Comparison of methods for predicting COVID-19-related death in the general population using the OpenSAFELY platform.
null nullElizabeth J WilliamsonJohn TazareKrishnan BhaskaranHelen I McDonaldAlex J WalkerLaurie TomlinsonKevin WingSebastian BaconChris BatesHelen J CurtisHarriet J ForbesCaroline MinassianCaroline E MortonEmily NightingaleAmir MehrkarDavid EvansBrian D NicholsonDavid A LeonPeter InglesbyBrian MacKennaNicholas G DaviesNicholas J DeVitoHenry DrysdaleJonathan CockburnWilliam J HulmeJessica MorleyIan DouglasChristopher T RentschRohini MathurAngel WongAnna SchultzeRichard CrokerJohn ParryFrank HesterSam HarperRichard GrieveDavid A HarrisonEwout W SteyerbergRosalind M EggoKarla Diaz-OrdazRuth KeoghStephen J W EvansLiam SmeethAlex J WalkerPublished in: Diagnostic and prognostic research (2022)
Our proposed models allow absolute risk estimation in the context of changing infection prevalence but predictive performance is sensitive to the proxy for infection prevalence. Simple models can provide excellent discrimination and may simplify implementation of risk prediction tools.