Smart-Data-Driven System for Alzheimer Disease Detection through Electroencephalographic Signals.

Area of Science:

• Neuroscience
• Medical Technology
• Artificial Intelligence

Background:

• Alzheimer's Disease (AD) is a leading cause of dementia, affecting primarily the elderly.
• AD progresses through three stages: Mild Cognitive Impairment (MCI), Mild and Moderate AD (ADM), and Advanced AD (ADA).
• Early diagnosis is critical to slow disease progression.

Purpose of the Study:

• To develop a system for differentiating AD stages using Electroencephalographic Signals (EEG).
• To aid in the early diagnosis of Alzheimer's Disease.

Main Methods:

• Nonlinear multi-band analysis of EEG signals using Wavelet Packet transform.
• Extraction of relevant features from EEG data.
• Classification of disease stages using Machine Learning (ML) and Deep Learning (DL) models.

Main Results:

• High classification accuracies were achieved across different AD stages.
• Maximum accuracies included 78.9% (C vs. MCI), 81.0% (C vs. ADM), 84.2% (C vs. ADA), 88.9% (MCI vs. ADM), and 93.8% (MCI vs. ADA).
• The system demonstrated superior performance in binary comparisons, outperforming previous studies.

Conclusions:

• The proposed EEG analysis method effectively differentiates AD stages.
• Central and parietal brain regions show abnormal activity progression in AD.
• This approach offers a promising tool for early AD detection and management.