Unsupervised machine-learning classification of electrophysiologically active electrodes during human cognitive task performance

Krishnakant V. Saboo, Yogatheesan Varatharajah, Brent M. Berry, Vaclav Kremen, Michael R. Sperling, Kathryn A. Davis, Barbara C. Jobst, Robert E. Gross, Bradley Lega, Sameer A. Sheth, Gregory A. Worrell, Ravishankar K. Iyer, Michal T. Kucewicz

Research output: Contribution to journalArticle

Abstract

Identification of active electrodes that record task-relevant neurophysiological activity is needed for clinical and industrial applications as well as for investigating brain functions. We developed an unsupervised, fully automated approach to classify active electrodes showing event-related intracranial EEG (iEEG) responses from 115 patients performing a free recall verbal memory task. Our approach employed new interpretable metrics that quantify spectral characteristics of the normalized iEEG signal based on power-in-band and synchrony measures. Unsupervised clustering of the metrics identified distinct sets of active electrodes across different subjects. In the total population of 11,869 electrodes, our method achieved 97% sensitivity and 92.9% specificity with the most efficient metric. We validated our results with anatomical localization revealing significantly greater distribution of active electrodes in brain regions that support verbal memory processing. We propose our machine-learning framework for objective and efficient classification and interpretation of electrophysiological signals of brain activities supporting memory and cognition.

Original languageEnglish (US)
Article number17390
JournalScientific reports
Volume9
Issue number1
DOIs
StatePublished - Dec 1 2019

Fingerprint

Task Performance and Analysis
Electrodes
Brain
Cognition
Cluster Analysis
Unsupervised Machine Learning
Sensitivity and Specificity
Population
Electrocorticography

ASJC Scopus subject areas

  • General

Cite this

Saboo, K. V., Varatharajah, Y., Berry, B. M., Kremen, V., Sperling, M. R., Davis, K. A., ... Kucewicz, M. T. (2019). Unsupervised machine-learning classification of electrophysiologically active electrodes during human cognitive task performance. Scientific reports, 9(1), [17390]. https://doi.org/10.1038/s41598-019-53925-5

Unsupervised machine-learning classification of electrophysiologically active electrodes during human cognitive task performance. / Saboo, Krishnakant V.; Varatharajah, Yogatheesan; Berry, Brent M.; Kremen, Vaclav; Sperling, Michael R.; Davis, Kathryn A.; Jobst, Barbara C.; Gross, Robert E.; Lega, Bradley; Sheth, Sameer A.; Worrell, Gregory A.; Iyer, Ravishankar K.; Kucewicz, Michal T.

In: Scientific reports, Vol. 9, No. 1, 17390, 01.12.2019.

Research output: Contribution to journalArticle

Saboo, KV, Varatharajah, Y, Berry, BM, Kremen, V, Sperling, MR, Davis, KA, Jobst, BC, Gross, RE, Lega, B, Sheth, SA, Worrell, GA, Iyer, RK & Kucewicz, MT 2019, 'Unsupervised machine-learning classification of electrophysiologically active electrodes during human cognitive task performance', Scientific reports, vol. 9, no. 1, 17390. https://doi.org/10.1038/s41598-019-53925-5
Saboo, Krishnakant V. ; Varatharajah, Yogatheesan ; Berry, Brent M. ; Kremen, Vaclav ; Sperling, Michael R. ; Davis, Kathryn A. ; Jobst, Barbara C. ; Gross, Robert E. ; Lega, Bradley ; Sheth, Sameer A. ; Worrell, Gregory A. ; Iyer, Ravishankar K. ; Kucewicz, Michal T. / Unsupervised machine-learning classification of electrophysiologically active electrodes during human cognitive task performance. In: Scientific reports. 2019 ; Vol. 9, No. 1.
@article{2d9254285cf64708bdce4d91a9978400,
title = "Unsupervised machine-learning classification of electrophysiologically active electrodes during human cognitive task performance",
abstract = "Identification of active electrodes that record task-relevant neurophysiological activity is needed for clinical and industrial applications as well as for investigating brain functions. We developed an unsupervised, fully automated approach to classify active electrodes showing event-related intracranial EEG (iEEG) responses from 115 patients performing a free recall verbal memory task. Our approach employed new interpretable metrics that quantify spectral characteristics of the normalized iEEG signal based on power-in-band and synchrony measures. Unsupervised clustering of the metrics identified distinct sets of active electrodes across different subjects. In the total population of 11,869 electrodes, our method achieved 97{\%} sensitivity and 92.9{\%} specificity with the most efficient metric. We validated our results with anatomical localization revealing significantly greater distribution of active electrodes in brain regions that support verbal memory processing. We propose our machine-learning framework for objective and efficient classification and interpretation of electrophysiological signals of brain activities supporting memory and cognition.",
author = "Saboo, {Krishnakant V.} and Yogatheesan Varatharajah and Berry, {Brent M.} and Vaclav Kremen and Sperling, {Michael R.} and Davis, {Kathryn A.} and Jobst, {Barbara C.} and Gross, {Robert E.} and Bradley Lega and Sheth, {Sameer A.} and Worrell, {Gregory A.} and Iyer, {Ravishankar K.} and Kucewicz, {Michal T.}",
year = "2019",
month = "12",
day = "1",
doi = "10.1038/s41598-019-53925-5",
language = "English (US)",
volume = "9",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Unsupervised machine-learning classification of electrophysiologically active electrodes during human cognitive task performance

AU - Saboo, Krishnakant V.

AU - Varatharajah, Yogatheesan

AU - Berry, Brent M.

AU - Kremen, Vaclav

AU - Sperling, Michael R.

AU - Davis, Kathryn A.

AU - Jobst, Barbara C.

AU - Gross, Robert E.

AU - Lega, Bradley

AU - Sheth, Sameer A.

AU - Worrell, Gregory A.

AU - Iyer, Ravishankar K.

AU - Kucewicz, Michal T.

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Identification of active electrodes that record task-relevant neurophysiological activity is needed for clinical and industrial applications as well as for investigating brain functions. We developed an unsupervised, fully automated approach to classify active electrodes showing event-related intracranial EEG (iEEG) responses from 115 patients performing a free recall verbal memory task. Our approach employed new interpretable metrics that quantify spectral characteristics of the normalized iEEG signal based on power-in-band and synchrony measures. Unsupervised clustering of the metrics identified distinct sets of active electrodes across different subjects. In the total population of 11,869 electrodes, our method achieved 97% sensitivity and 92.9% specificity with the most efficient metric. We validated our results with anatomical localization revealing significantly greater distribution of active electrodes in brain regions that support verbal memory processing. We propose our machine-learning framework for objective and efficient classification and interpretation of electrophysiological signals of brain activities supporting memory and cognition.

AB - Identification of active electrodes that record task-relevant neurophysiological activity is needed for clinical and industrial applications as well as for investigating brain functions. We developed an unsupervised, fully automated approach to classify active electrodes showing event-related intracranial EEG (iEEG) responses from 115 patients performing a free recall verbal memory task. Our approach employed new interpretable metrics that quantify spectral characteristics of the normalized iEEG signal based on power-in-band and synchrony measures. Unsupervised clustering of the metrics identified distinct sets of active electrodes across different subjects. In the total population of 11,869 electrodes, our method achieved 97% sensitivity and 92.9% specificity with the most efficient metric. We validated our results with anatomical localization revealing significantly greater distribution of active electrodes in brain regions that support verbal memory processing. We propose our machine-learning framework for objective and efficient classification and interpretation of electrophysiological signals of brain activities supporting memory and cognition.

UR - http://www.scopus.com/inward/record.url?scp=85075503697&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075503697&partnerID=8YFLogxK

U2 - 10.1038/s41598-019-53925-5

DO - 10.1038/s41598-019-53925-5

M3 - Article

C2 - 31758077

AN - SCOPUS:85075503697

VL - 9

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 17390

ER -