Early outcome detection for COVID-19 patients

Abstract With the outbreak of COVID-19 exerting a strong pressure on hospitals and health facilities, clinical decision support systems based on predictive models can help to effectively improve the management of the pandemic. We present a method for predicting mortality for COVID-19 patients. Start...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Alina Sîrbu, Greta Barbieri, Francesco Faita, Paolo Ferragina, Luna Gargani, Lorenzo Ghiadoni, Corrado Priami
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/34716b8d4543467a9ae9c449c07676a4
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:34716b8d4543467a9ae9c449c07676a4
record_format dspace
spelling oai:doaj.org-article:34716b8d4543467a9ae9c449c07676a42021-12-02T18:50:48ZEarly outcome detection for COVID-19 patients10.1038/s41598-021-97990-12045-2322https://doaj.org/article/34716b8d4543467a9ae9c449c07676a42021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97990-1https://doaj.org/toc/2045-2322Abstract With the outbreak of COVID-19 exerting a strong pressure on hospitals and health facilities, clinical decision support systems based on predictive models can help to effectively improve the management of the pandemic. We present a method for predicting mortality for COVID-19 patients. Starting from a large number of clinical variables, we select six of them with largest predictive power, using a feature selection method based on genetic algorithms and starting from a set of COVID-19 patients from the first wave. The algorithm is designed to reduce the impact of missing values in the set of variables measured, and consider only variables that show good accuracy on validation data. The final predictive model provides accuracy larger than 85% on test data, including a new patient cohort from the second COVID-19 wave, and on patients with imputed missing values. The selected clinical variables are confirmed to be relevant by recent literature on COVID-19.Alina SîrbuGreta BarbieriFrancesco FaitaPaolo FerraginaLuna GarganiLorenzo GhiadoniCorrado PriamiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Alina Sîrbu
Greta Barbieri
Francesco Faita
Paolo Ferragina
Luna Gargani
Lorenzo Ghiadoni
Corrado Priami
Early outcome detection for COVID-19 patients
description Abstract With the outbreak of COVID-19 exerting a strong pressure on hospitals and health facilities, clinical decision support systems based on predictive models can help to effectively improve the management of the pandemic. We present a method for predicting mortality for COVID-19 patients. Starting from a large number of clinical variables, we select six of them with largest predictive power, using a feature selection method based on genetic algorithms and starting from a set of COVID-19 patients from the first wave. The algorithm is designed to reduce the impact of missing values in the set of variables measured, and consider only variables that show good accuracy on validation data. The final predictive model provides accuracy larger than 85% on test data, including a new patient cohort from the second COVID-19 wave, and on patients with imputed missing values. The selected clinical variables are confirmed to be relevant by recent literature on COVID-19.
format article
author Alina Sîrbu
Greta Barbieri
Francesco Faita
Paolo Ferragina
Luna Gargani
Lorenzo Ghiadoni
Corrado Priami
author_facet Alina Sîrbu
Greta Barbieri
Francesco Faita
Paolo Ferragina
Luna Gargani
Lorenzo Ghiadoni
Corrado Priami
author_sort Alina Sîrbu
title Early outcome detection for COVID-19 patients
title_short Early outcome detection for COVID-19 patients
title_full Early outcome detection for COVID-19 patients
title_fullStr Early outcome detection for COVID-19 patients
title_full_unstemmed Early outcome detection for COVID-19 patients
title_sort early outcome detection for covid-19 patients
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/34716b8d4543467a9ae9c449c07676a4
work_keys_str_mv AT alinasirbu earlyoutcomedetectionforcovid19patients
AT gretabarbieri earlyoutcomedetectionforcovid19patients
AT francescofaita earlyoutcomedetectionforcovid19patients
AT paoloferragina earlyoutcomedetectionforcovid19patients
AT lunagargani earlyoutcomedetectionforcovid19patients
AT lorenzoghiadoni earlyoutcomedetectionforcovid19patients
AT corradopriami earlyoutcomedetectionforcovid19patients
_version_ 1718377495680516096