Background: The pandemic of severe acute respiratory syndrome by coronavirus 2 (SARS-CoV-2) is a multi-system disease caused by a diffuse systemic process involving a complex interaction of the inflammatory, immunological and coagulative cascades. This study aims to identify the most effective biomarkers to predict a poor outcome in the intensive care unit patients with severe COVID-19 disease. Methods: A single-centre retrospective observational study enrolled 69 deceased and 20 recovered patients treated in the Intensive Care Unit of the General Hospital Gradiska in the period from March 1, 2021. until April 1, 2022. We evaluated the leukocytes, lymphocytes, neutrophils, platelets, hemoglobin, neutrophil lymphocyte ratio (NPR), platelet lymphocyte ratio (PLR), systemic immune-inflammation index (SII). In addition, we  evaluated the IL-6, ferritin, CRP, D-dimer, magnesium, bilirubin and lactate dehydrogenase.  Results: Between deceased and recovered patients on admission to the ICU, there was a significant difference between the following parameters: leukocytes x109/L 11.5 (8.86-14.75) vs 9.4 (5.9-11.9), p =0.026; neutrophils x109/L 10.15 (7.81-12.74) vs 8.60 (4.8-10.3) p=0.022; NLR 15.01 (10.60-24.33) vs 9.45 (5.10-14.90) p=0.02; SII 3712 (2240-6543) vs 1949 (993-3720) p=0.003. The magnesium level increased significantly over time in the group of patients who died, while the hemoglobin level and platelet count decreased. ROC analysis showed the following AUC values: leukocytes 0.774; neutrophils 0.781; NLR 0.786; SII 0.776; D-dimer 0.741and bilrubine 0.713. Conclusions: In this retrospective study leukocytes, neutrophils, NLR, SII, D-dimer, bilirubin determined at hospital admission had a high value in predicting death among patients with severe COVID-19.