Table 2.

Binary classification results after the three groups are collapsed into binary groups

Metrics	Validation dataset		Test dataset
	(Na, PPGb + Gc)	(Na + PPGb, Gc)	(Na, PPGb + Gc)	(Na + PPGb, Gc)
AUROCd, %	95.91	96.42e	95.45f	95.24
Accuracy, %	89.96	90.57e	88.88f	86.11
Sensitivity, %	89.93	90.54e	88.63f	86.77
Specificity, %	89.99	90.59e	89.17f	85.49
Precision, %	87.92	94.13e	96.53f	95.46
F3g, %	89.73	89.80e	88.77f	86.56

^aN: normal

^bPPG: pre-perimetrical glaucoma

^cG: glaucoma

^dAUROC: area under the receiver operator characteristic curve

^ebest metrics value in the validation set

^fbest metrics value in the test set

^gF3: F-Beta measure, beta = 3