open access publication

Article, 2024

A tensor decomposition scheme for EEG-based diagnosis of mild cognitive impairment

Heliyon, ISSN 1879-4378, 2405-7843, 2405-8440, Volume 10, 4, Page e26365, 10.1016/j.heliyon.2024.e26365

Contributors

Faghfouri, Alireza 0009-0009-1863-2253 [1] Shalchyan, Vahid 0000-0003-1226-6132 (Corresponding author) [1] Toor, Hamza Ghazanfar 0000-0002-1406-6188 [2] Amjad, Imran 0000-0002-2824-0079 [2] [3] Niazi, Imran Khan 0000-0001-8752-7224 [3] [4] [5]

Affiliations

  1. [1] Iran University of Science and Technology
    2. [NORA names: Iran; Asia, Middle East];
  2. [2] Riphah International University
    3. [NORA names: Pakistan; Asia, South];
  3. [3] New Zealand College of Chiropractic
    4. [NORA names: New Zealand; Oceania; OECD];
  4. [4] Aalborg University
    5. [NORA names: AAU Aalborg University; University; Denmark; Europe, EU; Nordic; OECD];
  5. [5] Auckland University of Technology
    6. [NORA names: New Zealand; Oceania; OECD]

Abstract

Mild Cognitive Impairment (MCI) is the primary stage of acute Alzheimer's disease, and early detection is crucial for the person and those around him. It is difficult to recognize since this mild stage does not have clear clinical signs, and its symptoms are between normal aging and severe dementia. Here, we propose a tensor decomposition-based scheme for automatically diagnosing MCI using Electroencephalogram (EEG) signals. A new projection is proposed, which preserves the spatial information of the electrodes to construct a data tensor. Then, using parallel factor analysis (PARAFAC) tensor decomposition, the features are extracted, and a support vector machine (SVM) is used to discriminate MCI from normal subjects. The proposed scheme was tested on two different datasets. The results showed that the tensor-based method outperformed conventional methods in diagnosing MCI with an average classification accuracy of 93.96% and 78.65% for the first and second datasets, respectively. Therefore, it seems that maintaining the spatial topology of the signals plays a vital role in the processing of EEG signals.

Keywords

Alzheimer's disease, EEG signals, EEG-based diagnosis, accuracy, age, analysis, automatically, classification, classification accuracy, clinical signs, cognitive impairment, conventional methods, data, data tensor, dataset, decomposition, decomposition scheme, decomposition-based scheme, dementia, detection, diagnosing MCI, diagnosis of mild cognitive impairment, disease, early detection, electrode, electroencephalogram, factor analysis, features, impairment, information, machine, method, mild cognitive impairment, mild stage, normal aging, normal subjects, parallel factor analysis, persons, primary stage, process, processing of EEG signals, project, results, scheme, severe dementia, signal, signs, spatial information, spatial topology, stage, subjects, support, support vector machine, symptoms, tensor, tensor decomposition schemes, tensor-based method, topology, vector machine

Data Provider: Digital Science

LINKS
-

Matching Records in NORA

SUBJECTS
+

METRICS
+