Functional Connectivity Metrics in Temporal Lobe Epilepsy: A Machine Learning Perspective With MEG

Temporal Lobe Epilepsy (TLE) is a prevalent neurological disorder affecting millions worldwide, including a significant proportion in India. Precise diagnosis and effective treatment planning are critical for TLE patients, necessitating advanced neuroimaging techniques. Magnetoencephalography (MEG)...

Full description

Saved in:
Bibliographic Details
Main Authors: M. V. Suhas, N. Mariyappa, A. Karunakar Kotegar, M. Ravindranadh Chowdary, K. Raghavendra, Ajay Asranna, L. G. Viswanathan, H. Anitha, Sanjib Sinha
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10757422/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850266261553938432
author M. V. Suhas
N. Mariyappa
A. Karunakar Kotegar
M. Ravindranadh Chowdary
K. Raghavendra
Ajay Asranna
L. G. Viswanathan
H. Anitha
Sanjib Sinha
author_facet M. V. Suhas
N. Mariyappa
A. Karunakar Kotegar
M. Ravindranadh Chowdary
K. Raghavendra
Ajay Asranna
L. G. Viswanathan
H. Anitha
Sanjib Sinha
author_sort M. V. Suhas
collection DOAJ
description Temporal Lobe Epilepsy (TLE) is a prevalent neurological disorder affecting millions worldwide, including a significant proportion in India. Precise diagnosis and effective treatment planning are critical for TLE patients, necessitating advanced neuroimaging techniques. Magnetoencephalography (MEG) offers a non-invasive method for evaluating brain function, providing detailed insights into TLE. In this study, we aim to evaluate the potential of functional connectivity metrics derived from MEG data at the source level for distinguishing TLE patients from healthy controls (HCs). We analyse the data across various brain frequency bands, including alpha, beta, delta, gamma, theta, broadband, and high-frequency oscillations (HFO), using amplitude envelope correlation and graph theory metrics. We employ machine learning algorithms to classify TLE and HC groups based on these metrics. Chi2 feature importance analysis reveals significant importance of connectivity metrics such as local efficiency, mean clustering coefficient, mean shortest path length, small worldness score, weighted degree centrality, binary degree centrality, global efficiency across frequency bands, particularly in theta, alpha, beta, broadband and HFO bands. Various machine learning models demonstrate high classification performance, with accuracies reaching up to 100% in particular frequency bands in agreement with the Chi2 feature importance analysis. Overall, the Subspace Discriminant Ensemble model, especially in the Theta and Alpha frequency bands, show exceptional potential for classifying TLE and HCs. Overall, this study underscores the potential of MEG and functional connectivity analysis using specific frequency bands and machine learning models for classifying TLE and HC with high accuracy, which may contribute to improved diagnosis and management of epilepsy.
format Article
id doaj-art-fe5b26821ac04b61903c2dab7265a0de
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-fe5b26821ac04b61903c2dab7265a0de2025-08-20T01:54:12ZengIEEEIEEE Access2169-35362024-01-011217509117510710.1109/ACCESS.2024.350222710757422Functional Connectivity Metrics in Temporal Lobe Epilepsy: A Machine Learning Perspective With MEGM. V. Suhas0https://orcid.org/0000-0002-5337-7157N. Mariyappa1https://orcid.org/0000-0002-8021-1048A. Karunakar Kotegar2https://orcid.org/0000-0002-2458-3891M. Ravindranadh Chowdary3https://orcid.org/0000-0002-5360-257XK. Raghavendra4Ajay Asranna5L. G. Viswanathan6H. Anitha7https://orcid.org/0000-0001-5898-4442Sanjib Sinha8Department of Electronics and Communication Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, IndiaDepartment of Neurology, National Institute of Mental Health and Neurosciences (NIMHANS), Bengaluru, IndiaDepartment of Data Science and Computer Applications, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, IndiaDepartment of Neurology, National Institute of Mental Health and Neurosciences (NIMHANS), Bengaluru, IndiaDepartment of Neurology, National Institute of Mental Health and Neurosciences (NIMHANS), Bengaluru, IndiaDepartment of Neurology, National Institute of Mental Health and Neurosciences (NIMHANS), Bengaluru, IndiaDepartment of Neurology, National Institute of Mental Health and Neurosciences (NIMHANS), Bengaluru, IndiaDepartment of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, IndiaDepartment of Neurology, National Institute of Mental Health and Neurosciences (NIMHANS), Bengaluru, IndiaTemporal Lobe Epilepsy (TLE) is a prevalent neurological disorder affecting millions worldwide, including a significant proportion in India. Precise diagnosis and effective treatment planning are critical for TLE patients, necessitating advanced neuroimaging techniques. Magnetoencephalography (MEG) offers a non-invasive method for evaluating brain function, providing detailed insights into TLE. In this study, we aim to evaluate the potential of functional connectivity metrics derived from MEG data at the source level for distinguishing TLE patients from healthy controls (HCs). We analyse the data across various brain frequency bands, including alpha, beta, delta, gamma, theta, broadband, and high-frequency oscillations (HFO), using amplitude envelope correlation and graph theory metrics. We employ machine learning algorithms to classify TLE and HC groups based on these metrics. Chi2 feature importance analysis reveals significant importance of connectivity metrics such as local efficiency, mean clustering coefficient, mean shortest path length, small worldness score, weighted degree centrality, binary degree centrality, global efficiency across frequency bands, particularly in theta, alpha, beta, broadband and HFO bands. Various machine learning models demonstrate high classification performance, with accuracies reaching up to 100% in particular frequency bands in agreement with the Chi2 feature importance analysis. Overall, the Subspace Discriminant Ensemble model, especially in the Theta and Alpha frequency bands, show exceptional potential for classifying TLE and HCs. Overall, this study underscores the potential of MEG and functional connectivity analysis using specific frequency bands and machine learning models for classifying TLE and HC with high accuracy, which may contribute to improved diagnosis and management of epilepsy.https://ieeexplore.ieee.org/document/10757422/Amplitude envelope correlationbrain frequency bandsbrain networksclassificationepilepsy diagnosisgraph theory
spellingShingle M. V. Suhas
N. Mariyappa
A. Karunakar Kotegar
M. Ravindranadh Chowdary
K. Raghavendra
Ajay Asranna
L. G. Viswanathan
H. Anitha
Sanjib Sinha
Functional Connectivity Metrics in Temporal Lobe Epilepsy: A Machine Learning Perspective With MEG
IEEE Access
Amplitude envelope correlation
brain frequency bands
brain networks
classification
epilepsy diagnosis
graph theory
title Functional Connectivity Metrics in Temporal Lobe Epilepsy: A Machine Learning Perspective With MEG
title_full Functional Connectivity Metrics in Temporal Lobe Epilepsy: A Machine Learning Perspective With MEG
title_fullStr Functional Connectivity Metrics in Temporal Lobe Epilepsy: A Machine Learning Perspective With MEG
title_full_unstemmed Functional Connectivity Metrics in Temporal Lobe Epilepsy: A Machine Learning Perspective With MEG
title_short Functional Connectivity Metrics in Temporal Lobe Epilepsy: A Machine Learning Perspective With MEG
title_sort functional connectivity metrics in temporal lobe epilepsy a machine learning perspective with meg
topic Amplitude envelope correlation
brain frequency bands
brain networks
classification
epilepsy diagnosis
graph theory
url https://ieeexplore.ieee.org/document/10757422/
work_keys_str_mv AT mvsuhas functionalconnectivitymetricsintemporallobeepilepsyamachinelearningperspectivewithmeg
AT nmariyappa functionalconnectivitymetricsintemporallobeepilepsyamachinelearningperspectivewithmeg
AT akarunakarkotegar functionalconnectivitymetricsintemporallobeepilepsyamachinelearningperspectivewithmeg
AT mravindranadhchowdary functionalconnectivitymetricsintemporallobeepilepsyamachinelearningperspectivewithmeg
AT kraghavendra functionalconnectivitymetricsintemporallobeepilepsyamachinelearningperspectivewithmeg
AT ajayasranna functionalconnectivitymetricsintemporallobeepilepsyamachinelearningperspectivewithmeg
AT lgviswanathan functionalconnectivitymetricsintemporallobeepilepsyamachinelearningperspectivewithmeg
AT hanitha functionalconnectivitymetricsintemporallobeepilepsyamachinelearningperspectivewithmeg
AT sanjibsinha functionalconnectivitymetricsintemporallobeepilepsyamachinelearningperspectivewithmeg