Table 5 Comparison of predictive performance with Naïve Bayes, Logistic regression, IBk and J48 classifier. More details for prediction accuracy measurement are given in the Methods section. The results were obtained by 5-fold cross-validation.
Methods | Prediction accuracy (%) | |||
|---|---|---|---|---|
| Â | Q 2 | MCC | Sensitivity | Specificity |
SVM | 71.5 | 0.43 | 70.7 | 72.2 |
Naïve Bayes | 59.1 | 0.18 | 57.0 | 61.1 |
Logistic regression | 58.7 | 0.17 | 56.6 | 60.8 |
IBk (K-nearest neighbors) | 52.9 | 0.06 | 44.9 | 60.5 |
J48 (decision trees) | 54.2 | 0.09 | 53.6 | 54.7 |