Publication:
A predictive model for hospitalization and survival to COVID‑19 in a retrospective population‑based study

Simple item page
dc.contributor.authorCisterna García, Alejandro
dc.contributor.authorGuillén Teruel, Antonio
dc.contributor.authorCaracena, Marcos
dc.contributor.authorPérez-Cuadrado Martínez, Enrique
dc.contributor.authorJiménez Barrionuevo, Fernando
dc.contributor.authorFrancisco Verdú, Francisco J.
dc.contributor.authorReina, Gabriel
dc.contributor.authorGonzález Billalabeitia, Enrique
dc.contributor.authorPalma Méndez, José Tomás
dc.contributor.authorSánchez Ferrer, Álvaro
dc.contributor.authorBotía Blaya, Juan Antonio
dc.contributor.departmentIngeniería de la Información y las Comunicaciones
dc.contributor.otherFacultades de la UMU::Facultad de Informática
dc.date.accessioned2025-12-18T07:03:45Z
dc.date.available2025-12-18T07:03:45Z
dc.date.copyright© The Author(s) 2022
dc.date.issued2022-10-28
dc.description.abstractThe development of tools that provide early triage of COVID-19 patients with minimal use of diagnostic tests, based on easily accessible data, can be of vital importance in reducing COVID-19 mortality rates during high-incidence scenarios. This work proposes a machine learning model to predict mortality and risk of hospitalization using both 2 simple demographic features and 19 comorbidities obtained from 86,867 electronic medical records of COVID-19 patients, and a new method (LR-IPIP) designed to deal with data imbalance problems. The model was able to predict with high accuracy (90–93%, ROC-AUC = 0.94) the patient's final status (deceased or discharged), while its accuracy was medium (71–73%, ROC-AUC = 0.75) with respect to the risk of hospitalization. The most relevant characteristics for these models were age, sex, number of comorbidities, osteoarthritis, obesity, depression, and renal failure. Finally, to facilitate its use by clinicians, a user-friendly website has been developed (https://alejandrocisterna.shinyapps.io/PROVIA).
dc.formatapplication/pdf
dc.format.extent11
dc.identifier.citationScientific Reports, 2022, Vol. 12 : 18126
dc.identifier.doihttps://doi.org/10.1038/s41598-022-22547-9
dc.identifier.eissn2045-2322
dc.identifier.urihttp://hdl.handle.net/10201/181309
dc.languageeng
dc.publisherNature Research
dc.relationThis research was supported by the Science and Technology Agency, Séneca Foundation, Comunidad Autónoma Región de Murcia, Spain. AC was supported by the same foundation through the grant 20762/FPI/18. JB was supported by the same foundation through the research project 00007/COVI/20.
dc.relation.publisherversionhttps://www.nature.com/articles/s41598-022-22547-9
dc.rightsAttribution 4.0 International*
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectComputational science
dc.subjectPrognosis
dc.subjectStatistics
dc.subject.odsNo relacionado con ningún objetivo de desarrollo sostenible
dc.titleA predictive model for hospitalization and survival to COVID‑19 in a retrospective population‑based study
dc.typeinfo:eu-repo/semantics/article
dc.type.versioninfo:eu-repo/semantics/publishedVersion
dspace.entity.typePublicationes
relation.isAuthorOfPublication4f024a01-2f90-4358-856e-3f2f66264ab6
relation.isAuthorOfPublication47706328-5460-433a-b86f-dcbcc9841c53
relation.isAuthorOfPublication490d158d-e40d-4fdf-99f0-912bd4aa5a4e
relation.isAuthorOfPublicationaa6ca3f7-ee95-4c3b-b93d-82bbb7c57dd3
relation.isAuthorOfPublicationee187cf4-aebe-4d10-bfe0-09dedbc8daaf
relation.isAuthorOfPublication.latestForDiscovery4f024a01-2f90-4358-856e-3f2f66264ab6
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
s41598-022-22547-9.pdf
Size:
1.9 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.37 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos