Table 4.
Training and test set performances for the XGBoost model developed with the combination of CE-T1-weighted and T2-weighted-based radiomic features
| XGBoost model CE-T1-weighted and T2-weighted | ||
|---|---|---|
| Training set | Test set | |
| AUC | 0.90 (95% CI: 0.85–0.94) | 0.85 (95% CI: 0.75–0.95) |
| Accuracy | 0.81 (95% CI: 0.74–0.91) | 0.76 (95% CI: 0.64–0.88) |
| Sensitivity | 0.82 (95% CI: 0.71–0.89) | 0.81 (95% CI: 0.66–0.96) |
| Specificity | 0.80 (95% CI: 0.75–0.88) | 0.71 (95% CI: 0.53–0.89) |
AUC Area under the ROC curve, CI Confidence interval