Title: EEG wavelet packet power spectrum tool for checking Alzheimer's disease progression

Authors: Rui Miguel Cunha; Gabriel Silva; Marco Alves; Bruno Catarino Bispo; Dílio Alves; Carolina Garrett; Pedro M. Rodrigues

Addresses: Laboratório Associado, CBQF – Centro de Biotecnologia e Química Fina, Escola Superior de Biotecnologia, Universidade Católica Portuguesa, Rua Diogo Botelho 1327, 4169-005, Porto, Portugal ' Laboratório Associado, CBQF – Centro de Biotecnologia e Química Fina, Escola Superior de Biotecnologia, Universidade Católica Portuguesa, Rua Diogo Botelho 1327, 4169-005, Porto, Portugal ' Laboratório Associado, CBQF – Centro de Biotecnologia e Química Fina, Escola Superior de Biotecnologia, Universidade Católica Portuguesa, Rua Diogo Botelho 1327, 4169-005, Porto, Portugal ' Department of Electrical and Electronic Engineering, Federal University of Santa Catarina, 88040-370 Florianópolis, SC, Brazil ' Departamento de Neurologia, Centro Hospitalar São João, 4200-319 Porto, Portugal ' Departamento de Neurologia, Centro Hospitalar São João, 4200-319 Porto, Portugal ' Laboratório Associado, CBQF – Centro de Biotecnologia e Química Fina, Escola Superior de Biotecnologia, Universidade Católica Portuguesa, Rua Diogo Botelho 1327, 4169-005, Porto, Portugal

Abstract: Alzheimer's disease (AD) is one of the most prevalent neurodegenerative diseases and it is strongly associated with age. There are four AD stages: mild cognitive impairment (MCI), mild, moderate (ADM) and advanced (ADA). This work aims at developing a new tool capable of distinguishing the different stages of AD at scalp level. Features such as the conventional frequencies relative power of the power spectrum wavelet packet transform have been extracted from the electroencephalogram signals in order to feed four classifiers: random forest decision trees, linear and quadratic support-vector-machines and linear discriminant analysis. The obtained results were analyzed through topographic maps and enabled the distinguish between binary groups with the following overall accuracies: 85.5% (C-MCI); 88.2% (C-ADM); 91.4% (C-ADA); 89.7% (MCI-ADM); 82.4% (MCI-ADA) and 81.3% (ADM-ADA). The applied method was able to detect major differences in scalp areas above the frontal and temporal lobes of the brain as AD progresses.

Keywords: Alzheimer's disease; AD; mild cognitive impairment; MCI; power spectral density; wavelet packet transform; electroencephalogram signals; classifiers.

DOI: 10.1504/IJBET.2022.126497

International Journal of Biomedical Engineering and Technology, 2022 Vol.40 No.3, pp.289 - 302

Received: 20 Feb 2020
Accepted: 29 Jun 2020
Published online: 27 Oct 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article