Table 2.
Performance of the optimal fold for identifying EGFR 19Del, 21L858R and WT in lesion-wise and patient-wise on the independent test set
| Fold 3 | Mutation subtype | AUC (95% CI) | Sensitivity | Specificity | Accuracy | Overall accuracy (95% CI) |
|---|---|---|---|---|---|---|
| Lesion-wise | WT | 1.000 ± 0.000 | 1.000 | 0.816 | 0.859 | 0.818 ± 0.035 |
| 19Del | 0.996 ± 0.004 | 0.701 | 1.000 | 0.877 | ||
| 21L858R | 0.971 ± 0.013 | 0.833 | 0.936 | 0.901 | ||
| Patient-wise | WT | 1.000 ± 0.000 | 1.000 | 0.870 | 0.906 | |
| 19Del | 1.000 ± 0.000 | 0.726 | 1.000 | 0.899 | 0.874 ± 0.059 | |
| 21L858R | 0.991 ± 0.009 | 0.920 | 0.943 | 0.941 |
AUC and overall accuracy data are given as point estimation ± halfwidth of the 95% confidence interval (CI). 19Del 19 deletion, 21L858R 21-point mutation, AUC Area under the curve, EGFR Epidermal growth factor receptor, WT Wild-type