Table 2.
Results of the classification between single AD and Nold subjects based on composite rsEEG markers of source activity.
| Source Current Density (SCD) | Sensitivity (%) | Specificity (%) | Accuracy (%) | AUROC |
|---|---|---|---|---|
| Parietal delta/alpha1 | 77.5 | 70 | 74.1 | 0.79 |
| Occipital delta/alpha1 | 73.3 | 78 | 75.4 | 0.82 |
| Temporal delta/alpha1 | 78.3 | 70 | 74.5 | 0.78 |
| Limbic delta/alpha1 | 75.8 | 72 | 74.1 | 0.77 |
| Frontal theta/alpha1 | 70 | 72 | 70.9 | 0.76 |
| Central theta/alpha1 | 83.3 | 65 | 75.0 | 0.79 |
| Parietal theta/alpha1 | 78.3 | 74 | 76.3 | 0.82 |
| Occipital theta/alpha1 | 83.3 | 68 | 76.3 | 0.83 |
| Temporal theta/alpha1 | 70.8 | 83 | 76.3 | 0.82 |
| Limbic theta/alpha1 | 83.3 | 68 | 76.3 | 0.81 |
Specifically, those composite rsEEG markers were obtained by computing the ratio between the delta and alpha 1 source current density (SCD). The same procedure was followed to form the composite EEG markers obtained by computing the ratio between the theta and alpha 1 SCD. The classification rate is computed by the analysis of the area under the receiver operating characteristic curve (AUROC). The table reports the classification indexes for the composite EEG markers having an AUROC higher than 0.70 (i.e., 70%).