Objective to identify subgroups of patients hospitalized and treated with COVID-19 pneumonia using latent class clustering methods to assess the clinical and prognostic relevance of the resulting subgroups, with special interest in differential responses to calcifediol. Setting: Reina Sofia University Hospital, Córdoba Spain. Patients: Retrospective observational cohort study of patients admitted for COVID-19. Inclusion criteria: (i) age ≥ 18 and ≤ 90 years, (ii) pneumonia (presence of infiltrates on chest X-ray or CT scan), (iii) SARS-CoV-2 infection, confirmed, and (iv) CURB 65 scale >1. 707 patients hospitalized from 10 March 2020 to 4 March 2022 were included. Design An analysis of the patient profiles was carried out. For this purpose, a latent class analysis (LCA) was performed. Once the groups had been estimated by the model, the differences between them were assessed for each of the predictor variables by means of the chi-square test, Fisher's exact test (qualitative variables) and the Kruskal-Wallis test. Results: Optimal number of classes was 4. For the treatment variable, differences were found between class 3 (60% treated with calcifediol only) and classes 1 (less than 1% calcifediol only vs. 82% treated with both), 2 (less than 1% calcifediol only vs. 78% treated with both) and 4 (1% calcifediol only vs. 84% treated with both). Class 3, (60% calcifediol), had a significantly better prognosis compared to patients treated with glucocorticoids alone (OR: 15.2, 95% CI: [3.73 - 142], p<0.001) or no treatment (OR: 7.38, 95% CI: [2.63 - 30.2], p<0.001). Conclusions: our real-life study show that Calcifediol significantly reduces the need for ICU admission in patients hospitalized for COVID-19 pneumonia, especially in the group treated without glucocorticoids. When calcifediol and corticosteroids are administered, the greatest significance in reducing ICU admission occurs when the patient sequentially receives calcifediol first and then glucocorticoids are introduced at treatment (OR: 7.49; 95% CI: 2.63-27.7; p<0.001).