Research Article
Predicting Metabolic Syndrome Using the Random Forest Method
Table 3
Summary of statistical parameters for MS classification using Random Forest.
| | Internal test set (10-fold CV) | External test set | Acc | Sens | Spec | MCC | Acc | Sens | Spec | MCC |
| 10 | 97.10 | 94.28 | 97.98 | 0.92 | 97.99 | 95.00 | 98.92 | 0.94 | 20 | 97.94 | 95.07 | 98.82 | 0.94 | 98.11 | 94.00 | 99.38 | 0.95 | 30 | 98.02 | 94.72 | 99.04 | 0.94 | 97.64 | 92.00 | 99.38 | 0.93 | 40 | 98.02 | 94.81 | 99.02 | 0.94 | 97.76 | 92.50 | 99.38 | 0.94 | 50 | 98.02 | 94.64 | 99.07 | 0.94 | 97.76 | 92.50 | 99.38 | 0.94 |
|
|
10-fold CV: 10-fold cross-validation, Acc: accuracy, Sens: sensitivity, Spec: specificity, and MCC: Matthews correlation coefficient.
|