Table 5. Summary of statistical measures of the best classifiers on re-evaluation with independent dataset.

Classifier*	CSC J48	CSC LibSVM	CSC Naïve Bayes	CSC Random Forest
Accuracy	85.0	78.33	78.33	86.11
Sensitivity	81.82	77.27	68.18	86.36
Specificity	85.44	78.48	79.75	86.08
BCR$	83.63	77.88	73.96	86.22
F-value	0.57	0.47	0.43	0.60
MCC∧	0.53	0.41	0.36	0.57
auROC#	0.84	0.78	0.83	0.95

*CSC denotes Cost Sensitive classifier; BCR^$ is Balanced Classification Rate; MCC^∧ is Matthews Correlation Coefficient; auROC^# is area under Receiver Operating Characteristic (ROC) curve. Highest numerical value in each row is highlighted as bold letters.