Machine learning detects EEG microstate alterations in patients living with temporal lobe epilepsy

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.

[1]  Abdulhamit Subasi,et al.  EEG signal classification using PCA, ICA, LDA and support vector machines , 2010, Expert Syst. Appl..

[2]  John S. Duncan,et al.  Automated MR image classification in temporal lobe epilepsy , 2012, NeuroImage.

[3]  D Lehmann,et al.  Event-related electric microstates of the brain differ between words with visual and abstract meaning. , 1998, Electroencephalography and clinical neurophysiology.

[4]  Christoph M. Michel,et al.  Deviant dynamics of EEG resting state pattern in 22q11.2 deletion syndrome adolescents: A vulnerability marker of schizophrenia? , 2014, Schizophrenia Research.

[5]  Manouchehr Javidan,et al.  Electroencephalography in Mesial Temporal Lobe Epilepsy: A Review , 2012, Epilepsy research and treatment.

[6]  Tracy Warbrick,et al.  Spontaneous brain activity and EEG microstates. A novel EEG/fMRI analysis approach to explore resting-state networks , 2010, NeuroImage.

[7]  Thomas Dierks,et al.  Native EEG and treatment effects in neuroleptic-naïve schizophrenic patients: Time and frequency domain approaches , 2007, Schizophrenia Research.

[8]  D. Hubl,et al.  Brain connectivity at different time-scales measured with EEG , 2005, Philosophical Transactions of the Royal Society B: Biological Sciences.

[9]  R. D. Pascual-Marqui,et al.  The EEG microstate topography is predominantly determined by intracortical sources in the alpha band , 2017, NeuroImage.

[10]  Á. Pascual-Leone,et al.  Microstates in resting-state EEG: Current status and future directions , 2015, Neuroscience & Biobehavioral Reviews.

[11]  Dietrich Lehmann,et al.  Millisecond by Millisecond, Year by Year: Normative EEG Microstates and Developmental Stages , 2002, NeuroImage.

[12]  D. Lehmann,et al.  Segmentation of brain electrical activity into microstates: model estimation and validation , 1995, IEEE Transactions on Biomedical Engineering.

[13]  J. Gotman.  Automatic recognition of epileptic seizures in the EEG. , 1982, Electroencephalography and clinical neurophysiology.

[14]  Dietrich Lehmann,et al.  The functional significance of EEG microstates—Associations with modalities of thinking , 2016, NeuroImage.

[15]  Dietrich Lehmann,et al.  Resting-state connectivity in the prodromal phase of schizophrenia: Insights from EEG microstates , 2014, Schizophrenia Research.

[16]  Thomas Dierks,et al.  A pharmaco-EEG study on antipsychotic drugs in healthy volunteers , 2007, Psychopharmacology.

[17]  T. Santner,et al.  On the small sample properties of norm-restricted maximum likelihood estimators for logistic regression models , 1989 .

[18]  Thomas Dierks,et al.  EEG microstates associated with salience and frontoparietal networks in frontotemporal dementia, schizophrenia and Alzheimer’s disease , 2013, Clinical Neurophysiology.

[19]  M. Salinsky,et al.  Effectiveness of Multiple EEGs in Supporting the Diagnosis of Epilepsy: An Operational Curve , 1987, Epilepsia.

[20]  J. Pyrzowski,et al.  Interval analysis of interictal EEG: pathology of the alpha rhythm in focal epilepsy , 2015, Scientific Reports.

[21]  Louis Lemieux,et al.  Identification of EEG Events in the MR Scanner: The Problem of Pulse Artifact and a Method for Its Subtraction , 1998, NeuroImage.

[22]  K. Maurer,et al.  EEG-microstates in mild memory impairment and Alzheimer's disease: possible association with disturbed information processing , 2005, Journal of Neural Transmission.

[23]  D Lehmann,et al.  EEG alpha map series: brain micro-states by space-oriented adaptive segmentation. , 1987, Electroencephalography and clinical neurophysiology.

[24]  T. Koenig,et al.  EEG microstate duration and syntax in acute, medication-naïve, first-episode schizophrenia: a multi-center study , 2005, Psychiatry Research: Neuroimaging.

[25]  Dietrich Lehmann,et al.  Multimodal analysis of resting state cortical activity: What does fMRI add to our knowledge of microstates in resting state EEG activity? Commentary to the papers by Britz et al. and Musso et al. in the current issue of NeuroImage , 2010, NeuroImage.

[26]  R. Schaefer,et al.  A ridge logistic estimator , 1984 .

[27]  Abdul Rahman Othman,et al.  A Model Classification Technique for Linear Discriminant Analysis for Two Groups , 2012 .

[28]  Eugen Trinka,et al.  Automated diagnosis of temporal lobe epilepsy in the absence of interictal spikes , 2017, NeuroImage: Clinical.

[29]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[30]  Dietrich Lehmann,et al.  A deviant EEG brain microstate in acute, neuroleptic-naive schizophrenics at rest , 1999, European Archives of Psychiatry and Clinical Neuroscience.

[31]  Graeme Jackson,et al.  The peri-ictal state: cortical excitability changes within 24 h of a seizure. , 2009, Brain : a journal of neurology.

[32]  Terry M. Peters,et al.  Detection of temporal lobe epilepsy using support vector machines in multi-parametric quantitative MR imaging , 2015, Comput. Medical Imaging Graph..

[33]  Dimitri Van De Ville,et al.  BOLD correlates of EEG topography reveal rapid resting-state network dynamics , 2010, NeuroImage.

[34]  Thomas Dierks,et al.  EEG Microstate Analysis in Drug-Naive Patients with Panic Disorder , 2011, PloS one.

[35]  Julius Georgiou,et al.  Detection of epileptic electroencephalogram based on Permutation Entropy and Support Vector Machines , 2012, Expert Syst. Appl..

[36]  S. Cessie,et al.  Ridge Estimators in Logistic Regression , 1992 .

[37]  P. Simon.  Too Big to Ignore: The Business Case for Big Data , 2013 .

[38]  U. Rajendra Acharya,et al.  EEG Signal Analysis: A Survey , 2010, Journal of Medical Systems.

[39]  A STOLLER,et al.  Slowing of the alpha-rhythm of the electroencephalogram and its association with mental deterioration and epilepsy. , 1949, The Journal of mental science.