Computational methods of EEG signals analysis for Alzheimer's disease classification

Abstract

Alzheimer's disease (AD) is a progressive neurological illness that causes neuron cells degeneration, resulting in cognitive impairment, which includes loss of memory and space-time perception. While there is no cure for AD, early diagnosis is critical to improving the management and helping in the selection of new therapies, which leads to a better quality of life for the affected individuals, their relatives and caregivers. EEG is a non-invasive technique that can be employed in the investigation of AD, and computational analysis of EEG signals has revealed promising results in detecting AD. In this sense, the main goal of this article is to apply different computational methods to detect AD in order to compare them in terms of distinguishing AD patients from healthy elderly subjects and in terms of computational cost.

Detecting Alzheimer Disease in EEG Data with Machine Learning and the Graph Discrete Fourier Transform

“…In recent years, the analysis of EEG signals has emerged as a promising avenue for the early detection of AD and several other neurodegenerative diseases (Cassani et al, 2018). Several studies have successfully harnessed the functional connectivity of electrode sites in EEG signals by feature engineering with GSP, utilizing standard machine learning (ML) models, or employing state-of-the-art Deep Learning (DL) methods such as Graph Neural Networks (GNNs) (Meena et al, 2022); (Mathur & Chakka, 2020); (Padole et al, 2018); (Song et al, 2021); (Vicchietti et al, 2023). This study contributes to this ongoing effort by benchmarking several ML models using GSP features created and the Graph Discrete Fourier Transform (GDFT) for AD detection in EEG data.…”

EEG Signal Processing for Medical Diagnosis, Healthcare, and Monitoring: A Comprehensive Review

“…A total of 109 samples spanning AD, MCI, and HC categories are converted to scalograms using both Fourier and Wavelet Transforms. Through the utilization of Wavelet-based feature extraction, they attained classification accuracies of 83% for AD and normal cases,92% for health and mild AD cases, and 79% for Mild and AD classification scenarios.In[128], authors employed six computational techniques for analyzing time-series data i.e. EEG of 160 subjects with AD and 24 with HC.…”