Localizing epileptogenic regions using high-frequency oscillations and machine learning

Shennan A. Weiss; Zachary Waldman; Federico Raimondo; Diego Slezak; Mustafa Donmez; Gregory Worrell; Anatol Bragin; Jerome Engel; Richard Staba; Michael Sperling

doi:10.2217/bmm-2018-0335

Localizing epileptogenic regions using high-frequency oscillations and machine learning

Shennan A. Weiss, Zachary Waldman, Federico Raimondo, Diego Slezak, Mustafa Donmez, Gregory Worrell, Anatol Bragin, Jerome Engel, Richard Staba, Michael Sperling

Neurology

Research output: Contribution to journal › Review article › peer-review

4 Scopus citations

Abstract

Pathological high frequency oscillations (HFOs) are putative neurophysiological biomarkers of epileptogenic brain tissue. Utilizing HFOs for epilepsy surgery planning offers the promise of improved seizure outcomes for patients with medically refractory epilepsy. This review discusses possible machine learning strategies that can be applied to HFO biomarkers to better identify epileptogenic regions. We discuss the role of HFO rate, and utilizing features such as explicit HFO properties (spectral content, duration, and power) and phase-amplitude coupling for distinguishing pathological HFO (pHFO) events from physiological HFO events. In addition, the review highlights the importance of neuroanatomical localization in machine learning strategies.

Original language	English (US)
Pages (from-to)	409-418
Number of pages	10
Journal	Biomarkers in Medicine
Volume	13
Issue number	5
DOIs	https://doi.org/10.2217/bmm-2018-0335
State	Published - Apr 2019

Keywords

HFO
artificial intelligence
epilepsy
epilepsy surgery
epileptiform spike
fast ripple
high-frequency oscillation
machine learning
phase-amplitude coupling
ripple
seizure
wavelet

ASJC Scopus subject areas

Drug Discovery
Clinical Biochemistry
Biochemistry, medical

Access to Document

10.2217/bmm-2018-0335

Cite this

@article{bfd129754a054f4bb48feb4789909c60,

title = "Localizing epileptogenic regions using high-frequency oscillations and machine learning",

abstract = "Pathological high frequency oscillations (HFOs) are putative neurophysiological biomarkers of epileptogenic brain tissue. Utilizing HFOs for epilepsy surgery planning offers the promise of improved seizure outcomes for patients with medically refractory epilepsy. This review discusses possible machine learning strategies that can be applied to HFO biomarkers to better identify epileptogenic regions. We discuss the role of HFO rate, and utilizing features such as explicit HFO properties (spectral content, duration, and power) and phase-amplitude coupling for distinguishing pathological HFO (pHFO) events from physiological HFO events. In addition, the review highlights the importance of neuroanatomical localization in machine learning strategies.",

keywords = "HFO, artificial intelligence, epilepsy, epilepsy surgery, epileptiform spike, fast ripple, high-frequency oscillation, machine learning, phase-amplitude coupling, ripple, seizure, wavelet",

author = "Weiss, {Shennan A.} and Zachary Waldman and Federico Raimondo and Diego Slezak and Mustafa Donmez and Gregory Worrell and Anatol Bragin and Jerome Engel and Richard Staba and Michael Sperling",

note = "Publisher Copyright: {\textcopyright} 2019 Future Medicine Ltd.",

year = "2019",

month = apr,

doi = "10.2217/bmm-2018-0335",

language = "English (US)",

volume = "13",

pages = "409--418",

journal = "Biomarkers in Medicine",

issn = "1752-0363",

publisher = "Future Medicine Ltd.",

number = "5",

}

TY - JOUR

T1 - Localizing epileptogenic regions using high-frequency oscillations and machine learning

AU - Weiss, Shennan A.

AU - Waldman, Zachary

AU - Raimondo, Federico

AU - Slezak, Diego

AU - Donmez, Mustafa

AU - Worrell, Gregory

AU - Bragin, Anatol

AU - Engel, Jerome

AU - Staba, Richard

AU - Sperling, Michael

PY - 2019/4

Y1 - 2019/4

N2 - Pathological high frequency oscillations (HFOs) are putative neurophysiological biomarkers of epileptogenic brain tissue. Utilizing HFOs for epilepsy surgery planning offers the promise of improved seizure outcomes for patients with medically refractory epilepsy. This review discusses possible machine learning strategies that can be applied to HFO biomarkers to better identify epileptogenic regions. We discuss the role of HFO rate, and utilizing features such as explicit HFO properties (spectral content, duration, and power) and phase-amplitude coupling for distinguishing pathological HFO (pHFO) events from physiological HFO events. In addition, the review highlights the importance of neuroanatomical localization in machine learning strategies.

AB - Pathological high frequency oscillations (HFOs) are putative neurophysiological biomarkers of epileptogenic brain tissue. Utilizing HFOs for epilepsy surgery planning offers the promise of improved seizure outcomes for patients with medically refractory epilepsy. This review discusses possible machine learning strategies that can be applied to HFO biomarkers to better identify epileptogenic regions. We discuss the role of HFO rate, and utilizing features such as explicit HFO properties (spectral content, duration, and power) and phase-amplitude coupling for distinguishing pathological HFO (pHFO) events from physiological HFO events. In addition, the review highlights the importance of neuroanatomical localization in machine learning strategies.

KW - HFO

KW - artificial intelligence

KW - epilepsy

KW - epilepsy surgery

KW - epileptiform spike

KW - fast ripple

KW - high-frequency oscillation

KW - machine learning

KW - phase-amplitude coupling

KW - ripple

KW - seizure

KW - wavelet

UR - http://www.scopus.com/inward/record.url?scp=85066836557&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066836557&partnerID=8YFLogxK

U2 - 10.2217/bmm-2018-0335

DO - 10.2217/bmm-2018-0335

M3 - Review article

C2 - 31044598

AN - SCOPUS:85066836557

SN - 1752-0363

VL - 13

SP - 409

EP - 418

JO - Biomarkers in Medicine

JF - Biomarkers in Medicine

IS - 5

ER -

Localizing epileptogenic regions using high-frequency oscillations and machine learning

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this