Objective: To establish the diagnostic validity of the CALL score as a predictor of mortality in patients with severe COVID-19 in the Intensive Care Unit of the Trujillo Regional Teaching Hospital from April 2020 to July 2021.Material and methods: An analytical, retrospective study was carried out, in which 177 patients with severe COVID-19 admitted to the Intensive Care Unit of the Regional Teaching Hospital of Trujillo were included, according to selection criteria, the CALL score was calculated for each one and was associated with the mortality found; applying the statistical chi 2 test; Subsequently, a multivariate regression analysis was performed to identify risk factors associated with mortality. In turn, the AUROC (area under the ROC curve) was used to establish the predictive performance of the CALL score. Results: From a sample of 177 patients, when analyzing the information using the ROC curve, a cut-off value of 6 points was obtained for the CALL score, with an area under the curve (AUC) of 0.612 (p=0.014); sensitivity, specificity, positive and negative predictive value of 86%, 29%, 60% and 62% respectively. No statistically significant differences were found in terms of sex, age, septic shock, SOFA, Charlson comorbidity index, need for renal replacement therapy (RRT) or static compliance. On the other hand, an association with PaO2/FiO2 was evidenced.