About 20% of patients admitted to hospital with COVID-19 require intensive care (ICU). Supporting specialists and patients who need to make decisions about an ICU requires accurate predictions based on individual characteristics. Clinical prediction models can be used to predict the need for IC or death. To date, no accurate clinical prediction model has been developed that meets all methodological requirements and has been externally validated.
The aim of this retrospective study is to develop and validate clinical prediction models that support clinical care when making treatment decisions.