Marcolino MS, Pires MC, Ramos LEF, et al. - Researchers sought to generate and validate a score at hospital admission for predicting in-hospital mortality in COVID-19 patients. In addition, they compared this score with other existing ones. They carried out logistic regression analysis to generate the prediction model for in-hospital mortality, based on the 3,978 patients admitted between March-July, 2020. Validation of the model was done in the 1,054 patients admitted during August-September, as well as in an external cohort of 474 Spanish patients. The risk score included seven significant variables: age, blood urea nitrogen, number of comorbidities, C-reactive protein, SpO₂/FiO₂ ratio, platelet count and heart rate. This easy-to-use rapid scoring system showed a high discriminatory value, which was verified in the Brazilian and Spanish validation cohorts. It displayed better discrimination ability compared with other existing scores. Its implementation has been done in a freely available online risk calculator (https://abc2sph.com/).