Pattern extraction in interictal EEG recordings towards detection of electrodes leading to seizures

Biomed Sci Instrum. 2006;42:243-8.


This study introduces an algorithm for a new application dedicated at discriminating between electrodes leading to a seizure onset and those that do not lead to seizure using interictal subdural EEG data. The significance of this study is in determining among all of these channels, all containing interictal spikes that are asynchronously, independent of region and time, which are selected randomly (these EEG portions may or may not contain spikes), and yet through the developed algorithm, we are able to classify those channels that lead to seizure and those that do not. The main zones of ictal activity are supposed to evolve from the tissue located at the channels that present interictal activity, but sometimes this is no the case. The purpose is to gain a better understanding of the dynamics of the human brain through a study of subdural EEG, with an emphasis on attempting to characterize the common behaviors of interictal EEG channels prior to an ictal activity. The study will try to correlate the clinical features with the EEG findings and to determine whether the patient has a consistent source of ictal activity, which is coming from the location of the group of channels that present interictal activity. If a method was found to detect the electrodes that present interictal activity, with the most potential to lead to an pileptic seizure, then the epilepsy focus could be located with a higher degree of certainty. This analysis allows for the detection of neurological disorders due to epileptic activity in the brain, and rings out how different patients react prior to a seizure.

Publication types

  • Research Support, Non-U.S. Gov't
  • Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

  • Algorithms
  • Artificial Intelligence
  • Brain Mapping / instrumentation*
  • Brain Mapping / methods*
  • Child, Preschool
  • Diagnosis, Computer-Assisted / methods*
  • Electrodes*
  • Electroencephalography / methods*
  • Female
  • Humans
  • Male
  • Pattern Recognition, Automated / methods*
  • Reproducibility of Results
  • Seizures / classification
  • Seizures / diagnosis*
  • Seizures / physiopathology
  • Sensitivity and Specificity