A Tool for Early Prediction of Severe Coronavirus Disease 2019 (COVID-19): A Multicenter Study Using the Risk Nomogram in Wuhan and Guangdong, China

Abstract

Background: Because there is no reliable risk stratification tool for severe coronavirus disease 2019 (COVID-19) patients at admission, we aimed to construct an effective model for early identification of cases at high risk of progression to severe COVID-19.

Methods: In this retrospective multicenter study, 372 hospitalized patients with nonsevere COVID-19 were followed for > 15 days after admission. Patients who deteriorated to severe or critical COVID-19 and those who maintained a nonsevere state were assigned to the severe and nonsevere groups, respectively. Based on baseline data of the 2 groups, we constructed a risk prediction nomogram for severe COVID-19 and evaluated its performance.

Results: The training cohort consisted of 189 patients, and the 2 independent validation cohorts consisted of 165 and 18 patients. Among all cases, 72 (19.4%) patients developed severe COVID-19. Older age; higher serum lactate dehydrogenase, C-reactive protein, coefficient of variation of red blood cell distribution width, blood urea nitrogen, and direct bilirubin; and lower albumin were associated with severe COVID-19. We generated the nomogram for early identifying severe COVID-19 in the training cohort (area under the curve [AUC], 0.912 [95% confidence interval {CI}, .846-.978]; sensitivity 85.7%, specificity 87.6%) and the validation cohort (AUC, 0.853 [95% CI, .790-.916]; sensitivity 77.5%, specificity 78.4%). The calibration curve for probability of severe COVID-19 showed optimal agreement between prediction by nomogram and actual observation. Decision curve and clinical impact curve analyses indicated that nomogram conferred high clinical net benefit.

Conclusions: Our nomogram could help clinicians with early identification of patients who will progress to severe COVID-19, which will enable better centralized management and early treatment of severe disease.

Keywords: COVID-19; nomogram; risk stratification; severe COVID-19 prediction.