gustavo Modelli [UNESP] Granado, Rolando Claure-Del Ferreiro-Fuentes, Alejandro Lombardi, Raul |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) School of Medicine Universidad de La República |
dc.contributor.author.fl_str_mv |
Ponce, Daniela [UNESP] de Andrade, Luís Gustavo Modelli [UNESP] Granado, Rolando Claure-Del Ferreiro-Fuentes, Alejandro Lombardi, Raul |
description |
Acute kidney injury (AKI) is frequently associated with COVID-19 and it is considered an indicator of disease severity. This study aimed to develop a prognostic score for predicting in-hospital mortality in COVID-19 patients with AKI (AKI-COV score). This was a cross-sectional multicentre prospective cohort study in the Latin America AKI COVID-19 Registry. A total of 870 COVID-19 patients with AKI defined according to the KDIGO were included between 1 May 2020 and 31 December 2020. We evaluated four categories of predictor variables that were available at the time of the diagnosis of AKI: (1) demographic data; (2) comorbidities and conditions at admission; (3) laboratory exams within 24 h; and (4) characteristics and causes of AKI. We used a machine learning approach to fit models in the training set using tenfold cross-validation and validated the accuracy using the area under the receiver operating characteristic curve (AUC-ROC). The coefficients of the best model (Elastic Net) were used to build the predictive AKI-COV score. The AKI-COV score had an AUC-ROC of 0.823 (95% CI 0.761–0.885) in the validation cohort. The use of the AKI-COV score may assist healthcare workers in identifying hospitalized COVID-19 patients with AKI that may require more intensive monitoring and can be used for resource allocation. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-12-01 2022-04-29T08:38:19Z 2022-04-29T08:38:19Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1038/s41598-021-03894-5 Scientific Reports, v. 11, n. 1, 2021. 2045-2322 http://hdl.handle.net/11449/230191 10.1038/s41598-021-03894-5 2-s2.0-85122537958 |
url |
http://dx.doi.org/10.1038/s41598-021-03894-5 http://hdl.handle.net/11449/230191 |
identifier_str_mv |
Scientific Reports, v. 11, n. 1, 2021. 2045-2322 10.1038/s41598-021-03894-5 2-s2.0-85122537958 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Scientific Reports |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1799964795448852480 |