Analysis for Alzheimer's disease using cross-correlation of EEG data

As the elderly population grows, the number of people with dementia is also increasing. If dementia is detected at an early stage, it is possible to slow its progression. Patients with Alzheimer's disease, a type of dementia, show some specific EEG patterns, and we have therefore been investigating EEG analysis to detect Alzheimer's disease. In this paper, we propose a method that evaluates the phase relation between three electrodes. This method enables estimation of the dynamical behavior of an assumed dipole in the deep brain to potentially detect Alzheimer's disease, depending on the disease progression. This method requires only three electrodes and a short period of data collection (1 min). Experimental results show that Alzheimer's disease is identified with over 70% accuracy. Therefore, this Alzheimer's disease detection system appears to be feasible.