Introduction: Computerized tomography (CT) is a crucial technique for determining the severity of COVID-19. Ground glass opacities (GGO), crazy-paving patterns, and parenchymal consolidations are the most frequent patterns. Fibrosis, subpleural lines, the reversed "halo sign," pleural effusion, and lymphadenopathy are additional related CT features. The course and severity of the disease are related to CT results in COVID-19 patients. For patients with COVID-19, evaluation of laboratory and chest CT imaging features for prognostic prediction would be benecial for a better knowledge of disease pathogenesis, risk stratication, and the development of early treatment plans that ultimately minimise mortality Materials and Methods: Present study was performed on 100 laboratory conrmed cases of COVID–19 diagnosed on reverse transcriptase-quantitative polymerase chain reaction (RT-qPCR). Cases were divided into two groups based on clinical disease severity scoring based on the criteria provided by Chinese Centre of Disease Control (CDC)5 as Group A (Disease presenting with dyspnoea, respiratory rate ≥ 30/min and SpO2 ≤ 93%) and Group B (Disease presenting with mild symptoms without dyspnoea, respiratory rate < 30/ min and SpO2 > 93 %). Patients Information on demography, clinical data with symptoms, comorbidity and disease severity were collected. CT Chest was sent in every patient at the time of admission. Observations and Results: Right and left lower lobe was affected in majority i.e 47 (47 %) and 52 (52 %) respectively. In group A moderate 25 (25 %) and severe CT 17 (17 %) score was found in majority whereas in group B mild 33 (33 %) CT score was in majority. Result was statistically signicant (P<0.00001). Ground glass opacity was the main CT pattern found in majority 47 (47 %). In group B compared to group A maximum patients got discharged within 10 days. Also ICU admissions were less 1 (1 %). Result was statistically signicant (P=0.008) Conclusion: Temporal changes of chest CT features and severity scores were closely associated with the outcome of COVID-19, which may be valuable for early identication of severe cases and eventually reducing the morbidity of COVID-19