Modulated high frequency oscillations can identify regions of interest in human iEEG using hidden Markov models

Mirna Guirgis,Yotin Chinvarun,Peter L Carlen,Berj L Bardakjian,Martin Del Campo

doi:10.1109/ner.2015.7146777

Modulated high frequency oscillations can identify regions of interest in human iEEG using hidden Markov models

Mirna Guirgis, Yotin Chinvarun + Show 3 more

https://doi.org/10.1109/ner.2015.7146777

Copy DOI

Publication Date: Apr 1, 2015

Citations: 10

Affiliation: University of Toronto, Phramongkutklao Hospital, University Health Network

#Hidden Markov Models #Unsupervised Learning Algorithm + Show 8 more

Abstract
Full-Text PDF
Similar Papers

Abstract

This study investigated the seizure and non-seizure state transitions in the intracranial electroencephalogram (iEEG) recordings of extratemporal lobe epilepsy patients. Cross-frequency coupling between low and high frequency oscillations in conjunction with an unsupervised learning algorithm - namely, hidden Markov models - was used to objectively identify seizure and non-seizure states as well as transition states. Channels consistently capturing two and/or three distinct states in a 32-channel iEEG array were able to identify regions of interest located in resected tissue of patients who experienced improved post-surgical outcomes.

Full Text