Development and performance of a population-based risk stratification model for COVID-19

The shortage of recently approved vaccines against the severe acute respiratory syndrome coronavirus (SARS-CoV-2) has highlighted the need for evidence-based tools to prioritize healthcare resources for people at higher risk of severe coronavirus disease 2019 (COVID-19). Current evidence indicates that age is far from accurate in identifying the risk of severe illness; furthermore, the count of individual risk factors has limited applicability to population-based “stratify-and-shield” strategies. We developed a COVID-19 risk stratification system that allows allocating people into four mutually-exclusive risk categories based on multivariate models for hospital admissions, transfer to intensive care unit (ICU), and mortality among the general population. The model was developed using clinical, hospital, and epidemiological data from the entire population of Catalonia (North-East Spain; 7.5 million people) and validated using an independent dataset of 218,329 individuals with PCR-confirmed COVID-19, who were infected after developing the model. This showed high discrimination capacity, with an area under the curve of the receiving operating characteristics of 0.85 (95% CI 0.85 – 0.85) for hospital admissions, 0.86 (0.86 – 0.97) for ICU transfers, and 0.96 (0.96 – 0.96) for deaths. Our results provide clinicians and policymakers with an evidence-based tool for prioritizing COVID-19 healthcare resources other population groups aside from those with higher exposure to SARS-CoV-2 and frontline workers.