A Machine Learning Analysis Of Correlates Of Mortality Among Patients Hospitalized With Covid-19

This study examined the pre-existing patient characteristics that are associated with COVID-19 mortality in a sample of 145,944 patients hospitalized with COVID-19 across 21 healthcare systems in the US. Machine learning analyses revealed that age, hypertension, insurance status, and healthcare system (hospital site) were especially predictive of mortality across the full sample. However, multiple variables were especially predictive in subgroups of patients, with mortality rates ranging from about 2-30%. The findings of this study suggest that subgroups of patients are at heightened risk of COVID-19 mortality due to combinations of preadmission risk factors.