Table 5.

The predictive performance of the model.

Characteristic	Training set (95%CI)	Testing set (95%CI)
AUC	0.75 (0.71–0.79)	0.79 (0.73–0.85)
Accuracy	0.76 (0.72–0.79)	0.77 (0.72–0.82)
Sensitivity	0.56 (0.46–0.63)	0.51 (0.41–0.62)
Specificity	0.83 (0.79–0.86)	0.87 (0.83–0.92)
NPV	0.84 (0.81–0.87)	0.83 (0.78–0.87)
PPV	0.53 (0.46–0.60)	0.60 (0.49–0.71)

AUC: the area under the curve, NPV: negative predictive value, PPV: positive predictive value.