Table 4 Comparison between classification metrics of the different models in the training and validation sets.
From: Machine learning algorithms as new screening approach for patients with endometriosis
Models | Training set | Validation set | ||||||
|---|---|---|---|---|---|---|---|---|
Sensitivity | Specificity | F1-score | AUC | Sensitivity | Specificity | F1-score | AUC | |
Random forest (RF) | 0.98 | 0.8 | 0.88 | 0.89 | 0.92 | 0.92 | 0.92 | 0.92 |
Logistic regression (LR) | 1 | 0 | 0 | 0.5 | 0.95 | 0.81 | 0.87 | 0.88 |
Decision tree (DT) | 0.82 | 0.8 | 0.81 | 0.82 | 0.91 | 0.66 | 0.77 | 0.78 |
eXtreme gradient boosting (XGB) | 0.98 | 0.8 | 0.88 | 0.89 | 0.93 | 0.92 | 0.92 | 0.93 |
Voter classifier soft | 0.98 | 0.6 | 0.74 | 0.75 | 0.93 | 0.88 | 0.9 | 0.90 |
Voter classifier hard | 0.95 | 0.8 | 0.87 | 0.88 | 0.91 | 0.92 | 0.91 | 0.92 |
