Skip to main content
Fig. 7 | BMC Medical Imaging

Fig. 7

From: Nomogram to identify severe coronavirus disease 2019 (COVID-19) based on initial clinical and CT characteristics: a multi-center study

Fig. 7

a Decision curve analysis for the nomogram. The decision curve indicated that when the threshold probability of a patient was within a range from 0.01 to 0.93, use of the nomogram for predicting severe COVID-19 would provide greater benefit than the “treat-all” or “treat-none” schemes. The curve of the nomogram over the severity score of lung showed the greatest benefit. b Clinical impact curve of the nomogram plotted the number of COVID-19 patients classified as high risk, and the number of cases classified high risk with severe COVID-19 at each high risk threshold. A risk chart plotted performance against caseload in the training cohort c and validation cohort d, respectively. Area under the recall (green) curves was 94 and 95% in the training and validation cohort, respectively

Back to article page