Table 4.
Comparison of prediction performances among different models for bone metastasis.
| Models | Internal test | External test | ||||||
|---|---|---|---|---|---|---|---|---|
| AUC | Accuracy | Sensitivity (recall rate) | Specificity | AUC | Accuracy | Sensitivity (recall rate) | Specificity | |
| LR | 0.839 | 0.795 | 0.796 | 0.761 | 0.878 | 0.777 | 0.768 | 0.834 |
| NBC | 0.839 | 0.822 | 0.825 | 0.686 | 0.863 | 0.836 | 0.823 | 0.761 |
| DT | 0.831 | 0.658 | 0.662 | 0.836 | 0.863 | 0.660 | 0.713 | 0.849 |
| RF | 0.847 | 0.765 | 0.764 | 0.780 | 0.862 | 0.780 | 0.771 | 0.834 |
| GBM | 0.850 | 0.783 | 0.784 | 0.777 | 0.880 | 0.787 | 0.779 | 0.834 |
| XGB | 0.857 | 0.787 | 0.787 | 0.791 | 0.888 | 0.803 | 0.801 | 0.837 |
DT, Decision tree; LR, Logistic regression; GBM, Gradient Boosting Machine; NBC, Naive Bayes classification; RF, Random Forest; XGB, Extreme gradient boosting.