COVID-19 in Portugal: predictability of hospitalization, ICU and respiratory-assistance needs

The current SARS-COV-2 epidemic is associated with nearly 1 million estimated deaths and responsible for multiple disturbances around the world, including the overload of health care systems. The timely prediction of the medical needs of infected individuals enables a better and quicker care provision for the necessary cases, supporting the management of available resources.

This work ascertains the predictability of medical needs (as hospitalization, respiratory support, and admission to intensive care units) and the survivability of individuals testing SARS-CoV-2 positive considering a cohort with all infected individuals in Portugal as per June 30, 2020. Predictions are performed at the various stages of a patient’s cycle, namely: pre-hospitalization (testing time), pos-hospitalization, and pos-intensive care. A thorough optimization of state-of-the-art predictors is undertaken to assess the ability to anticipate medical needs and infection outcomes using demographic and comorbidity variables, as well as onset date of symptoms, test and hospitalization.