Mean value and SD of balanced accuracy, recall, precision, F 1 score, AUC, MCC, DYI and kappa of the machine learning models and the proposed method implemented in this study
| Methods | Balanced accuracy | Recall | Precision | F1 score |
| SVM | 81.24±0.54 | 81.31±0.61 | 81.26±0.64 | 81.54±0.67 |
| DT | 83.25±0.78 | 83.17±0.72 | 83.15±0.73 | 83.31±0.74 |
| GNB | 80.08±0.67 | 80.11±0.75 | 79.91±0.62 | 80.07±0.66 |
| KNN | 85.42±0.59 | 85.48±0.45 | 86.01±0.35 | 86.08±0.41 |
| XGB | 92.37±0.31 | 92.43±0.36 | 92.55±0.24 | 92.42±0.27 |
| Methods | AUC | MCC | DYI | Kappa |
| SVM | 0.81±0.02 | 72.03±0.65 | 80.96±0.68 | 72.65±0.64 |
| DT | 0.83±0.02 | 72.94±0.72 | 82.79±0.63 | 73.58±0.69 |
| GNB | 0.80±0.02 | 71.65±0.75 | 79.87±0.71 | 72.61±0.73 |
| KNN | 0.85±0.02 | 75.16±0.43 | 85.23±0.47 | 75.86±0.51 |
| XGB | 0.92±0.02 | 84.23±0.26 | 92.39±0.24 | 85.14±0.25 |
AUC, area under the curve; DT, decision tree; DYI, degenerate Youden index; GNB, Gaussian naïve Bayes; KNN, k-nearest neighbors; MCC, Matthew’s correlation coefficient; SVM, support vector machine; XGB, eXtreme Gradient Boosting.