Table 7. Sensitivity boost of the ‘curated’ dataset with two labels, for healthy and diseased categories.
| Margin Max (0.4) Boosting Healthy | Original | Margin Max (0.4) Boosting Diseased | |
|---|---|---|---|
| accuracy | 0.9022 | 0.9091 | 0.8968 |
| Sensitivity Healthy | 0.9852 | 0.9726 | 0.9343 |
| Sensitivity Diseased | 0.6467 | 0.7132 | 0.7815 |
| Specificity Healthy | 0.8957 | 0.9127 | 0.9294 |
| Specificity Diseased | 0.9340 | 0.8943 | 0.7942 |
| F1 Score Healthy | 0.9383 | 0.9417 | 0.9319 |
| F1 Score Diseased | 0.7642 | 0.7935 | 0.7878 |
| PPV Healthy | 0.8957 | 0.9127 | 0.9294 |
| PPV Diseased | 0.9340 | 0.8943 | 0.7942 |
| NPV Healthy | 0.9340 | 0.8943 | 0.7942 |
| NPV Diseased | 0.8957 | 0.9127 | 0.9294 |