Assessment of axial spondyloarthritis activity using a magnetic resonance imaging-based multi-region-of-interest fusion model

Table 2 axSpA activity prediction performance of models based upon different Rad_Sig

Models	Accuracy	AUC	95% CI	Sensitivity	Specificity	PPV	NPV	Youden	Cohort
Fusion	0.908	0.977	0.9536–0.9998	0.909	0.907	0.857	0.942	0.500	Train
Circle	0.874	0.882	0.7880–0.9752	0.848	0.889	0.824	0.906	0.362	Train
Facet	0.966	0.988	0.9703–1.0000	0.970	0.963	0.941	0.981	0.438	Train
Fusion	0.818	0.857	0.6994–1.0000	0.750	0.857	0.750	0.857	0.361	Test
Circle	0.727	0.777	0.5781–0.9755	1.000	0.571	0.571	1.000	0.300	Test
Facet	0.682	0.714	0.4822–0.9463	1.000	0.538	0.533	1.000	0.345	Test

AUC area under the curve, CI confidence interval, PPV positive predictive value, NPV negative predictive value

ISSN: 1478-6362