Table 3 Performance of Each Machine Learning Algorithm in the Independent Test Set of Patients*
| Â | XGBoost | Multi-Layer Perception | Support Vector Machine | Elastic Net Logistic Regression | Random Forest |
|---|---|---|---|---|---|
Accuracy | 0.86 (0.84 to 0.87) | 0.86 (0.85 to 0.87) | 0.86 (0.86 to 0.87) | 0.86 (0.86 to 0.87) | 0.88 (0.87 to 0.89) |
Sensitivity | 0.16 (0.10 to 0.21) | 0.0 (0.0 to 0.0) | 0.0 (0.0 to 0.0) | 0.11 (0.06 to 0.16) | 0.17 (0.11 to 0.24) |
Specificity | 0.96 (0.95 to 0.98) | 0.99 (0.99 to 1.0) | 1.0 (1.0 to 1.0) | 0.98 (0.97 to 0.99) | 0.98 (0.98 to 0.99) |
Precision | 0.42 (0.27 to 0.58) | 0.0 (0.0 to 0.0) | 0.0 (0.0 to 0.0) | 0.36 (0.21 to 0.51) | 0.59 (0.41 to 0.77) |
F1 Score | 0.21 (0.14 to 0.28) | 0.0 (0.0 to 0.0) | 0.0 (0.0 to 0.0) | 0.18 (0.10 to 0.26) | 0.25 (0.17 to 0.33) |
Brier Score | 0.10 (0.09 to 0.11) | 0.12 (0.11 to 0.12) | 0.11 (0.11 to 0.11) | 0.10 (0.09 to 0.11) | 0.10 (0.09 to 0.10) |
AUC | 0.76 (0.73 to 0.80) | 0.66 (0.60 to 0.73) | 0.69 (0.64 to 0.74) | 0.69 (0.63 to 0.75) | 0.81 (0.77 to 0.85) |