Development and validation of a simple machine learning tool to predict mortality in leptospirosis
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1038/s41598-023-31707-4 http://hdl.handle.net/11449/247031 |
Resumo: | Predicting risk factors for death in leptospirosis is challenging, and identifying high-risk patients is crucial as it might expedite the start of life-saving supportive care. Admission data of 295 leptospirosis patients were enrolled, and a machine-learning approach was used to fit models in a derivation cohort. The comparison of accuracy metrics was performed with two previous models—SPIRO score and quick SOFA score. A Lasso regression analysis was the selected model, demonstrating the best accuracy to predict mortality in leptospirosis [area under the curve (AUC-ROC) = 0.776]. A score-based prediction was carried out with the coefficients of this model and named LeptoScore. Then, to simplify the predictive tool, a new score was built by attributing points to the predictors with importance values higher than 1. The simplified score, named QuickLepto, has five variables (age > 40 years; lethargy; pulmonary symptom; mean arterial pressure < 80 mmHg and hematocrit < 30%) and good predictive accuracy (AUC-ROC = 0.788). LeptoScore and QuickLepto had better accuracy to predict mortality in patients with leptospirosis when compared to SPIRO score (AUC-ROC = 0.500) and quick SOFA score (AUC-ROC = 0.782). The main result is a new scoring system, the QuickLepto, that is a simple and useful tool to predict death in leptospirosis patients at hospital admission. |
id |
UNSP_ecefc87b8c39f8b41d13eb1c74ed8ada |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/247031 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Development and validation of a simple machine learning tool to predict mortality in leptospirosisPredicting risk factors for death in leptospirosis is challenging, and identifying high-risk patients is crucial as it might expedite the start of life-saving supportive care. Admission data of 295 leptospirosis patients were enrolled, and a machine-learning approach was used to fit models in a derivation cohort. The comparison of accuracy metrics was performed with two previous models—SPIRO score and quick SOFA score. A Lasso regression analysis was the selected model, demonstrating the best accuracy to predict mortality in leptospirosis [area under the curve (AUC-ROC) = 0.776]. A score-based prediction was carried out with the coefficients of this model and named LeptoScore. Then, to simplify the predictive tool, a new score was built by attributing points to the predictors with importance values higher than 1. The simplified score, named QuickLepto, has five variables (age > 40 years; lethargy; pulmonary symptom; mean arterial pressure < 80 mmHg and hematocrit < 30%) and good predictive accuracy (AUC-ROC = 0.788). LeptoScore and QuickLepto had better accuracy to predict mortality in patients with leptospirosis when compared to SPIRO score (AUC-ROC = 0.500) and quick SOFA score (AUC-ROC = 0.782). The main result is a new scoring system, the QuickLepto, that is a simple and useful tool to predict death in leptospirosis patients at hospital admission.Medical Sciences Postgraduate Program Federal University of Ceará, Rua Silva Jatahy 1000 ap 600, CearáHospital Universitário Walter Cantídio Federal University of Ceará, CearáHospital Geral de Fortaleza, CearaBotucatu Medical School Universidade Estadual Paulista, São PauloSchool of Medicine Medical Sciences and Public Health Postgraduate Programs University of Fortaleza, CearáBotucatu Medical School Universidade Estadual Paulista, São PauloFederal University of CearáHospital Geral de FortalezaUniversidade Estadual Paulista (UNESP)University of FortalezaGaldino, Gabriela Studartde Sandes-Freitas, Tainá Verasde Andrade, Luis Gustavo Modelli [UNESP]Adamian, Caio Manuel CaetanoMeneses, Gdayllon Cavalcanteda Silva Junior, Geraldo Bezerrade Francesco Daher, Elizabeth2023-07-29T12:57:09Z2023-07-29T12:57:09Z2023-12-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1038/s41598-023-31707-4Scientific Reports, v. 13, n. 1, 2023.2045-2322http://hdl.handle.net/11449/24703110.1038/s41598-023-31707-42-s2.0-85150665881Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengScientific Reportsinfo:eu-repo/semantics/openAccess2023-07-29T12:57:09Zoai:repositorio.unesp.br:11449/247031Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T17:08:55.584069Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Development and validation of a simple machine learning tool to predict mortality in leptospirosis |
title |
Development and validation of a simple machine learning tool to predict mortality in leptospirosis |
spellingShingle |
Development and validation of a simple machine learning tool to predict mortality in leptospirosis Galdino, Gabriela Studart |
title_short |
Development and validation of a simple machine learning tool to predict mortality in leptospirosis |
title_full |
Development and validation of a simple machine learning tool to predict mortality in leptospirosis |
title_fullStr |
Development and validation of a simple machine learning tool to predict mortality in leptospirosis |
title_full_unstemmed |
Development and validation of a simple machine learning tool to predict mortality in leptospirosis |
title_sort |
Development and validation of a simple machine learning tool to predict mortality in leptospirosis |
author |
Galdino, Gabriela Studart |
author_facet |
Galdino, Gabriela Studart de Sandes-Freitas, Tainá Veras de Andrade, Luis Gustavo Modelli [UNESP] Adamian, Caio Manuel Caetano Meneses, Gdayllon Cavalcante da Silva Junior, Geraldo Bezerra de Francesco Daher, Elizabeth |
author_role |
author |
author2 |
de Sandes-Freitas, Tainá Veras de Andrade, Luis Gustavo Modelli [UNESP] Adamian, Caio Manuel Caetano Meneses, Gdayllon Cavalcante da Silva Junior, Geraldo Bezerra de Francesco Daher, Elizabeth |
author2_role |
author author author author author author |
dc.contributor.none.fl_str_mv |
Federal University of Ceará Hospital Geral de Fortaleza Universidade Estadual Paulista (UNESP) University of Fortaleza |
dc.contributor.author.fl_str_mv |
Galdino, Gabriela Studart de Sandes-Freitas, Tainá Veras de Andrade, Luis Gustavo Modelli [UNESP] Adamian, Caio Manuel Caetano Meneses, Gdayllon Cavalcante da Silva Junior, Geraldo Bezerra de Francesco Daher, Elizabeth |
description |
Predicting risk factors for death in leptospirosis is challenging, and identifying high-risk patients is crucial as it might expedite the start of life-saving supportive care. Admission data of 295 leptospirosis patients were enrolled, and a machine-learning approach was used to fit models in a derivation cohort. The comparison of accuracy metrics was performed with two previous models—SPIRO score and quick SOFA score. A Lasso regression analysis was the selected model, demonstrating the best accuracy to predict mortality in leptospirosis [area under the curve (AUC-ROC) = 0.776]. A score-based prediction was carried out with the coefficients of this model and named LeptoScore. Then, to simplify the predictive tool, a new score was built by attributing points to the predictors with importance values higher than 1. The simplified score, named QuickLepto, has five variables (age > 40 years; lethargy; pulmonary symptom; mean arterial pressure < 80 mmHg and hematocrit < 30%) and good predictive accuracy (AUC-ROC = 0.788). LeptoScore and QuickLepto had better accuracy to predict mortality in patients with leptospirosis when compared to SPIRO score (AUC-ROC = 0.500) and quick SOFA score (AUC-ROC = 0.782). The main result is a new scoring system, the QuickLepto, that is a simple and useful tool to predict death in leptospirosis patients at hospital admission. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-29T12:57:09Z 2023-07-29T12:57:09Z 2023-12-01 |
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/s41598-023-31707-4 Scientific Reports, v. 13, n. 1, 2023. 2045-2322 http://hdl.handle.net/11449/247031 10.1038/s41598-023-31707-4 2-s2.0-85150665881 |
url |
http://dx.doi.org/10.1038/s41598-023-31707-4 http://hdl.handle.net/11449/247031 |
identifier_str_mv |
Scientific Reports, v. 13, n. 1, 2023. 2045-2322 10.1038/s41598-023-31707-4 2-s2.0-85150665881 |
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_ |
1808128762752008192 |