Table 8. Sensitivity boost of the ‘un-curated’ dataset with two labels, for healthy and diseased categories.
| Margin Max (0.4) Boosting Healthy | Original | Margin Max (0.4) Boosting Diseased | |
|---|---|---|---|
| accuracy | 0.8921 | 0.8963 | 0.8810 |
| Sensitivity Healthy | 0.9831 | 0.9665 | 0.9154 |
| Sensitivity Diseased | 0.6346 | 0.6975 | 0.7836 |
| Specificity Healthy | 0.8840 | 0.9005 | 0.923 |
| Specificity Diseased | 0.9297 | 0.8801 | 0.7659 |
| F1 Score Healthy | 0.9309 | 0.9323 | 0.9192 |
| F1 Score Diseased | 0.7543 | 0.7783 | 0.7746 |
| NPV Healthy | 0.9297 | 0.8801 | 0.7659 |
| NPV Diseased | 0.884 | 0.9005 | 0.923 |
| PPV Healthy | 0.8840 | 0.9005 | 0.9230 |
| PPV Diseased | 0.9297 | 0.8801 | 0.7659 |