Table 7.

The predictive value of the BLS model for high ovarian response.

Variables	Training set	Testing set
AUC (95% CI)	0.692 (0.636-0.748)	0.706 (0.622-0.791)
Accuracy (95% CI)	0.613 (0.561-0.666)	0.625 (0.546-0.704)
Sensitivity (95% CI)	0.964 (0.936-0.992)	0.958 (0.912-1.000)
Specificity (95% CI)	0.266 (0.200-0.333)	0.292 (0.187-0.397)
PPV (95% CI)	0.565 (0.507-0.324)	0.575 (0.487-0.380)
NPV (95% CI)	0.882 (0.794-0.971)	0.875 (0.743-1.000)

AUC: area under the curve; PPV: positive predictive value; NPV: negative predictive value; CI: confidence interval.