| C8a(0) |
k
-8
|
k
-9
|
k
-10
|
k
-12
|
---|
C8a(0)
| 0.569 | 0.747 | 0.626 | 0.808 | 0.690 |
k
-8
| 0.747 |
0.736
| 0.760 |
0.898
| 0.800 |
k
-9
| 0.626 | 0.760 | 0.603 | 0.822 | 0.709 |
k
-10
| 0.808 |
0.898
| 0.822 |
0.795
| 0.858 |
k
-12
| 0.690 | 0.800 | 0.709 | 0.858 | 0.676 |
- A common performance measure for classifiers is the area under the ROC curve. The worst and best achievable performance is 0.5 and 1, respectively. The evaluation of the area under the ROC curve verifies that if only one marker can be used, k-10 (area = 0.795) and k-8 (area = 0.736) are the best choice (on-diagonal bold numbers). In case of two markers, the combination of k-8 - k-10 allows for the best classification (area = 0.898) (off-diagonal bold numbers). For the three markers k-8, k-10, and k-12, the area under the ROC curve is 0.966.