COVID-19 prediction models mostly consist of combined clinical features, laboratory parameters, and, less often, chest X-ray (CXR) findings. Our main goal was to propose a prediction model involving imaging methods, specifically ultrasound. This was a single-center, retrospective cohort observational study of patients admitted to the University Hospital Split from November 2020 to May 2021. Imaging protocols were based on the assessment of 14 lung zones for both lung ultrasound (LUS) and computed tomography (CT), correlated to a CXR score assessing 6 lung zones. Prediction models for the necessity of mechanical ventilation (MV) or a lethal outcome were developed by combining imaging, biometric, and biochemical parameters. A total of 255 patients with COVID-19 pneumonia were included in the study. Four independent predictors were added to the regression model for the necessity of MV: LUS score, day of the illness, leukocyte count, and cardiovascular disease (χ2 = 29.16, p < 0.001). The model accurately classified 89.9% of cases. For the lethal outcome, only two independent predictors contributed to the regression model: LUS score and patient’s age (χ2 = 48.56, p < 0.001, 93.2% correctly classified). The predictive model identified four key parameters at patient admission which could predict an adverse outcome.
Keywords: COVID-19; CT; chest X-ray; lung ultrasound; pneumonia; prognostic.