Automated interictal EEG spike detection using artificial neural networks

Andrew J. Gabor, Masud Seyal

Research output: Contribution to journalArticle

137 Scopus citations

Abstract

Feed-forward, error-back-propagation artificial neural networks were applied to recognition of epileptiform patterns in the EEG. The inherent network properties of generalization and variability tolerance were effective in identifying wave forms that differed from the training patterns but still maintained 'epileptiform' spatio-temporal characteristics. The certainty of recognition was measured as a continuous function with a range of 0-1. Two levels of certainty (0.825 and 0.900) were used to indicate recognition of spikes and sharp waves (SSW). An average 94.2% (± 7.3) of the SSW were recognized; 20.9% (± 22.9) of all recognized SSW were false-positive recognitions. The time required for pattern recognition was well within the time required for digitizing the analogue data. This study provides evidence that neural network technology is, in principle, an effective pattern recognition strategy for identification of epileptiform transients in the EEG. The analysis is sufficiently rapid to be of potential value as a strategy for data reduction of long recordings stored on bulk media.

Original languageEnglish (US)
Pages (from-to)271-280
Number of pages10
JournalElectroencephalography and Clinical Neurophysiology
Volume83
Issue number5
DOIs
StatePublished - 1992

Keywords

  • Neural network
  • Spike detection

ASJC Scopus subject areas

  • Clinical Neurology
  • Neuroscience(all)

Fingerprint Dive into the research topics of 'Automated interictal EEG spike detection using artificial neural networks'. Together they form a unique fingerprint.

  • Cite this