Combining CT Images and Clinical Features of Four Periods to Predict Whether Patients Have Rectal Cancer

Table 5

The predictive performance of the prediction models using the testing set.

Variables	Clinical demographics	Radiomic	Total model
Cut off	0.426	0.265	0.557
Sensitivity (95% CI)	0.944 (0.839–1.000)	0.778 (0.586–0.970)	0.778 (0.586–0.970)
Specificity (95% CI)	0.844 (0.718–0.970)	0.844 (0.718–0.970)	1.000 (1.000–1.000)
PPV (95% CI)	0.773 (0.598–0.948)	0.737 (0.539–0.935)	1.000 (1.000–1.000)
NPV (95% CI)	0.964 (0.896–1.000)	0.871 (0.753–0.989)	0.889 (0.786–0.992)
AUC (95% CI)	0.911 (0.834–0.989)	0.903 (0.821–0.985)	0.962 (0.915–1.000)
Accuracy (95% CI)	0.880 (0.790–0.970)	0.820 (0.714–0.926)	0.920 (0.845–0.995)

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