Variational mode decomposition-based EEG analysis for the classification of disorders of consciousness
Aberrant alterations in any of the two dimensions of consciousness, namely awareness and arousal, can lead to the emergence of disorders of consciousness (DOC). The development of DOC may arise from more severe or targeted lesions in the brain, resulting in widespread functional abnormalities. Howev...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2024-02-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2024.1340528/full |
_version_ | 1797323724997787648 |
---|---|
author | Sreelakshmi Raveendran Raghavendra Kenchaiah Santhos Kumar Jayakrushna Sahoo M. K. Farsana Ravindranadh Chowdary Mundlamuri Sonia Bansal V. S. Binu A. G. Ramakrishnan Subasree Ramakrishnan S. Kala |
author_facet | Sreelakshmi Raveendran Raghavendra Kenchaiah Santhos Kumar Jayakrushna Sahoo M. K. Farsana Ravindranadh Chowdary Mundlamuri Sonia Bansal V. S. Binu A. G. Ramakrishnan Subasree Ramakrishnan S. Kala |
author_sort | Sreelakshmi Raveendran |
collection | DOAJ |
description | Aberrant alterations in any of the two dimensions of consciousness, namely awareness and arousal, can lead to the emergence of disorders of consciousness (DOC). The development of DOC may arise from more severe or targeted lesions in the brain, resulting in widespread functional abnormalities. However, when it comes to classifying patients with disorders of consciousness, particularly utilizing resting-state electroencephalogram (EEG) signals through machine learning methods, several challenges surface. The non-stationarity and intricacy of EEG data present obstacles in understanding neuronal activities and achieving precise classification. To address these challenges, this study proposes variational mode decomposition (VMD) of EEG before feature extraction along with machine learning models. By decomposing preprocessed EEG signals into specified modes using VMD, features such as sample entropy, spectral entropy, kurtosis, and skewness are extracted across these modes. The study compares the performance of the features extracted from VMD-based approach with the frequency band-based approach and also the approach with features extracted from raw-EEG. The classification process involves binary classification between unresponsive wakefulness syndrome (UWS) and the minimally conscious state (MCS), as well as multi-class classification (coma vs. UWS vs. MCS). Kruskal-Wallis test was applied to determine the statistical significance of the features and features with a significance of p < 0.05 were chosen for a second round of classification experiments. Results indicate that the VMD-based features outperform the features of other two approaches, with the ensemble bagged tree (EBT) achieving the highest accuracy of 80.5% for multi-class classification (the best in the literature) and 86.7% for binary classification. This approach underscores the potential of integrating advanced signal processing techniques and machine learning in improving the classification of patients with disorders of consciousness, thereby enhancing patient care and facilitating informed treatment decision-making. |
first_indexed | 2024-03-08T05:32:32Z |
format | Article |
id | doaj.art-ed2a67e3f1a246e68b2a12a11497de8d |
institution | Directory Open Access Journal |
issn | 1662-453X |
language | English |
last_indexed | 2024-03-08T05:32:32Z |
publishDate | 2024-02-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Neuroscience |
spelling | doaj.art-ed2a67e3f1a246e68b2a12a11497de8d2024-02-06T04:35:43ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2024-02-011810.3389/fnins.2024.13405281340528Variational mode decomposition-based EEG analysis for the classification of disorders of consciousnessSreelakshmi Raveendran0Raghavendra Kenchaiah1Santhos Kumar2Jayakrushna Sahoo3M. K. Farsana4Ravindranadh Chowdary Mundlamuri5Sonia Bansal6V. S. Binu7A. G. Ramakrishnan8Subasree Ramakrishnan9S. Kala10Department of Electronics and Communication Engineering, Indian Institute of Information Technology, Kottayam, Kerala, IndiaDepartment of Neurology, NIMHANS, Bangalore, Karnataka, IndiaDepartment of Electronics and Communication Engineering, Indian Institute of Information Technology, Kottayam, Kerala, IndiaDepartment of Computer Science and Engineering, Indian Institute of Information Technology, Kottayam, Kerala, IndiaDepartment of Neurology, NIMHANS, Bangalore, Karnataka, IndiaDepartment of Neurology, NIMHANS, Bangalore, Karnataka, IndiaDepartment of Neuroanaesthesia and Neurocritical Care, NIMHANS, Bangalore, Karnataka, IndiaDepartment of Biostatistics, NIMHANS, Bangalore, Karnataka, IndiaDepartment of Electrical Engineering and Centre for Neuroscience, Indian Institute of Science, Bangalore, Karnataka, IndiaDepartment of Neurology, NIMHANS, Bangalore, Karnataka, IndiaDepartment of Electronics and Communication Engineering, Indian Institute of Information Technology, Kottayam, Kerala, IndiaAberrant alterations in any of the two dimensions of consciousness, namely awareness and arousal, can lead to the emergence of disorders of consciousness (DOC). The development of DOC may arise from more severe or targeted lesions in the brain, resulting in widespread functional abnormalities. However, when it comes to classifying patients with disorders of consciousness, particularly utilizing resting-state electroencephalogram (EEG) signals through machine learning methods, several challenges surface. The non-stationarity and intricacy of EEG data present obstacles in understanding neuronal activities and achieving precise classification. To address these challenges, this study proposes variational mode decomposition (VMD) of EEG before feature extraction along with machine learning models. By decomposing preprocessed EEG signals into specified modes using VMD, features such as sample entropy, spectral entropy, kurtosis, and skewness are extracted across these modes. The study compares the performance of the features extracted from VMD-based approach with the frequency band-based approach and also the approach with features extracted from raw-EEG. The classification process involves binary classification between unresponsive wakefulness syndrome (UWS) and the minimally conscious state (MCS), as well as multi-class classification (coma vs. UWS vs. MCS). Kruskal-Wallis test was applied to determine the statistical significance of the features and features with a significance of p < 0.05 were chosen for a second round of classification experiments. Results indicate that the VMD-based features outperform the features of other two approaches, with the ensemble bagged tree (EBT) achieving the highest accuracy of 80.5% for multi-class classification (the best in the literature) and 86.7% for binary classification. This approach underscores the potential of integrating advanced signal processing techniques and machine learning in improving the classification of patients with disorders of consciousness, thereby enhancing patient care and facilitating informed treatment decision-making.https://www.frontiersin.org/articles/10.3389/fnins.2024.1340528/fullvariational mode decompositiondisorders of consciousnessresting-state EEGensemble bagged treepatient careresource management |
spellingShingle | Sreelakshmi Raveendran Raghavendra Kenchaiah Santhos Kumar Jayakrushna Sahoo M. K. Farsana Ravindranadh Chowdary Mundlamuri Sonia Bansal V. S. Binu A. G. Ramakrishnan Subasree Ramakrishnan S. Kala Variational mode decomposition-based EEG analysis for the classification of disorders of consciousness Frontiers in Neuroscience variational mode decomposition disorders of consciousness resting-state EEG ensemble bagged tree patient care resource management |
title | Variational mode decomposition-based EEG analysis for the classification of disorders of consciousness |
title_full | Variational mode decomposition-based EEG analysis for the classification of disorders of consciousness |
title_fullStr | Variational mode decomposition-based EEG analysis for the classification of disorders of consciousness |
title_full_unstemmed | Variational mode decomposition-based EEG analysis for the classification of disorders of consciousness |
title_short | Variational mode decomposition-based EEG analysis for the classification of disorders of consciousness |
title_sort | variational mode decomposition based eeg analysis for the classification of disorders of consciousness |
topic | variational mode decomposition disorders of consciousness resting-state EEG ensemble bagged tree patient care resource management |
url | https://www.frontiersin.org/articles/10.3389/fnins.2024.1340528/full |
work_keys_str_mv | AT sreelakshmiraveendran variationalmodedecompositionbasedeeganalysisfortheclassificationofdisordersofconsciousness AT raghavendrakenchaiah variationalmodedecompositionbasedeeganalysisfortheclassificationofdisordersofconsciousness AT santhoskumar variationalmodedecompositionbasedeeganalysisfortheclassificationofdisordersofconsciousness AT jayakrushnasahoo variationalmodedecompositionbasedeeganalysisfortheclassificationofdisordersofconsciousness AT mkfarsana variationalmodedecompositionbasedeeganalysisfortheclassificationofdisordersofconsciousness AT ravindranadhchowdarymundlamuri variationalmodedecompositionbasedeeganalysisfortheclassificationofdisordersofconsciousness AT soniabansal variationalmodedecompositionbasedeeganalysisfortheclassificationofdisordersofconsciousness AT vsbinu variationalmodedecompositionbasedeeganalysisfortheclassificationofdisordersofconsciousness AT agramakrishnan variationalmodedecompositionbasedeeganalysisfortheclassificationofdisordersofconsciousness AT subasreeramakrishnan variationalmodedecompositionbasedeeganalysisfortheclassificationofdisordersofconsciousness AT skala variationalmodedecompositionbasedeeganalysisfortheclassificationofdisordersofconsciousness |