Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study

Abstract The COVID-19 pandemic has created an urgent need for robust, scalable monitoring tools supporting stratification of high-risk patients. This research aims to develop and validate prediction models, using the UK Biobank, to estimate COVID-19 mortality risk in confirmed cases. From the 11,245...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Mohammad A. Dabbah, Angus B. Reed, Adam T. C. Booth, Arrash Yassaee, Aleksa Despotovic, Benjamin Klasmer, Emily Binning, Mert Aral, David Plans, Davide Morelli, Alain B. Labrique, Diwakar Mohan
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/9352a4ce63234c028f61bb338256452d
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:9352a4ce63234c028f61bb338256452d
record_format dspace
spelling oai:doaj.org-article:9352a4ce63234c028f61bb338256452d2021-12-02T18:51:52ZMachine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study10.1038/s41598-021-95136-x2045-2322https://doaj.org/article/9352a4ce63234c028f61bb338256452d2021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-95136-xhttps://doaj.org/toc/2045-2322Abstract The COVID-19 pandemic has created an urgent need for robust, scalable monitoring tools supporting stratification of high-risk patients. This research aims to develop and validate prediction models, using the UK Biobank, to estimate COVID-19 mortality risk in confirmed cases. From the 11,245 participants testing positive for COVID-19, we develop a data-driven random forest classification model with excellent performance (AUC: 0.91), using baseline characteristics, pre-existing conditions, symptoms, and vital signs, such that the score could dynamically assess mortality risk with disease deterioration. We also identify several significant novel predictors of COVID-19 mortality with equivalent or greater predictive value than established high-risk comorbidities, such as detailed anthropometrics and prior acute kidney failure, urinary tract infection, and pneumonias. The model design and feature selection enables utility in outpatient settings. Possible applications include supporting individual-level risk profiling and monitoring disease progression across patients with COVID-19 at-scale, especially in hospital-at-home settings.Mohammad A. DabbahAngus B. ReedAdam T. C. BoothArrash YassaeeAleksa DespotovicBenjamin KlasmerEmily BinningMert AralDavid PlansDavide MorelliAlain B. LabriqueDiwakar MohanNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Mohammad A. Dabbah
Angus B. Reed
Adam T. C. Booth
Arrash Yassaee
Aleksa Despotovic
Benjamin Klasmer
Emily Binning
Mert Aral
David Plans
Davide Morelli
Alain B. Labrique
Diwakar Mohan
Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study
description Abstract The COVID-19 pandemic has created an urgent need for robust, scalable monitoring tools supporting stratification of high-risk patients. This research aims to develop and validate prediction models, using the UK Biobank, to estimate COVID-19 mortality risk in confirmed cases. From the 11,245 participants testing positive for COVID-19, we develop a data-driven random forest classification model with excellent performance (AUC: 0.91), using baseline characteristics, pre-existing conditions, symptoms, and vital signs, such that the score could dynamically assess mortality risk with disease deterioration. We also identify several significant novel predictors of COVID-19 mortality with equivalent or greater predictive value than established high-risk comorbidities, such as detailed anthropometrics and prior acute kidney failure, urinary tract infection, and pneumonias. The model design and feature selection enables utility in outpatient settings. Possible applications include supporting individual-level risk profiling and monitoring disease progression across patients with COVID-19 at-scale, especially in hospital-at-home settings.
format article
author Mohammad A. Dabbah
Angus B. Reed
Adam T. C. Booth
Arrash Yassaee
Aleksa Despotovic
Benjamin Klasmer
Emily Binning
Mert Aral
David Plans
Davide Morelli
Alain B. Labrique
Diwakar Mohan
author_facet Mohammad A. Dabbah
Angus B. Reed
Adam T. C. Booth
Arrash Yassaee
Aleksa Despotovic
Benjamin Klasmer
Emily Binning
Mert Aral
David Plans
Davide Morelli
Alain B. Labrique
Diwakar Mohan
author_sort Mohammad A. Dabbah
title Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study
title_short Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study
title_full Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study
title_fullStr Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study
title_full_unstemmed Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study
title_sort machine learning approach to dynamic risk modeling of mortality in covid-19: a uk biobank study
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/9352a4ce63234c028f61bb338256452d
work_keys_str_mv AT mohammadadabbah machinelearningapproachtodynamicriskmodelingofmortalityincovid19aukbiobankstudy
AT angusbreed machinelearningapproachtodynamicriskmodelingofmortalityincovid19aukbiobankstudy
AT adamtcbooth machinelearningapproachtodynamicriskmodelingofmortalityincovid19aukbiobankstudy
AT arrashyassaee machinelearningapproachtodynamicriskmodelingofmortalityincovid19aukbiobankstudy
AT aleksadespotovic machinelearningapproachtodynamicriskmodelingofmortalityincovid19aukbiobankstudy
AT benjaminklasmer machinelearningapproachtodynamicriskmodelingofmortalityincovid19aukbiobankstudy
AT emilybinning machinelearningapproachtodynamicriskmodelingofmortalityincovid19aukbiobankstudy
AT mertaral machinelearningapproachtodynamicriskmodelingofmortalityincovid19aukbiobankstudy
AT davidplans machinelearningapproachtodynamicriskmodelingofmortalityincovid19aukbiobankstudy
AT davidemorelli machinelearningapproachtodynamicriskmodelingofmortalityincovid19aukbiobankstudy
AT alainblabrique machinelearningapproachtodynamicriskmodelingofmortalityincovid19aukbiobankstudy
AT diwakarmohan machinelearningapproachtodynamicriskmodelingofmortalityincovid19aukbiobankstudy
_version_ 1718377397382807552