Accurate Prediction of Advanced Liver Fibrosis Using the Decision Tree Learning Algorithm in Chronic Hepatitis C Egyptian Patients

Table 3

Accuracy and Roc analysis of model 1, model 2, and FIB-4 for predicting advanced fibrosis with criteria value zero.

Model	Sensitivity %	Specificity %	PPV %	NPV %	ROC	Accuracy %
Model 1	15.1	97.9	55.2	87	0.78	85.7
Model 2	17.5	97.5	54.8	87.3	0.78	85.7
Model 1	14.4	97.9	56.6	85.9	0.78	84.7
Model 2	17.4	97.5	56.6	86.2	0.78	84.8
FIB-4	17.9	95.51	42.8	86.1	0.73	83.2

PPV: positive predictive value; NPP: negative predictive value; ROC: receiver operating characteristic curve.
Applying the model on the training set.
Applying the model on the test set.