Table 1 Performance measures for classification between ALS and PP for SVM, PCA-SVM, and PCA-LR: sensitivity, specificity, and AUC. In addition, the accuracy measures are also given for a SVM classification between ALS and PP based on the ALS- and PP-specific pattern expression scores as determined by PCA-SVM by using a healthy control group and projecting individual 18F-FDG PET scans onto the ALS and PP-specific metabolic brain patterns
Sensitivity | Specificity | AUC | |
|---|---|---|---|
SVM | 0.86 ± 0.01 | 0.82 ± 0.01 | 0.89 ± 0.01 |
PCA-SVM | 0.86 ± 0.02 | 0.82 ± 0.02 | 0.90 ± 0.01 |
PCA-LR | 0.85 ± 0.02 | 0.82 ± 0.02 | 0.90 ± 0.01 |
Classification based on ALS and PP expression scores (SVM) | 0.90 ± 0.02 | 0.83 ± 0.01 | 0.91 ± 0.01 |