Fig. 3

The nomogram and calibration curves based on significant features in multivariate analysis. A A nomogram was built on the basis of eight significant features in multivariate Logistic model. If a patient is suspected to be COVID-19 by radiological diagnosis, the data needed includes whether he has fever, contact history, decreased WBC count, left lower lobe involvement, pleural thickening, multifocal lesions, peripheral distribution or absence of mediastinal lymphadenopathy. The point of each feature adds up to a total score with a corresponding probability of COVID-19. B The calibration curve was determined with bootstrap analysis to get bias-corrected estimation. It indicated great agreement between the prediction and the actual grouping in the probability