Table 3.
Summary of the performances of the breast cancer recurrence prediction models on the independent test in terms of accuracy, sensitivity, and specificity, using the Optimal Subset of Features (OSF) also combined with the clinical features (OSF + clinical), respectively. The features were selected for the exams at timepoint T1 alone or at timepoints T1–T2 simultaneously (original model). The number of features selected for OSF and OSF+ clinical are also highlighted.
| Independent Test | ||||
|---|---|---|---|---|
| Performance Metric | OSF | OSF + Clinical | ||
| T1 | T1–T2 | T1 | T1–T2 | |
| N. features | 15 | 13 + 5 | 15 + 4 | 13 + 5 + 4 |
| Accuracy | 80.7% | 80.7% | 80.3% | 85.2% |
| Sensitivity | 47.1% | 76.5% | 53.9% | 84.6% |
| Specificity | 93.3% | 82.2% | 90.2% | 85.4% |