Artificial intelligence in the diagnosis of dental diseases on panoramic radiographs: a preliminary study

BMC Oral Health

Table 5 Diagnostic performance of the framework and individual dentists for residual roots

Var	Spe	Sen	Youden’s index	AUC (SE; 95% CI)	P	Z
Framework	0.999	0.871	0.870	0.935 (0.02150; 0.929–0.940)	ref	ref
H1	1.000	0.919	0.919	0.960 (0.01740; 0.955–0.964)	0.310	1.016
H2	0.999	0.919	0.918	0.959 (0.01740; 0.955–0.963)	0.316	1.003
H3	1.000	0.887	0.887	0.943 (0.02030; 0.938–0.948)	0.731	0.344
M1	0.999	0.823	0.822	0.911 (0.02450; 0.905–0.917)	0.412	0.821
M2	0.999	0.839	0.838	0.919 (0.02350; 0.913–0.925)	0.567	0.572
M3	0.999	0.855	0.854	0.927 (0.02260; 0.921–0.932)	0.761	0.304
L1	0.999	0.839	0.838	0.919 (0.02350; 0.912–0.925)	0.592	0.536
L2	1.000	0.871	0.871	0.935 (0.02150; 0.930–0.941)	0.987	0.017
L3	0.999	0.839	0.838	0.919 (0.02350; 0.913–0.925)	0.569	0.570

Delong test was conducted for statistically analysis of the difference of AUC between the framework and the dentists. * represents significant difference (p < 0.05)

ISSN: 1472-6831