Noninvasive Evaluation of Liver Fibrosis Reverse Using Artificial Neural Network Model for Chronic Hepatitis B Patients

Table 3

Sensitivity, specificity, and AUC of the ANN model and logistic regression.

	Sensitivity (%)	Specificity (%)	AUC	LR+	LR−	PPV (%)	NPV (%)
ANN model	83.1	85.2	0.809 ± 0.062	5.61	0.19	93.0	74.5
Logistic regression	75.0	78.6	0.756 ± 0.059	3.50	0.32	87.2	61.1

LR+, positive likelihood ratio; LR−, negative likelihood ratio; PPV, positive predictive value; NPV, negative predictive value.