Functional connectivity in EEG: a multiclass classification approach for disorders of consciousness DOI Creative Commons

Sreelakshmi Raveendran,

S Kala,

A. G. Ramakrishnan

et al.

Frontiers in Neuroscience, Journal Year: 2025, Volume and Issue: 19

Published: March 28, 2025

Characterizing functional connectivity (FC) in the human brain is crucial for understanding and supporting clinical decision making disorders of consciousness. This study investigates FC using sliding window correlation (SWC) analysis electroencephalogram (EEG) applied to three measures: phase-lag index (PLI) weighted (wPLI), which quantify phase synchronization, amplitude envelope (AEC), captures amplitude-based coactivation patterns between pairs channels. SWC performed across five canonical frequency bands (delta, theta, alpha, beta, gamma) EEG data from four distinct groups: coma, unresponsive wakefulness syndrome, minimally conscious state, healthy controls. The extracted metrics, mean, reflecting stability connectivity, standard deviation, indicating variability, are analyzed discern differences at group level. Multiclass classification attempted various models artificial neural networks that include different multilayer perceptrons (MLP), recurrent networks, long-short-term memory gated units, a hybrid CNN-LSTM model combines convolutional (CNN) network validate discriminative power these features. results show MLP 2 achieves accuracy 96.3% AEC features obtained with length 16s, highlighting effectiveness AEC. An evaluation performance sizes (16 20 s) shows consistently high accuracy, ranging 95.5% 96.3%, When wPLI combined, maximum increases 96.9% 96.7% 3, size 17 seconds both cases.

Language: Английский

Serotonergic psychedelics as potential therapeutics for post-COVID-19 syndrome (or Long COVID): A comprehensive review DOI
Zhen Xuen Brandon Low, Shin Jie Yong, Hayam Ali AlRasheed

et al.

Progress in Neuro-Psychopharmacology and Biological Psychiatry, Journal Year: 2025, Volume and Issue: unknown, P. 111279 - 111279

Published: Feb. 1, 2025

Language: Английский

Citations

0
Functional connectivity in EEG: a multiclass classification approach for disorders of consciousness DOI Creative Commons

Sreelakshmi Raveendran,

S Kala,

A. G. Ramakrishnan

et al.

Frontiers in Neuroscience, Journal Year: 2025, Volume and Issue: 19

Published: March 28, 2025

Characterizing functional connectivity (FC) in the human brain is crucial for understanding and supporting clinical decision making disorders of consciousness. This study investigates FC using sliding window correlation (SWC) analysis electroencephalogram (EEG) applied to three measures: phase-lag index (PLI) weighted (wPLI), which quantify phase synchronization, amplitude envelope (AEC), captures amplitude-based coactivation patterns between pairs channels. SWC performed across five canonical frequency bands (delta, theta, alpha, beta, gamma) EEG data from four distinct groups: coma, unresponsive wakefulness syndrome, minimally conscious state, healthy controls. The extracted metrics, mean, reflecting stability connectivity, standard deviation, indicating variability, are analyzed discern differences at group level. Multiclass classification attempted various models artificial neural networks that include different multilayer perceptrons (MLP), recurrent networks, long-short-term memory gated units, a hybrid CNN-LSTM model combines convolutional (CNN) network validate discriminative power these features. results show MLP 2 achieves accuracy 96.3% AEC features obtained with length 16s, highlighting effectiveness AEC. An evaluation performance sizes (16 20 s) shows consistently high accuracy, ranging 95.5% 96.3%, When wPLI combined, maximum increases 96.9% 96.7% 3, size 17 seconds both cases.

Language: Английский

Citations

0