Table 2.
Machine learning models and performance during nested resampling.
| Statistical procedure | Balanced accuracy (%) | AUC | Sensitivity (%) | Specificity (%) | PPV (%) | NPV (%) |
|---|---|---|---|---|---|---|
| Logistic regression | 75.13 | 0.85 | 71 | 80 | 85 | 62 |
| Tree | 71.55 | 0.79 | 76 | 67 | 79 | 63 |
| Random forest | 74.12 | 0.86 | 78 | 70 | 81 | 66 |
| Gradient boosting | 72.63 | 0.84 | 76 | 69 | 80 | 63 |
| KNN | 69.56 | 0.80 | 68 | 71 | 80 | 57 |
| SVM | 76.85 | 0.84 | 81 | 73 | 83 | 69 |
| Naive Bayes | 77.01 | 0.84 | 85 | 73 | 84 | 69 |
AUC, area under the curve (level of discrimination); PPV, positive predictive value; NPV, negative predictive value; KNN, k-nearest neighbors; SVM, support vector machines.