Table 3.

Performance comparison of logistic regression models for prediction of high-grade clear cell renal cell carcinoma.

Included Variables in Models	Sensitivity	Specificity	PPV	NPV	Accuracy (%)	AUC (95% CI)
SETD2 (frozen tissue)	0.84	0.59	0.84	0.59	71.43%	0.779 (0.704–0.853)
DDX11 (frozen tissue)	1.00	0.93	1.00	0.93	96.43%	0.964 (0.931–0.997)
SETD2 + DDX11 (frozen tissue)	0.97	0.99	0.97	0.99	97.86%	0.997 (0.992–1.000)
SETD2 (plasma)	0.86	1.00	1.00	0.86	92.86%	0.952 (0.918–0.987)
DDX11 (plasma)	0.84	0.70	0.84	0.70	77.14%	0.836 (0.771–0.900)
SETD2 + DDX11 (plasma)	0.93	0.93	0.93	0.93	92.86%	0.971 (0.947–0.994)

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