Insights into Imaging

Table 4 Results of the radiomics model’s predictive ability for predicting the Leibovich risk groups in three cohorts

From: Validity of a multiphase CT-based radiomics model in predicting the Leibovich risk groups for localized clear cell renal cell carcinoma: an exploratory study

Model	Cohort	AUC (95% CI)	Sensitivity	Specificity	Accuracy	Cutoff
Radiomics model	Training	0.872 (0.821–0.923)	0.781	0.866	0.843	0.308
	Validation	0.865 (0.800–0.930)	0.897	0.733	0.789	0.239
	External testing	0.848 (0.728–0.967)	0.765	0.852	0.818	0.388

AUC Area under the receiver operating characteristic curve, CI Confidence interval

Back to article page