Identifying seizure onset zone from electrocorticographic recordings: A machine learning approach based on phase locking value

Bahareh Elahian, Mohammed Yeasin, Basanagoud Mudigoudar, James Wheless, Abbas Babajani-Feremi

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Purpose Using a novel technique based on phase locking value (PLV), we investigated the potential for features extracted from electrocorticographic (ECoG) recordings to serve as biomarkers to identify the seizure onset zone (SOZ). Methods We computed the PLV between the phase of the amplitude of high gamma activity (80–150 Hz) and the phase of lower frequency rhythms (4–30 Hz) from ECoG recordings obtained from 10 patients with epilepsy (21 seizures). We extracted five features from the PLV and used a machine learning approach based on logistic regression to build a model that classifies electrodes as SOZ or non-SOZ. Results More than 96% of electrodes identified as the SOZ by our algorithm were within the resected area in six seizure-free patients. In four non-seizure-free patients, more than 31% of the identified SOZ electrodes by our algorithm were outside the resected area. In addition, we observed that the seizure outcome in non-seizure-free patients correlated with the number of non-resected SOZ electrodes identified by our algorithm. Conclusion This machine learning approach, based on features extracted from the PLV, effectively identified electrodes within the SOZ. The approach has the potential to assist clinicians in surgical decision-making when pre-surgical intracranial recordings are utilized.

Original languageEnglish (US)
Pages (from-to)35-42
Number of pages8
JournalSeizure
Volume51
DOIs
StatePublished - Oct 1 2017

Fingerprint

Seizures
Electrodes
Machine Learning
Epilepsy
Decision Making
Biomarkers
Logistic Models

All Science Journal Classification (ASJC) codes

  • Neurology
  • Clinical Neurology

Cite this

Identifying seizure onset zone from electrocorticographic recordings : A machine learning approach based on phase locking value. / Elahian, Bahareh; Yeasin, Mohammed; Mudigoudar, Basanagoud; Wheless, James; Babajani-Feremi, Abbas.

In: Seizure, Vol. 51, 01.10.2017, p. 35-42.

Research output: Contribution to journalArticle

@article{34bc3dda550e4bc3929b2138c210a18f,
title = "Identifying seizure onset zone from electrocorticographic recordings: A machine learning approach based on phase locking value",
abstract = "Purpose Using a novel technique based on phase locking value (PLV), we investigated the potential for features extracted from electrocorticographic (ECoG) recordings to serve as biomarkers to identify the seizure onset zone (SOZ). Methods We computed the PLV between the phase of the amplitude of high gamma activity (80–150 Hz) and the phase of lower frequency rhythms (4–30 Hz) from ECoG recordings obtained from 10 patients with epilepsy (21 seizures). We extracted five features from the PLV and used a machine learning approach based on logistic regression to build a model that classifies electrodes as SOZ or non-SOZ. Results More than 96{\%} of electrodes identified as the SOZ by our algorithm were within the resected area in six seizure-free patients. In four non-seizure-free patients, more than 31{\%} of the identified SOZ electrodes by our algorithm were outside the resected area. In addition, we observed that the seizure outcome in non-seizure-free patients correlated with the number of non-resected SOZ electrodes identified by our algorithm. Conclusion This machine learning approach, based on features extracted from the PLV, effectively identified electrodes within the SOZ. The approach has the potential to assist clinicians in surgical decision-making when pre-surgical intracranial recordings are utilized.",
author = "Bahareh Elahian and Mohammed Yeasin and Basanagoud Mudigoudar and James Wheless and Abbas Babajani-Feremi",
year = "2017",
month = "10",
day = "1",
doi = "10.1016/j.seizure.2017.07.010",
language = "English (US)",
volume = "51",
pages = "35--42",
journal = "Seizure : the journal of the British Epilepsy Association",
issn = "1059-1311",
publisher = "W.B. Saunders Ltd",

}

TY - JOUR

T1 - Identifying seizure onset zone from electrocorticographic recordings

T2 - A machine learning approach based on phase locking value

AU - Elahian, Bahareh

AU - Yeasin, Mohammed

AU - Mudigoudar, Basanagoud

AU - Wheless, James

AU - Babajani-Feremi, Abbas

PY - 2017/10/1

Y1 - 2017/10/1

N2 - Purpose Using a novel technique based on phase locking value (PLV), we investigated the potential for features extracted from electrocorticographic (ECoG) recordings to serve as biomarkers to identify the seizure onset zone (SOZ). Methods We computed the PLV between the phase of the amplitude of high gamma activity (80–150 Hz) and the phase of lower frequency rhythms (4–30 Hz) from ECoG recordings obtained from 10 patients with epilepsy (21 seizures). We extracted five features from the PLV and used a machine learning approach based on logistic regression to build a model that classifies electrodes as SOZ or non-SOZ. Results More than 96% of electrodes identified as the SOZ by our algorithm were within the resected area in six seizure-free patients. In four non-seizure-free patients, more than 31% of the identified SOZ electrodes by our algorithm were outside the resected area. In addition, we observed that the seizure outcome in non-seizure-free patients correlated with the number of non-resected SOZ electrodes identified by our algorithm. Conclusion This machine learning approach, based on features extracted from the PLV, effectively identified electrodes within the SOZ. The approach has the potential to assist clinicians in surgical decision-making when pre-surgical intracranial recordings are utilized.

AB - Purpose Using a novel technique based on phase locking value (PLV), we investigated the potential for features extracted from electrocorticographic (ECoG) recordings to serve as biomarkers to identify the seizure onset zone (SOZ). Methods We computed the PLV between the phase of the amplitude of high gamma activity (80–150 Hz) and the phase of lower frequency rhythms (4–30 Hz) from ECoG recordings obtained from 10 patients with epilepsy (21 seizures). We extracted five features from the PLV and used a machine learning approach based on logistic regression to build a model that classifies electrodes as SOZ or non-SOZ. Results More than 96% of electrodes identified as the SOZ by our algorithm were within the resected area in six seizure-free patients. In four non-seizure-free patients, more than 31% of the identified SOZ electrodes by our algorithm were outside the resected area. In addition, we observed that the seizure outcome in non-seizure-free patients correlated with the number of non-resected SOZ electrodes identified by our algorithm. Conclusion This machine learning approach, based on features extracted from the PLV, effectively identified electrodes within the SOZ. The approach has the potential to assist clinicians in surgical decision-making when pre-surgical intracranial recordings are utilized.

UR - http://www.scopus.com/inward/record.url?scp=85026458309&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026458309&partnerID=8YFLogxK

U2 - 10.1016/j.seizure.2017.07.010

DO - 10.1016/j.seizure.2017.07.010

M3 - Article

C2 - 28772200

AN - SCOPUS:85026458309

VL - 51

SP - 35

EP - 42

JO - Seizure : the journal of the British Epilepsy Association

JF - Seizure : the journal of the British Epilepsy Association

SN - 1059-1311

ER -