U-survival for prognostic prediction of disease progression and mortality of patients with COVID-19

Abstract The rapid increase of patients with coronavirus disease 2019 (COVID-19) has introduced major challenges to healthcare services worldwide. Therefore, fast and accurate clinical assessment of COVID-19 progression and mortality is vital for the management of COVID-19 patients. We developed an...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Janne J. Näppi, Tomoki Uemura, Chinatsu Watari, Toru Hironaka, Tohru Kamiya, Hiroyuki Yoshida
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/3d012675bb3543f6a9af28dbc3904e5e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3d012675bb3543f6a9af28dbc3904e5e
record_format	dspace
spelling	oai:doaj.org-article:3d012675bb3543f6a9af28dbc3904e5e2021-12-02T16:56:10ZU-survival for prognostic prediction of disease progression and mortality of patients with COVID-1910.1038/s41598-021-88591-z2045-2322https://doaj.org/article/3d012675bb3543f6a9af28dbc3904e5e2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88591-zhttps://doaj.org/toc/2045-2322Abstract The rapid increase of patients with coronavirus disease 2019 (COVID-19) has introduced major challenges to healthcare services worldwide. Therefore, fast and accurate clinical assessment of COVID-19 progression and mortality is vital for the management of COVID-19 patients. We developed an automated image-based survival prediction model, called U-survival, which combines deep learning of chest CT images with the established survival analysis methodology of an elastic-net Cox survival model. In an evaluation of 383 COVID-19 positive patients from two hospitals, the prognostic bootstrap prediction performance of U-survival was significantly higher (P < 0.0001) than those of existing laboratory and image-based reference predictors both for COVID-19 progression (maximum concordance index: 91.6% [95% confidence interval 91.5, 91.7]) and for mortality (88.7% [88.6, 88.9]), and the separation between the Kaplan–Meier survival curves of patients stratified into low- and high-risk groups was largest for U-survival (P < 3 × 10–14). The results indicate that U-survival can be used to provide automated and objective prognostic predictions for the management of COVID-19 patients.Janne J. NäppiTomoki UemuraChinatsu WatariToru HironakaTohru KamiyaHiroyuki YoshidaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Janne J. Näppi Tomoki Uemura Chinatsu Watari Toru Hironaka Tohru Kamiya Hiroyuki Yoshida U-survival for prognostic prediction of disease progression and mortality of patients with COVID-19
description	Abstract The rapid increase of patients with coronavirus disease 2019 (COVID-19) has introduced major challenges to healthcare services worldwide. Therefore, fast and accurate clinical assessment of COVID-19 progression and mortality is vital for the management of COVID-19 patients. We developed an automated image-based survival prediction model, called U-survival, which combines deep learning of chest CT images with the established survival analysis methodology of an elastic-net Cox survival model. In an evaluation of 383 COVID-19 positive patients from two hospitals, the prognostic bootstrap prediction performance of U-survival was significantly higher (P < 0.0001) than those of existing laboratory and image-based reference predictors both for COVID-19 progression (maximum concordance index: 91.6% [95% confidence interval 91.5, 91.7]) and for mortality (88.7% [88.6, 88.9]), and the separation between the Kaplan–Meier survival curves of patients stratified into low- and high-risk groups was largest for U-survival (P < 3 × 10–14). The results indicate that U-survival can be used to provide automated and objective prognostic predictions for the management of COVID-19 patients.
format	article
author	Janne J. Näppi Tomoki Uemura Chinatsu Watari Toru Hironaka Tohru Kamiya Hiroyuki Yoshida
author_facet	Janne J. Näppi Tomoki Uemura Chinatsu Watari Toru Hironaka Tohru Kamiya Hiroyuki Yoshida
author_sort	Janne J. Näppi
title	U-survival for prognostic prediction of disease progression and mortality of patients with COVID-19
title_short	U-survival for prognostic prediction of disease progression and mortality of patients with COVID-19
title_full	U-survival for prognostic prediction of disease progression and mortality of patients with COVID-19
title_fullStr	U-survival for prognostic prediction of disease progression and mortality of patients with COVID-19
title_full_unstemmed	U-survival for prognostic prediction of disease progression and mortality of patients with COVID-19
title_sort	u-survival for prognostic prediction of disease progression and mortality of patients with covid-19
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/3d012675bb3543f6a9af28dbc3904e5e
work_keys_str_mv	AT jannejnappi usurvivalforprognosticpredictionofdiseaseprogressionandmortalityofpatientswithcovid19 AT tomokiuemura usurvivalforprognosticpredictionofdiseaseprogressionandmortalityofpatientswithcovid19 AT chinatsuwatari usurvivalforprognosticpredictionofdiseaseprogressionandmortalityofpatientswithcovid19 AT toruhironaka usurvivalforprognosticpredictionofdiseaseprogressionandmortalityofpatientswithcovid19 AT tohrukamiya usurvivalforprognosticpredictionofdiseaseprogressionandmortalityofpatientswithcovid19 AT hiroyukiyoshida usurvivalforprognosticpredictionofdiseaseprogressionandmortalityofpatientswithcovid19
_version_	1718382794730635264

U-survival for prognostic prediction of disease progression and mortality of patients with COVID-19

Ejemplares similares