Classification of Single Normal and Alzheimer's Disease Individuals from Cortical Sources of Resting State EEG Rhythms.

摘要: Previous studies have shown abnormal power and functional connectivity of resting state electroencephalographic (EEG) rhythms in groups Alzheimer's disease (AD) compared to healthy elderly (Nold) subjects. Here we tested the best classification rate 120 AD patients 100 matched Nold subjects using EEG markers based on cortical sources these rhythms. data were recorded during eyes-closed condition. Exact low-resolution brain electromagnetic tomography (eLORETA) estimated frontal, central, parietal, occipital, temporal, limbic regions. Delta (2-4 Hz), theta (4-8 alpha 1 (8-10.5 2 (10.5-13 beta (13-20 (20-30 gamma (30-40 Hz) frequency bands interest. The rates interest those with an area under receiver operating characteristic curve (AUROC) higher than 0.7 as a threshold for moderate (i.e., 70%). Results showed that following overcame this threshold: (i) delta/alpha current density; (ii) occipital (iii) frontal theta/alpha (iv) inter-hemispherical connectivity; (v) occipital-temporal right left intra-hemispherical (vi) parietal-limbic connectivity. Occipital density (sensitivity 73.3%, specificity 78%, accuracy 75.5%, AUROC 82%). These results suggest source can classify individuals 80%.