BMC Medical Informatics and Decision Making

Table 6 Se, Sp, PPV, NPV, AUC of CNN algorithms

From: Analysis of anterior segment in primary angle closure suspect with deep learning models

		Se	Sp	PPV	NPV	AUC
VGG-16	1	0.83	0.93	0.88	0.9	0.73
	2	0.94	0.86	0.81	0.96	0.79
	3	0.89	0.86	0.8	0.92	0.82
	4	0.83	0.93	0.88	0.9	0.82
	5	0.72	0.93	0.87	0.84	0.79
	M (95%CI)	0.84 (0.74,0.94)	0.90 (0.85,0.95)	0.85 (0.80,0.90)	0.90 (0.85,0.96)	0.79 (0.74,0.84)
Alexnet	1	0.89	0.93	0.89	0.93	0.81
	2	0.89	0.93	0.89	0.93	0.94
	3	0.89	0.96	0.94	0.93	0.8
	4	0.72	0.96	0.93	0.84	0.86
	5	0.78	0.96	0.93	0.87	0.82
	M (95%CI)	0.83 (0.74,0.93)	0.95 (0.93,0.97)	0.92 (0.89,0.95)	0.90 (0.85,0.95)	0.85 (0.77,0.92)

Se: sensitivity; Sp: Specificity; PPV: positive predict value; NPV: negative predict value; AUC: area under the curve; CNN: convolutional neural network; VGG-16: Visual Geometry Group-16

Back to article page

ISSN: 1472-6947

Contact us

General enquiries: journalsubmissions@springernature.com