Table 4.
Confusion matrix following a PCA + LMT classification combination using brain iron content measures only.
| T2-weighted Image Features (based on quantitative R2, R2′, and R2* Features) | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Class | TP Rate | FP Rate | Precision | Recall | F-Measure | MCC | ROC Area | Confusion Matrix | Accuracy | ||
| HC | PD | PSP-RS | |||||||||
| HC | 0.763 | 0.108 | 0.806 | 0.763 | 0.784 | 0.663 | 0.875 | 29 | 7 | 2 | 75.7% |
| PD | 0.756 | 0.207 | 0.739 | 0.756 | 0.747 | 0.547 | 0.845 | 7 | 34 | 4 | |
| PSP-RS | 0.750 | 0.072 | 0.714 | 0.750 | 0.732 | 0.665 | 0.948 | 0 | 5 | 15 | |
TP, True Positive; FP, False Positive; MCC, Matthews Correlation Coefficient; ROC AUC, Area under the receiver operating characteristic curve; HC, Healthy Controls; PD, Parkinson's disease; PSP-RS, Progressive supranuclear palsy Richardson's syndrome.