Table 3.
Summary of the performances achieved by the pCR prediction models in terms of AUC.
| Set | Model | N. Features | AUC | Acc. | Sens. | Spec. |
|---|---|---|---|---|---|---|
| Public DB Independent test: 45 patients (13 pCR) |
Clinical | 5 | 58.2% | 64.4% | 53.6% | 68.8% |
| F-merged | 29 | 75.0% | 73.3% | 69.2% | 75.0% | |
| F-merged + clinical | 34 | 80.3% | 84.4% | 69.2% | 90.6% | |
| Private DB Independent test: 22 patients (7 pCR) |
Clinical | 5 | 56.0% | 59.1% | 42.9% | 66.7% |
| F-merged | 28 | 72.4% | 77.3% | 57.1% | 86.7% | |
| F-merged + clinical | 33 | 78.0% | 77.3% | 71.4% | 80.0% |
Accuracy (Acc.), Sensitivity (Sens.), and Specificity (Spec.) on the independent tests of the public DB and private DB. The number of features comprising each model is also reported. The best results achieved for each of the evaluation metrics are indicated in bold.