Fig. 7

Decision curve analysis (DCA) in the training and testing datasets. The y-axis represents the net benefit (the net benefit was calculated by subtracting the proportion of all false-positive patients from the true-positive patient, and the weight is the relative hazard of abandoning treatment versus negative patients). The red solid line indicates the model. The black solid line indicates the hypothesis that all patients were treated by one scheme (for example, assuming that all patients were in the RT-PCR-negative group). The black dotted line represents the hypothesis that all patients were treated by another scheme (for example, assuming that all patients were in the RT-PCR positive group). The model shows the added net benefit if the probability thresholds in the training and testing datasets are more than 0.20 and between 0.15 and 0.82, respectively