Table 4. Classification results using combined data including sulcal measures, cortical thickness, cortical volume, subcortical volume and the MMSE score.
| Feature Set | Selected Attributes | Classifier | Accuracy | Sensitivity | Specificity | AUC |
|---|---|---|---|---|---|---|
| SM,CT,CV,SV,MMSE | MMSE | Naïve Bayesa | 0.894 | 0.867 | 0.861 | 0.893 |
| Hippocampus L | ||||||
| Hippocampus R | ||||||
| Amygdala R | Logistic Regressiona | 0.878 | 0.867 | 0.863 | 0.864 | |
| Parahippocampal_volume R | ||||||
| Precuneus_volume L | ||||||
| Precuneus_thickness R | SVMa | 0.909 | 0.889 | 0.884 | 0.826 | |
| Supramarginal_thickness R | ||||||
| g-SI L | ||||||
| Entorhinal_volume R |
Abbreviations: SM-- sulcal measures; CT-- cortical thickness; CV-- cortical volume; SV-- subcortical volume
L-- Left hemisphere; R-- Right hemisphere
a Significantly different from single measure using a two-tailed t-test (p<0.001).