Functional Brain Network Disruptions in Parkinson’s Disease: Insights from Information Theory and Machine Learning DOI Creative Commons
Ömer Akgüller, Mehmet Ali Balcı, Gabriela Cioca

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(23), P. 2728 - 2728

Published: Dec. 4, 2024

This study investigates disruptions in functional brain networks Parkinson's Disease (PD), using advanced modeling and machine learning. Functional were constructed the Nonlinear Autoregressive Distributed Lag (NARDL) model, which captures nonlinear asymmetric dependencies between regions of interest (ROIs). Key network metrics information-theoretic measures extracted to classify PD patients healthy controls (HC), deep learning models, with explainability methods employed identify influential features.

Language: Английский

Beta-to-Theta Entropy Ratio of EEG in Aging, Frontotemporal Dementia, and Alzheimer's Dementia DOI
Ahmad Zandbagleh, Ανδρέας Μιλτιάδους,

Saeid Sanei

et al.

American Journal of Geriatric Psychiatry, Journal Year: 2024, Volume and Issue: 32(11), P. 1361 - 1382

Published: July 4, 2024

Language: Английский

Citations

5
Diagnosis of Cognitive and Mental Disorders: A New Approach Based on Spectral–Spatiotemporal Analysis and Local Graph Structures of Electroencephalogram Signals DOI Creative Commons

Arezoo Sanati Fahandari,

Sara Moshiryan,

Ateke Goshvarpour

et al.

Brain Sciences, Journal Year: 2025, Volume and Issue: 15(1), P. 68 - 68

Published: Jan. 14, 2025

Background/Objectives: The classification of psychological disorders has gained significant importance due to recent advancements in signal processing techniques. Traditionally, research this domain focused primarily on binary classifications disorders. This study aims classify five distinct states, including one control group and four categories Methods: Our investigation will utilize algorithms based Granger causality local graph structures improve accuracy. Feature extraction from connectivity matrices was performed using structure graphs. extracted features were subsequently classified employing K-Nearest Neighbors (KNN), Support Vector Machine (SVM), AdaBoost, Naïve Bayes classifiers. Results: KNN classifier demonstrated the highest accuracy gamma band for depression category, achieving an 89.36%, a sensitivity 89.57%, F1 score 94.30%, precision 99.90%. Furthermore, SVM surpassed other machine learning when all integrated, attaining 89.06%, 88.97%, 94.16%, 100% discrimination band. Conclusions: proposed methodology provides novel approach analyzing EEG signals holds potential applications

Language: Английский

Citations

0
EEG Responses to Exercise Intensity in Parkinson's Disease DOI Creative Commons
Zahra Alizadeh, Emad Arasteh, Maryam S. Mirian

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 17, 2025

1. Abstract 1.1. Background Exercise is increasingly recognized as a beneficial intervention for Parkinson’s disease (PD), yet the optimal type and intensity of exercise remain unclear. This study investigated relationship between neural responses in PD patients, using electroencephalography (EEG) to explore potential markers that could be ultimately used guide intensity. 1.2. Method EEG data were collected from 14 patients (5 females) 8 healthy controls (HC) performing stationary pedaling exercises at 60 RPM with resistance adjusted target heart rates 30%, 40%, 50%, 60%, 70% maximum rate. Subjects pedaled 3 minutes each level counterbalanced order. Canonical Time-series Characteristics (Catch-22) features Multi-set Correlation Analysis (MCCA) utilized identify common profiles increasing across subjects. 1.3. Results We identified statistically significant MCCA component demonstrating monotonic The dominant feature this was Periodicity Wang (PW), related autocorrelation EEG. revealed consistent trend features: six increased intensity, indicating heightened rhythmic engagement sustained activation, while three decreased, suggesting reduced variability enhanced predictability responses. Notably, exhibited more rigid, response patterns compared (HC), who showed greater flexibility their adaptation intensities. 1.4. Conclusion highlights feasibility EEG-derived track identifying specific correlating varying levels. subjects demonstrate less inter-subject motor Our results suggest biomarkers can assess differing brain involvement same potentially useful guiding targeted therapeutic strategies maximizing neurological benefits PD.

Language: Английский

Citations

0
Optimizing Parkinson’s Disease Detection: Hybrid S-transform-EEG Feature Reduction Through Trajectory Analysis DOI

Melina Maria Afonso,

Damodar Reddy Edla,

R. Ravinder Reddy

et al.

SN Computer Science, Journal Year: 2025, Volume and Issue: 6(2)

Published: Feb. 3, 2025

Language: Английский

Citations

0
Intra- and Inter-Regional Complexity in Multi-Channel Awake EEG Through Multivariate Multiscale Dispersion Entropy for Assessing Sleep Quality and Aging DOI Creative Commons
Ahmad Zandbagleh, Saeid Sanei, Lucía Penalba‐Sánchez

et al.

Biosensors, Journal Year: 2025, Volume and Issue: 15(4), P. 240 - 240

Published: April 9, 2025

Aging and poor sleep quality are associated with altered brain dynamics, yet current electroencephalography (EEG) analyses often overlook regional complexity. This study addresses this gap by introducing a novel integration of intra- inter-regional complexity analysis using multivariate multiscale dispersion entropy (mvMDE) from awake resting-state EEG for the first time. Moreover, assessing both provides comprehensive perspective on dynamic interplay between localized neural activity its coordination across regions, which is essential understanding substrates aging quality. Data 58 participants—24 young adults (mean age = 24.7 ± 3.4) 34 older 72.9 4.2)—were analyzed, each group further divided based Pittsburgh Sleep Quality Index (PSQI) scores. To capture complexity, mvMDE was applied to most informative sensors, one sensor selected region four methods: highest average correlation, entropy, mutual information, principal component loading. targeted approach reduced computational cost enhanced effect sizes (ESs), particularly at large scale factors (e.g., 25) linked delta-band activity, PCA-based method achieving ESs (1.043 in adults). Overall, we expect that inter- intra-regional will play pivotal role elucidating mechanisms as captured various physiological data modalities—such EEG, magnetoencephalography, magnetic resonance imaging—thereby offering promising insights range biomedical applications.

Language: Английский

Citations

0
Multivariate distance dispersion entropy: a complexity analysis method capturing intra- and inter-channel signal variations for multichannel data DOI
Yan Niu, Runan Ding, Mengni Zhou

et al.

Nonlinear Dynamics, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 7, 2024

Language: Английский

Citations

1
1924–2024: First centennial of EEG DOI Creative Commons
Paolo Maria Rossini, Jonathan Cole, Walter Paulus

et al.

Clinical Neurophysiology, Journal Year: 2024, Volume and Issue: 170, P. 132 - 135

Published: Dec. 19, 2024

Language: Английский

Citations

0
Functional Brain Network Disruptions in Parkinson’s Disease: Insights from Information Theory and Machine Learning DOI Creative Commons
Ömer Akgüller, Mehmet Ali Balcı, Gabriela Cioca

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(23), P. 2728 - 2728

Published: Dec. 4, 2024

This study investigates disruptions in functional brain networks Parkinson's Disease (PD), using advanced modeling and machine learning. Functional were constructed the Nonlinear Autoregressive Distributed Lag (NARDL) model, which captures nonlinear asymmetric dependencies between regions of interest (ROIs). Key network metrics information-theoretic measures extracted to classify PD patients healthy controls (HC), deep learning models, with explainability methods employed identify influential features.

Language: Английский

Citations

0