Table 3.
Performance of machine learning classifiers for predicting tumor budding status in test dataset.
| Classifier | AUC (95% CI) | Accuracy (95% CI) | Sensitivity | Specificity | PPV | NPV |
|---|---|---|---|---|---|---|
| LR | 0.742 (0.572–0.907) |
0.769 (0.564–0.910) |
0.857 | 0.737 | 0.546 | 0.933 |
| RF | 0.782 (0.528–0.884) |
0.731 (0.522–0.884) |
0.750 | 0.722 | 0.546 | 0.867 |
| SVM | 0.849 (0.740–1.000) |
0.885 (0.699–0.976) |
0.900 | 0.875 | 0.818 | 0.933 |
| NN | 0.891 (0.768–1.000) |
0.731 (0.522–0.884) |
0.667 | 0.786 | 0.727 | 0.733 |
AUC, area under curve; CI, confidence interval; PPV, positive predictive value; NPV, negative predictive value; LR, logistic regression; RF, random forest; SVM, support vector machine; NN, neural network.