Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study
Authors:
- Mohammad A. DabbahMDMohammad A. Dabbah
- Angus B. ReedARAngus B. Reed
- Adam T.C. BoothABAdam T.C. Booth
- Arrash YassaeeAYArrash Yassaee
- Alex DespotovicADAlex Despotovic
- Benjamin KlasmerBKBenjamin Klasmer
- Emily BinningEBEmily Binning
- Mert AralMAMert Aral
- David PlansDPDavid Plans
- Alain B. LabriqueALAlain B. Labrique
- Diwakar MohanDMDiwakar Mohan
Preprint
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.Keywords
All Related Versions
- Published version: Scientific Reports, 11 (1), 1.
This publication has 46 references indexed in Scilit:
- Comparison of Sociodemographic and Health-Related Characteristics of UK Biobank Participants With Those of the General PopulationAmerican Journal of Epidemiology, 2017
- UK Biobank: An Open Access Resource for Identifying the Causes of a Wide Range of Complex Diseases of Middle and Old AgePLOS Medicine, 2015
- Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD StatementBMC Medicine, 2015
- Sleep duration predicts cardiovascular outcomes: a systematic review and meta-analysis of prospective studiesEuropean Heart Journal, 2011
- Leave-One-Out Cross-Validation2011
- Sleep Duration and All-Cause Mortality: A Systematic Review and Meta-Analysis of Prospective StudiesSLEEP, 2010
- Sleep Duration as a Risk Factor for Diabetes Incidence in a Large US SampleSLEEP, 2007
- Random ForestsMachine Learning, 2001
- Bagging predictorsMachine Learning, 1996
- The Jackknife, the Bootstrap and Other Resampling Plans1982