Table 5 Performance evaluation of XGBoost, the clinic nomogram and the clinic-ML nomogram in the training (first line in each cell) and test set (second line in each cell)
Models | Sensitivity (95% CL) | Specificity (95% CL) | F1 (95% CL) | AUC (95% CL) |
|---|---|---|---|---|
XGBoost | 0.924 (0.883–0.965) 0.680 (0.535–0.825) | 0.963 (0.933–0.993) 0.853 (0.743–0.963) | 0.927 (0.886–0.968) 0.664 (0.518–0.810) | 0.989 (0.980–0.998) 0.842 (0.764–0.919) |
Clinic nomogram | 0.704 (0.633–0.775) 0.609 (0.458–0.760) | 0.870(0.817–0.923) 0.822 (0.703–0.941) | 0.700(0.628–0.772) 0.585 (0.432–0.738) | 0.897 (0.867–0.926) 0.837 (0.764–0.910) |
Clinic-ML nomogram | 0.983 (0.963–1.000) 0.713 (0.573–0.853) | 0.994 (0.982–1.000) 0.869 (0.764–0.974) | 0.985 (0.966–1.000) 0.699 (0.557–0.841) | 0.998 (0.996–1.000) 0.864 (0.794–0.935) |