A Clinical Radiomics Nomogram Was Developed by Integrating Radiomics Signatures and Clinical Variables to Distinguish High-Grade ccRCC from Type 2 pRCC

Table 3

Comparison of the diagnostic performance among the three models.

Model	Training cohort				Testing cohort
	AUC (95% CI)	Accuracy%	Specificity%	Sensitivity%	AUC (95% CI)	Accuracy%	Specificity%	Sensitivity%
Clinical factor model	0.921	88.8	85.7	91.8	0.872	77.3	90.9	63.6
	(0.872, 0.966)				(0.78, 0.95)
Radiomics signature	0.968	91.8	89.8	93.9	0.936	86.4	90.9	81.8
	(0.941, 0.990)				(0.876, 0.986)
Clinical radiomics nomogram	0.974	93.9	98.0	89.8	0.952	88.6	100	77.3
	(0.944, 0.997)				(0.903, 0.992)

AUC, the area under the curve; CI, confidence interval.