Recognition Enhancement of Dementia Patients’ Working Memory Using Entropy-Based Features and Local Tangent Space Alignment Algorithm

Abstract

Detecting dementia presents a barrier to advancing individualized healthcare. Electroencephalographic (EEG) signals’ nonlinear nature has been characterized using entropies. While a working memory (WM), the EEGs of 5 patients suffering vascular dementia (VD), 15 patients had stroke-related mild cognitive impairment (SMCI), and 15 healthy normal control (NC) participants were evaluated in this study. A four-step framework for the automatic identification of dementia is provided, with the first stage employing the newly developed automatic independent component analysis and wavelet (AICA-WT) method. In the second stage, nonlinear entropy features using fuzzy entropy (FuzzEn), fluctuation-based dispersion entropy (FDispEn), and bubble entropy (BubbEn) were utilized to extract various dynamical properties from multi-channel EEG signals derived from patients with dementia. A statistical examination of the individual performance was conducted using analysis of variance (ANOVA) to determine the degree of EEG complexity across brain regions. Afterwards, the nonlinear local tangent space alignment (LSTA) dimensionality reduction approach was utilized to enhance the automatic diagnosis of dementia patients’. Using k-nearest neighbors (kNN), support vector machine (SVM), and decision tree (DT) classifiers, the impairment of post-stroke patients was finally identified. BubbEn is chosen to develop a new BubbEn-LTSA mapping process for creating the innovative AICA-WT-BubbEn-LTSA dementia recognition framework, which is the basis for an automated VD detection.