Table 3.
Four statistical measures evaluating the performance of the template-based classification in the training set and test set of the AML data.
| Tubes | Training set |
Test set |
||||||
|---|---|---|---|---|---|---|---|---|
| Precision | Recall | Specificity | F-value | Precision | Recall | Specificity | F-value | |
| 4 | 0.94 | 0.74 | 0.99 | 0.83 | 1.00 | 0.75 | 1.00 | 0.86 |
| 5 | 0.75 | 0.91 | 0.96 | 0.82 | 0.65 | 0.85 | 0.94 | 0.74 |
| 6 | 1.00 | 0.70 | 1.00 | 0.82 | 1.00 | 0.80 | 1.00 | 0.89 |
| All (2–7) | 1.00 | 0.74 | 1.00 | 0.85 | 1.00 | 0.85 | 1.00 | 0.92 |
| 4–6 | 1.00 | 0.96 | 1.00 | 0.98 | 1.00 | 1.00 | 1.00 | 1.00 |
The statistical measures are computed for each tube separately and two combinations of tubes.