Knowing which individuals are at greatest risk of severe illness and death could enable us to refine vaccine rollouts to reach the most vulnerable groups sooner, personalise care for patients with COVID-19 and improve the design of observational studies. Our open-source interpretable prognostic model was developed using the Optum COVID-19 Electronic Health Record dataset and was trained and tested using de-identified records from 17,086 patients who had been hospitalised with COVID-19 across the USA. While we found that age was the most important predictor of all-cause mortality, we also found that vital signs and laboratory results added considerable prognostic information. Join me to find out more about our modelling work and its implications.