From: Nerve detection with optical spectroscopy for regional anesthesia procedures
Classification method | Feature selection | MCC | ACC | SENS (%) | SPEC (%) | PPV | NPV | TP | FN | FP | TN |
---|---|---|---|---|---|---|---|---|---|---|---|
SVM | Fit | 0.683 | 0.848 | 85.0 | 84.6 | 0.765 | 0.906 | 91 | 16 | 28 | 154 |
SVM | PCA | 0.693 | 0.855 | 83.2 | 86.8 | 0.788 | 0.898 | 89 | 18 | 24 | 158 |
SVM | Segments | 0.717 | 0.862 | 88.8 | 84.6 | 0.772 | 0.928 | 95 | 12 | 28 | 154 |
SVM | Combined | 0.751 | 0.882 | 86.9 | 89.0 | 0.823 | 0.920 | 93 | 14 | 20 | 162 |
PLSDA | 10PC’s | 0.580 | 0.789 | 84.1 | 75.8 | 0.672 | 0.890 | 90 | 17 | 44 | 138 |
CART | Fit | 0.442 | 0.730 | 71.0 | 74.2 | 0.618 | 0.813 | 76 | 31 | 47 | 135 |