Automated unsupervised behavioral state classification using intracranial electrophysiology

Research output: Contribution to journalArticle

Abstract

Objective. Automated behavioral state classification in intracranial EEG (iEEG) recordings may be beneficial for iEEG interpretation and quantifying sleep patterns to enable behavioral state dependent neuromodulation therapy in next generation implantable brain stimulation devices. Here, we introduce a fully automated unsupervised framework to differentiate between awake (AW), sleep (N2), and slow wave sleep (N3) using intracranial EEG (iEEG) only and validated with expert scored polysomnography. Approach. Data from eight patients undergoing evaluation for epilepsy surgery (age , three female) with intracranial depth electrodes for iEEG monitoring were included. Spectral power features (0.1-235 Hz) spanning several frequency bands from a single electrode were used to classify behavioral states of patients into AW, N2, and N3. Main results. Overall, classification accuracy of 94%, with 94% sensitivity and 93% specificity across eight subjects using multiple spectral power features from a single electrode was achieved. Classification performance of N3 sleep was significantly better (95%, sensitivity 95%, specificity 93%) than that of the N2 sleep phase (87%, sensitivity 78%, specificity 96%). Significance. Automated, unsupervised, and robust classification of behavioral states based on iEEG data is possible, and it is feasible to incorporate these algorithms into future implantable devices with limited computational power, memory, and number of electrodes for brain monitoring and stimulation.

Original languageEnglish (US)
Article number026004
JournalJournal of neural engineering
Volume16
Issue number2
DOIs
StatePublished - Jan 1 2019

Fingerprint

Electrophysiology
Electroencephalography
Sleep
Electrodes
Sensitivity and Specificity
Brain
Equipment and Supplies
Polysomnography
Monitoring
Evoked Potentials
Surgery
Frequency bands
Epilepsy
Electrocorticography
Data storage equipment
Power (Psychology)

Keywords

  • behavioral states
  • classification
  • deep brain stimulation
  • epilepsy
  • intracranial EEG
  • machine learning
  • sleep staging

ASJC Scopus subject areas

  • Biomedical Engineering
  • Cellular and Molecular Neuroscience

Cite this

@article{645263695ffd459ca4f792caada06e5d,
title = "Automated unsupervised behavioral state classification using intracranial electrophysiology",
abstract = "Objective. Automated behavioral state classification in intracranial EEG (iEEG) recordings may be beneficial for iEEG interpretation and quantifying sleep patterns to enable behavioral state dependent neuromodulation therapy in next generation implantable brain stimulation devices. Here, we introduce a fully automated unsupervised framework to differentiate between awake (AW), sleep (N2), and slow wave sleep (N3) using intracranial EEG (iEEG) only and validated with expert scored polysomnography. Approach. Data from eight patients undergoing evaluation for epilepsy surgery (age , three female) with intracranial depth electrodes for iEEG monitoring were included. Spectral power features (0.1-235 Hz) spanning several frequency bands from a single electrode were used to classify behavioral states of patients into AW, N2, and N3. Main results. Overall, classification accuracy of 94{\%}, with 94{\%} sensitivity and 93{\%} specificity across eight subjects using multiple spectral power features from a single electrode was achieved. Classification performance of N3 sleep was significantly better (95{\%}, sensitivity 95{\%}, specificity 93{\%}) than that of the N2 sleep phase (87{\%}, sensitivity 78{\%}, specificity 96{\%}). Significance. Automated, unsupervised, and robust classification of behavioral states based on iEEG data is possible, and it is feasible to incorporate these algorithms into future implantable devices with limited computational power, memory, and number of electrodes for brain monitoring and stimulation.",
keywords = "behavioral states, classification, deep brain stimulation, epilepsy, intracranial EEG, machine learning, sleep staging",
author = "Vaclav Kremen and Benjamin Brinkmann and {Van Gompel}, Jamie and Stead, {Squire Matthew} and {St Louis}, {Erik K} and Worrell, {Gregory Alan}",
year = "2019",
month = "1",
day = "1",
doi = "10.1088/1741-2552/aae5ab",
language = "English (US)",
volume = "16",
journal = "Journal of Neural Engineering",
issn = "1741-2560",
publisher = "IOP Publishing Ltd.",
number = "2",

}

TY - JOUR

T1 - Automated unsupervised behavioral state classification using intracranial electrophysiology

AU - Kremen, Vaclav

AU - Brinkmann, Benjamin

AU - Van Gompel, Jamie

AU - Stead, Squire Matthew

AU - St Louis, Erik K

AU - Worrell, Gregory Alan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Objective. Automated behavioral state classification in intracranial EEG (iEEG) recordings may be beneficial for iEEG interpretation and quantifying sleep patterns to enable behavioral state dependent neuromodulation therapy in next generation implantable brain stimulation devices. Here, we introduce a fully automated unsupervised framework to differentiate between awake (AW), sleep (N2), and slow wave sleep (N3) using intracranial EEG (iEEG) only and validated with expert scored polysomnography. Approach. Data from eight patients undergoing evaluation for epilepsy surgery (age , three female) with intracranial depth electrodes for iEEG monitoring were included. Spectral power features (0.1-235 Hz) spanning several frequency bands from a single electrode were used to classify behavioral states of patients into AW, N2, and N3. Main results. Overall, classification accuracy of 94%, with 94% sensitivity and 93% specificity across eight subjects using multiple spectral power features from a single electrode was achieved. Classification performance of N3 sleep was significantly better (95%, sensitivity 95%, specificity 93%) than that of the N2 sleep phase (87%, sensitivity 78%, specificity 96%). Significance. Automated, unsupervised, and robust classification of behavioral states based on iEEG data is possible, and it is feasible to incorporate these algorithms into future implantable devices with limited computational power, memory, and number of electrodes for brain monitoring and stimulation.

AB - Objective. Automated behavioral state classification in intracranial EEG (iEEG) recordings may be beneficial for iEEG interpretation and quantifying sleep patterns to enable behavioral state dependent neuromodulation therapy in next generation implantable brain stimulation devices. Here, we introduce a fully automated unsupervised framework to differentiate between awake (AW), sleep (N2), and slow wave sleep (N3) using intracranial EEG (iEEG) only and validated with expert scored polysomnography. Approach. Data from eight patients undergoing evaluation for epilepsy surgery (age , three female) with intracranial depth electrodes for iEEG monitoring were included. Spectral power features (0.1-235 Hz) spanning several frequency bands from a single electrode were used to classify behavioral states of patients into AW, N2, and N3. Main results. Overall, classification accuracy of 94%, with 94% sensitivity and 93% specificity across eight subjects using multiple spectral power features from a single electrode was achieved. Classification performance of N3 sleep was significantly better (95%, sensitivity 95%, specificity 93%) than that of the N2 sleep phase (87%, sensitivity 78%, specificity 96%). Significance. Automated, unsupervised, and robust classification of behavioral states based on iEEG data is possible, and it is feasible to incorporate these algorithms into future implantable devices with limited computational power, memory, and number of electrodes for brain monitoring and stimulation.

KW - behavioral states

KW - classification

KW - deep brain stimulation

KW - epilepsy

KW - intracranial EEG

KW - machine learning

KW - sleep staging

UR - http://www.scopus.com/inward/record.url?scp=85062865646&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062865646&partnerID=8YFLogxK

U2 - 10.1088/1741-2552/aae5ab

DO - 10.1088/1741-2552/aae5ab

M3 - Article

VL - 16

JO - Journal of Neural Engineering

JF - Journal of Neural Engineering

SN - 1741-2560

IS - 2

M1 - 026004

ER -