Electrophysiological Biomarkers of Epileptic Tissue in Human Brain Epilepsy

Kamila Lepkova, Petr Nejedly, Vladimir Sladky, Filip Mivalt, Pavel Krsek, Martin Kudr, Matyas Ebel, Petr Marusic, David Krysl, Adam Kalina, Radek Janca, Vaclav Kremen, Gregory A. Worrell

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Objective: Localization and mapping of seizure-generating brain tissue, i.e., seizure onset zone (SOZ) is essential to ensure an excellent patient outcome after surgical resection. The clinical approach is to record spontaneous seizures with intracranial EEG (iEEG) and determine SOZ. However, this practice is burdened by inter-patient variability, temporal variability, time-consuming data annotation, and long and variable waiting period for seizures to happen. Approach: Here, we use data from intracranial monitoring of 28 patients with neocortical focal epilepsy. Kurtosis, complexity, activity, mobility, mean, median, min, max, peak to peak, variance, standard deviation, root mean square, and interquartile were extracted as features from the time domain in two frequency bands (12-55 Hz and 55-80 Hz). The features were extracted from segments of inter-ictal iEEG from 8962 channels and tested by Wilcoxon rank sum test with Bonferroni correction of alpha to compare if mean of the feature differs in SOZ versus non-SOZ in each patient individually. Results: From all features, kurtosis, maximum, minimum, peak to peak, standard deviation, root mean square, variance, interquartile shown consistent differences between SOZ and non-SOZ channels across patients (p<0.0004). Conclusion: We analyzed several iEEG time domain features and we found features that significantly differ for data recorded from SOZ channels in most of the dataset with the same trend across patients. Such features can help to automatically differentiate between SOZ and non-SOZ electrodes and a combination of multiple features can yield better classification performance to discover epileptic foci using inter-ictal data without waiting for seizure to be recorded.

Original languageEnglish (US)
Title of host publication2022 10th E-Health and Bioengineering Conference, EHB 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665485579
StatePublished - 2022
Event10th E-Health and Bioengineering Conference, EHB 2022 - Virtual, Online, Romania
Duration: Nov 17 2022Nov 18 2022

Publication series

Name2022 10th E-Health and Bioengineering Conference, EHB 2022


Conference10th E-Health and Bioengineering Conference, EHB 2022
CityVirtual, Online


  • biomarkers
  • epilepsy
  • feature extraction
  • machine learning
  • neuroscience

ASJC Scopus subject areas

  • Computer Science Applications
  • Biomedical Engineering
  • Health Informatics
  • Health(social science)


Dive into the research topics of 'Electrophysiological Biomarkers of Epileptic Tissue in Human Brain Epilepsy'. Together they form a unique fingerprint.

Cite this