Kiran Raj V1, Shyam Sundar Rajagopalan2, Sujas Bhardwaj1, Rajanikant Panda1, Venkateswara Reddy Reddam1, Chaitanya Ganne3, Raghavendra Kenchaiah3, Ravindranadh C Mundlamuri3, Thennarasu Kandavel4, Kaushik K Majumdar5, Satishchandra Parthasarathy3, Sanjib Sinha3, Rose Dawn Bharath6. 1. Department of Neuroimaging and Interventional Radiology, National Institute of Mental Health and Neurosciences, Bangalore, Karnataka 560029, India; Advanced Brain Imaging Facility, Cognitive Neuroscience Centre, National Institute of Mental Health and Neurosciences, Bangalore, Karnataka 560029, India. 2. Department of Psychiatry, St. John's Medical College and Hospital, Bangalore, India. 3. Department of Neurology, National Institute of Mental Health and Neurosciences, Bangalore, Karnataka 560029, India. 4. Department of Biostatistics, National Institute of Mental Health and Neurosciences, Bangalore, Karnataka 560029, India. 5. Systems Science and Informatics Unit, Indian Statistical Institute, Bangalore, Karnataka 560059, India. 6. Department of Neuroimaging and Interventional Radiology, National Institute of Mental Health and Neurosciences, Bangalore, Karnataka 560029, India; Advanced Brain Imaging Facility, Cognitive Neuroscience Centre, National Institute of Mental Health and Neurosciences, Bangalore, Karnataka 560029, India. Electronic address: cns.researchers@gmail.com.
Abstract
PURPOSE: Quasi-stable electrical distribution in EEG called microstates could carry useful information on the dynamics of large scale brain networks. Using machine learning techniques we explored if abnormalities in microstates can identify patients with Temporal Lobe Epilepsy (TLE) in the absence of an interictal discharge (IED). METHOD: 4 Classes of microstates were computed from 2 min artefact free EEG epochs in 42 subjects (21 TLE and 21 controls). The percentage of time coverage, frequency of occurrence and duration for each of these microstates were computed and redundancy reduced using feature selection methods. Subsequently, Fishers Linear Discriminant Analysis (FLDA) and logistic regression were used for classification. RESULT: FLDA distinguished TLE with 76.1% accuracy (85.0% sensitivity, 66.6% specificity) considering frequency of occurrence and percentage of time coverage of microstate C as features. CONCLUSION: Microstate alterations are present in patients with TLE. This feature might be useful in the diagnosis of epilepsy even in the absence of an IED.
PURPOSE: Quasi-stable electrical distribution in EEG called microstates could carry useful information on the dynamics of large scale brain networks. Using machine learning techniques we explored if abnormalities in microstates can identify patients with Temporal Lobe Epilepsy (TLE) in the absence of an interictal discharge (IED). METHOD: 4 Classes of microstates were computed from 2 min artefact free EEG epochs in 42 subjects (21 TLE and 21 controls). The percentage of time coverage, frequency of occurrence and duration for each of these microstates were computed and redundancy reduced using feature selection methods. Subsequently, Fishers Linear Discriminant Analysis (FLDA) and logistic regression were used for classification. RESULT: FLDA distinguished TLE with 76.1% accuracy (85.0% sensitivity, 66.6% specificity) considering frequency of occurrence and percentage of time coverage of microstate C as features. CONCLUSION: Microstate alterations are present in patients with TLE. This feature might be useful in the diagnosis of epilepsy even in the absence of an IED.
Authors: Mustafa Aykut Kural; Jin Jing; Franz Fürbass; Hannes Perko; Erisela Qerama; Birger Johnsen; Steffen Fuchs; M Brandon Westover; Sándor Beniczky Journal: Epilepsia Date: 2022-03-07 Impact factor: 6.740