EEG-Based Alzheimer's Detection Using Power Spectral Density, Tsallis Entropy, Amplitude Features, and SVM Classification DOI Creative Commons

A. Cissé,

Zineb Farahat, Nabila Zrira

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 16, 2024

Abstract Alzheimer's disease (AD) is a neurodegenerative of brain tissue, currently incurable, which leads to the progressive and irreversible loss mental functions, particularly memory. It rare detect Alzheimer an early stage. However, diagnosis can allow faster treatment thus improve patient's well-being. Electroencephalogram (EEG) non-invasive cost-effective tool that measures electrical activity in brain. In this study, we aimed create automatic detection method by combining several powerful EEG biomarkers which, our knowledge, were never put together namely Power Spectral Density, Tsallis entropy changes amplitude. The features then into Support Vector Machine (SVM) for identifications patients healthy controls (CN). Using five-fold cross-validation strategy across entire frequency band, classification accuracy reached 83.08%, with sensitivity 78% specificity 90% while it 78.46% ,75% 83% using leave one subject out cross validation.

Language: Английский

STEADYNet: Spatiotemporal EEG analysis for dementia detection using convolutional neural network DOI
Pramod Kachare, Sandeep B. Sangle, Digambar Puri

et al.

Cognitive Neurodynamics, Journal Year: 2024, Volume and Issue: 18(5), P. 3195 - 3208

Published: July 19, 2024

Language: Английский

Citations

13
LCADNet: a novel light CNN architecture for EEG-based Alzheimer disease detection DOI
Pramod Kachare, Digambar Puri, Sandeep B. Sangle

et al.

Physical and Engineering Sciences in Medicine, Journal Year: 2024, Volume and Issue: unknown

Published: June 11, 2024

Language: Английский

Citations

9
Unlocking the Potential of EEG in Alzheimer's Disease Research: Current Status and Pathways to Precision Detection DOI Creative Commons

Faisal Akbar,

Imran Taj,

Syed Muhammad Usman

et al.

Brain Research Bulletin, Journal Year: 2025, Volume and Issue: unknown, P. 111281 - 111281

Published: March 1, 2025

Alzheimer's disease (AD) affects millions of individuals worldwide and is considered a serious global health issue due to its gradual neuro-degenerative effects on cognitive abilities such as memory, thinking, behavior. There no cure for this but early detection along with supportive care plan may aid in improving the quality life patients. Automated AD challenging because symptoms vary patients genetic, environmental, or other co-existing conditions. In recent years, multiple researchers have proposed automated methods using MRI fMRI. These approaches are expensive, poor temporal resolution, do not offer real-time insights, proven be very accurate. contrast, only limited number studies explored potential Electroencephalogram (EEG) signals detection. present cost-effective, non-invasive, high-temporal-resolution alternative Despite their potential, application EEG research remains under-explored. This study reviews publicly available datasets, variety machine learning models developed detection, performance metrics achieved by these methods. It provides critical analysis existing approaches, highlights challenges, identifies key areas requiring further investigation. Key findings include detailed evaluation current methodologies, prevailing trends, gaps field. What sets work apart in-depth Disease providing stronger more reliable foundation understanding role area.

Language: Английский

Citations

1
LEADNet: Detection of Alzheimer’s Disease Using Spatiotemporal EEG Analysis and Low-Complexity CNN DOI Creative Commons
Digambar Puri, Pramod Kachare, Sandeep B. Sangle

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 113888 - 113897

Published: Jan. 1, 2024

Clinical methods for dementia detection are expensive and prone to human errors. Despite various computer-aided using electroencephalography (EEG) signals artificial intelligence, a consistent separation of Alzheimer's disease (AD) normal-control (NC) subjects remains elusive. This paper proposes low-complexity EEG-based AD CNN called LEADNet generate disease-specific features. employs spatiotemporal EEG as input, two convolution layers feature generation, max-pooling layer asymmetric redundancy reduction, fully-connected nonlinear transformation selection, softmax probability prediction. Different quantitative measures calculated an open-source dataset compare four pre-trained models. The results show that the lightweight architecture has at least 150-fold reduction in network parameters highest testing accuracy 98.75% compared investigation individual showed successive improvements selection separating NC subjects. A comparison with state-of-the-art models accuracy, sensitivity, specificity were achieved by model.

Language: Английский

Citations

8
EEG complexity-based algorithm using Multiscale Fuzzy Entropy: Towards a detection of Alzheimer’s disease DOI Creative Commons
Andrea Cataldo, Sabatina Criscuolo, Egidio De Benedetto

et al.

Measurement, Journal Year: 2023, Volume and Issue: 225, P. 114040 - 114040

Published: Dec. 15, 2023

Alzheimer's Disease (AD) is a progressive neurodegenerative condition causing memory, attention, and language decline. Current AD diagnostic methods lack objectivity non-invasiveness. While electroencephalography (EEG) holds promise for research, conventional EEG analysis have proven unsatisfactory. Non-linear dynamical approaches are considered more effective in assessing the brain's complex nature. Starting from these considerations, this study presents an entropy-based algorithm utilizing Multiscale Fuzzy Entropy (MFE) as promising, method. Computed across 20 different time scales public dataset, MFE showed significant discriminative power. Notably, trend inversion was observed results: subjects displayed higher complexity values slow frequency bands compared to healthy controls, while opposite found fast bands. These findings underscore potential of effectively distinguishing patients individuals, marking advance toward objective reliable diagnosis strategies.

Language: Английский

Citations

12
A novel optimal wavelet filter banks for automated diagnosis of Alzheimer’s disease and mild cognitive impairment using Electroencephalogram signals DOI Creative Commons
Digambar Puri, Jayanand P. Gawande, Jaswantsing L. Rajput

et al.

Decision Analytics Journal, Journal Year: 2023, Volume and Issue: 9, P. 100336 - 100336

Published: Oct. 5, 2023

Electroencephalogram (EEG) of Alzheimer's disease (AD) patients show a slowing effect and less synchronization. EEG signal's transient abrupt nature is captured from various mother wavelets. However, better performance can be obtained by balancing time-frequency localization in wavelet filters. We propose new approach for designing filter banks based on optimal four-step lifting structure (FSLS). First, we design FSLS using Euler's Frobenius half-band polynomial (EFHBP). The perfect reconstruction condition vanishing moments are imposed EFHBP to achieve maximum flat filters (HBFs). HBFs optimized balanced uncertainty metric obtain spread balance. Afterward, these used the synthesis analysis banks. proposed biorthogonal (TFOBWFBs) achieved balance between localization. Further, TFBOBWFBs applied decompose signals AD patients. Twenty different features were extracted decomposed subbands, which twelve significant selected Kruskal Walli's test. machine learning models trained tested with 10-fold cross-validation leave-one-subject-out cross-validation. To validate this study, TFOBWFBs have been two publicly available datasets mild cognitive impairment (MCI), AD, healthy control (HC) subjects. 98.90% accuracy 2-way (AD vs. HC) 96.50% 3-way MCI classification support vector model method outperforms existing detection techniques. framework optimization more fast compared previous studies. Also, detect other neurodegenerative disorders.

Language: Английский

Citations

11
A Novel Metric for Alzheimer’s Disease Detection Based on Brain Complexity Analysis via Multiscale Fuzzy Entropy DOI Creative Commons
Andrea Cataldo, Sabatina Criscuolo, Egidio De Benedetto

et al.

Bioengineering, Journal Year: 2024, Volume and Issue: 11(4), P. 324 - 324

Published: March 27, 2024

Alzheimer's disease (AD) is a neurodegenerative brain disorder that affects cognitive functioning and memory. Current diagnostic tools, including neuroimaging techniques questionnaires, present limitations such as invasiveness, high costs, subjectivity. In recent years, interest has grown in using electroencephalography (EEG) for AD detection due to its non-invasiveness, low cost, temporal resolution. this regard, work introduces novel metric by multiscale fuzzy entropy (MFE) assess complexity, offering clinicians an objective, cost-effective tool aid early intervention patient care. To purpose, patterns different frequency bands 35 healthy subjects (HS) patients were investigated. Then, based on the resulting MFE values, specific algorithm, able complexity abnormalities are typical of AD, was developed further validated 24 EEG test recordings. This MFE-based method achieved accuracy 83% differentiating between HS with odds ratio 25, Matthews correlation coefficient 0.67, indicating viability diagnosis. Furthermore, algorithm showed potential identifying anomalies when tested subject mild impairment (MCI), warranting investigation future research.

Language: Английский

Citations

4
Insights into computer-aided EEG signal processing for traumatic brain injury assessment: A review DOI

Farzaneh Manzari,

Peyvand Ghaderyan

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 117279 - 117279

Published: March 1, 2025

Language: Английский

Citations

0
MSE-VGG: A Novel Deep Learning Approach Based on EEG for Rapid Ischemic Stroke Detection DOI Creative Commons
Wei Tong, Weiqi Yue, Fangni Chen

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(13), P. 4234 - 4234

Published: June 29, 2024

Ischemic stroke is a type of brain dysfunction caused by pathological changes in the blood vessels which leads to tissue ischemia and hypoxia ultimately results cell necrosis. Without timely effective treatment early time window, ischemic can lead long-term disability even death. Therefore, rapid detection crucial patients with stroke. In this study, we developed deep learning model based on fusion features extracted from electroencephalography (EEG) signals for fast Specifically, recruited 20 who underwent EEG examination during acute phase collected 19 adults no history as control group. Afterwards, constructed correlation-weighted Phase Lag Index (cwPLI), novel feature, explore synchronization information functional connectivity between channels. Moreover, spatio-temporal nonlinear complexity were fused combining cwPLI matrix Sample Entropy (SaEn) together further improve discriminative ability model. Finally, MSE-VGG network was employed classifier distinguish non-ischemic data. Five-fold cross-validation experiments demonstrated that proposed possesses excellent performance, accuracy, sensitivity, specificity reaching 90.17%, 89.86%, 90.44%, respectively. Experiments consumption verified method superior other state-of-the-art examinations. This study contributes advancement stroke, shedding light untapped potential demonstrating efficacy identification.

Language: Английский

Citations

3
ComBat models for harmonization of resting-state EEG features in multisite studies DOI Creative Commons
Alberto Jaramillo‐Jimenez, Diego Tovar, Yorguin-José Mantilla-Ramos

et al.

Clinical Neurophysiology, Journal Year: 2024, Volume and Issue: 167, P. 241 - 253

Published: Sept. 24, 2024

Language: Английский

Citations

3