Table 1.
Performance values for each final classifier model.
| Complete set of features |
Reduced set of features |
|||
|---|---|---|---|---|
| Classifier performances | cv-ACC | AUC | cv-ACC | AUC |
| Model 1 (HC vs. AD) | 0.62 | 0.66 | 0.67 | 0.74 |
| Model 2 (HC vs. VaD) | 0.65 | 0.68 | 0.72 | 0.77 |
| Model 3 (AD vs. VaD) | 0.59 | 0.62 | 0.57 | 0.61 |
| Model 4 (HC vs. AD&VaD) | 0.70 | 0.75 | 0.77 | 0.83 |
Average of the CV accuracy (cv-ACC) and AUC performed for each final classifier using two different sets of features. The Complete Set of Features included a total of 132 predictors and the Reduced Set of Features included variable number of predictors based on automatic feature reduction. Values from [0.5–0.6] = Fail; [0.6–0.7] = Poor; [0.7–0.8] = Fair; [0.8–0.9] = Good; [0.9–1.0] = Excellent.