Development and validation of a nomogram based on biparametric MRI PI-RADS v2.1 and clinical parameters to avoid unnecessary prostate biopsies

Table 3 Performance comparison (AUC, 95% CI) of the different models and the DeLong test for significance

Cohorts	Clinical model			bpMRI PI-RADS v2.1-based model			p value for AUCs
Cohorts	Sensitivity%	Specificity%	AUC (95% CI)	Sensitivity%	Specificity%	AUC (95% CI)	p value for AUCs
Development Cohort	95	34	0.796(0.737, 0.856)	95	61	0.891 (0.849, 0.934)	< 0.001
Validation Cohort 1	95	0	0.676(0.586, 0.766)	95	51	0.877(0.826, 0.928)	< 0.001
Validation Cohort 2	95	8	0.664(0.577, 0.752)	95	19	0.833(0.768, 0.897)	< 0.001

AUC area under the curve, CI confidence interval, bpMRI biparametric Magnetic Resonance Imaging, PI-RADS v2.1 Prostate Imaging Reporting and Data System version 2.1

ISSN: 1471-2342