The prognosis of a patient with COVID-19 pneumonia is uncertain. Our objective was to establish a predictive model of disease progression to facilitate early decision-making. A retrospective study was performed of patients admitted with COVID-19 pneumonia, classified as severe (admission to the intensive care unit, mechanic invasive ventilation, or death) or non-severe. A predictive model based on clinical, laboratory, and radiological parameters was built. The probability of progression to severe disease was estimated by logistic regression analysis. Calibration and discrimination (receiver operating characteristics curves and AUC) were assessed to determine model performance. During the study period 1152 patients presented with SARS-CoV-2 infection, of whom 229 (19.9%) were admitted for pneumonia. During hospitalization, 51 (22.3%) progressed to severe disease, of whom 26 required ICU care (11.4); 17 (7.4%) underwent invasive mechanical ventilation, and 32 (14%) died of any cause. Five predictors determined within 24 h of admission were identified: Diabetes, Age, Lymphocyte count, SaO2, and pH (DALSH score). The prediction model showed a good clinical performance, including discrimination (AUC 0.87 CI 0.81, 0.92) and calibration (Brier score = 0.11). In total, 0%, 12%, and 50% of patients with severity risk scores ≤ 5%, 6–25%, and > 25% exhibited disease progression, respectively. A risk score based on five factors predicts disease progression and facilitates early decision-making according to prognosis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.