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

Table 1 The mathematical equations used for the evaluation metrics

	Mathematical euations
Se	TP / (TP + FN)
Sp	TN / (FP + TN)
PPV	TP / (FP + TP)
NPV	TN / (FN + TN)
AUC	AUC=[∑_{i∈positive class} ranki-M×(M + 1)/2]/(M×N)

Se: sensitivity; Sp: specificity; PPV: positive predictive value; NPV: negative predictive value; AUC: area under curve; TP: true positive; FN: false negative; TN: true negative; FP: false positive; i, the number of the sample after the probability scores of all samples were ranked from smallest to largest; M, the number of postive sample; N, the number of negative sample

ISSN: 1472-6947