Table 3.

Predictive performance of the three models.

Model	Training set (N = 133)						Validation set (N = 57)
	Accuracy	Sensitivity	Specificity	PPV	NPV	AUC (95% CI)	Accuracy	Sensitivity	Specificity	PPV	NPV	AUC (95% CI)
Radiomics model	75.18	80.36	71.43	67.16	83.33	0.85 (0.79–0.91)	71.93	87.50	60.61	61.76	86.96	0.84 (0.73–0.95)
Clinical–radiological model	75.19	81.08	72.92	53.57	90.91	0.77 (0.69–0.85)	66.67	63.16	68.42	50.00	78.79	0.76 (0.64–0.88)
Combined model	81.20	71.83	91.94	91.07	74.03	0.90 (0.85–0.95)	84.21	85.71	83.33	75.00	90.91	0.88 (0.80–0.97)

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