Quantification of the impact of vagus nerve stimulation parameters on electroencephalographic measures

Michael Bewernitz, Georges Ghacibeh, Onur Seref, Panos M. Pardalos, Chang Chia Liu, Basim Uthman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This study presents an application of support vector machines (S VMs) to the analysis of electroencephalograms (EEG) obtained from the scalp of patients with epilepsy implanted with the vagus nerve stimulator (VNS) used in VNS Therapy®. The purpose of this study is to devise a physiologic marker using scalp EEG for determining optimal VNS parameters. Scalp EEG recordings were obtained from six patients with history of intractable partial onset epilepsy treated with VNS as adjunctive therapy to medicines. Averaged scalp EEG samples were used as features for separation. SVM classification accuracy was used as a measure of EEG similarity to separate a time segment during the beginning of stimulation from all the successive non-overlapping time segments within a full VNS on/off cycle. This analysis was performed for all the automated VNS cycles occurring during approximately twenty-four hours of 25 channels of scalp EEG. The patient that resulted in the lowest degree of EEG pattern similarity had the highest VNS stimulation frequency and experienced a monthly seizure rate among the lowest of all six patients included in this study. The patient with the greatest degree of pattern similarity had the lowest VNS stimulation frequency, shortest VNS pulse width, and experienced the greatest monthly seizure rate of all six patients included in this study. It is possible that VNS exerts its therapeutic effect by mimicking a theorized seizure effect for which a seizure has been observed to "reset" the brain from an unfavorable preictal state to a more favorable interictal state. These encouraging results suggest that data mining tools may be able to extract EEG patterns which could be used as an electrographic marker of optimal VNS stimulation parameters.

Original languageEnglish (US)
Title of host publicationAIP Conference Proceedings
Pages206-219
Number of pages14
Volume953
DOIs
StatePublished - 2007
Externally publishedYes
EventConference on Data Mining, Systems Analysis, and Optimization in Biomedicine, 2007 - Gainesville, FL, United States
Duration: Mar 28 2007Mar 30 2007

Other

OtherConference on Data Mining, Systems Analysis, and Optimization in Biomedicine, 2007
CountryUnited States
CityGainesville, FL
Period3/28/073/30/07

Fingerprint

nerves
stimulation
electroencephalography
seizures
epilepsy
markers
therapy
data mining
cycles
medicine
brain
pulse duration
recording
histories

Keywords

  • Data mining
  • Epilepsy
  • Quantitative EEG analysis
  • Support vector machine
  • Vagus nerve stimulation

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Cite this

Bewernitz, M., Ghacibeh, G., Seref, O., Pardalos, P. M., Liu, C. C., & Uthman, B. (2007). Quantification of the impact of vagus nerve stimulation parameters on electroencephalographic measures. In AIP Conference Proceedings (Vol. 953, pp. 206-219) https://doi.org/10.1063/1.2817344

Quantification of the impact of vagus nerve stimulation parameters on electroencephalographic measures. / Bewernitz, Michael; Ghacibeh, Georges; Seref, Onur; Pardalos, Panos M.; Liu, Chang Chia; Uthman, Basim.

AIP Conference Proceedings. Vol. 953 2007. p. 206-219.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bewernitz, M, Ghacibeh, G, Seref, O, Pardalos, PM, Liu, CC & Uthman, B 2007, Quantification of the impact of vagus nerve stimulation parameters on electroencephalographic measures. in AIP Conference Proceedings. vol. 953, pp. 206-219, Conference on Data Mining, Systems Analysis, and Optimization in Biomedicine, 2007, Gainesville, FL, United States, 3/28/07. https://doi.org/10.1063/1.2817344
Bewernitz M, Ghacibeh G, Seref O, Pardalos PM, Liu CC, Uthman B. Quantification of the impact of vagus nerve stimulation parameters on electroencephalographic measures. In AIP Conference Proceedings. Vol. 953. 2007. p. 206-219 https://doi.org/10.1063/1.2817344
Bewernitz, Michael ; Ghacibeh, Georges ; Seref, Onur ; Pardalos, Panos M. ; Liu, Chang Chia ; Uthman, Basim. / Quantification of the impact of vagus nerve stimulation parameters on electroencephalographic measures. AIP Conference Proceedings. Vol. 953 2007. pp. 206-219
@inproceedings{9efa735f584542b19608c6e6a211a5e9,
title = "Quantification of the impact of vagus nerve stimulation parameters on electroencephalographic measures",
abstract = "This study presents an application of support vector machines (S VMs) to the analysis of electroencephalograms (EEG) obtained from the scalp of patients with epilepsy implanted with the vagus nerve stimulator (VNS) used in VNS Therapy{\circledR}. The purpose of this study is to devise a physiologic marker using scalp EEG for determining optimal VNS parameters. Scalp EEG recordings were obtained from six patients with history of intractable partial onset epilepsy treated with VNS as adjunctive therapy to medicines. Averaged scalp EEG samples were used as features for separation. SVM classification accuracy was used as a measure of EEG similarity to separate a time segment during the beginning of stimulation from all the successive non-overlapping time segments within a full VNS on/off cycle. This analysis was performed for all the automated VNS cycles occurring during approximately twenty-four hours of 25 channels of scalp EEG. The patient that resulted in the lowest degree of EEG pattern similarity had the highest VNS stimulation frequency and experienced a monthly seizure rate among the lowest of all six patients included in this study. The patient with the greatest degree of pattern similarity had the lowest VNS stimulation frequency, shortest VNS pulse width, and experienced the greatest monthly seizure rate of all six patients included in this study. It is possible that VNS exerts its therapeutic effect by mimicking a theorized seizure effect for which a seizure has been observed to {"}reset{"} the brain from an unfavorable preictal state to a more favorable interictal state. These encouraging results suggest that data mining tools may be able to extract EEG patterns which could be used as an electrographic marker of optimal VNS stimulation parameters.",
keywords = "Data mining, Epilepsy, Quantitative EEG analysis, Support vector machine, Vagus nerve stimulation",
author = "Michael Bewernitz and Georges Ghacibeh and Onur Seref and Pardalos, {Panos M.} and Liu, {Chang Chia} and Basim Uthman",
year = "2007",
doi = "10.1063/1.2817344",
language = "English (US)",
isbn = "9780735404670",
volume = "953",
pages = "206--219",
booktitle = "AIP Conference Proceedings",

}

TY - GEN

T1 - Quantification of the impact of vagus nerve stimulation parameters on electroencephalographic measures

AU - Bewernitz, Michael

AU - Ghacibeh, Georges

AU - Seref, Onur

AU - Pardalos, Panos M.

AU - Liu, Chang Chia

AU - Uthman, Basim

PY - 2007

Y1 - 2007

N2 - This study presents an application of support vector machines (S VMs) to the analysis of electroencephalograms (EEG) obtained from the scalp of patients with epilepsy implanted with the vagus nerve stimulator (VNS) used in VNS Therapy®. The purpose of this study is to devise a physiologic marker using scalp EEG for determining optimal VNS parameters. Scalp EEG recordings were obtained from six patients with history of intractable partial onset epilepsy treated with VNS as adjunctive therapy to medicines. Averaged scalp EEG samples were used as features for separation. SVM classification accuracy was used as a measure of EEG similarity to separate a time segment during the beginning of stimulation from all the successive non-overlapping time segments within a full VNS on/off cycle. This analysis was performed for all the automated VNS cycles occurring during approximately twenty-four hours of 25 channels of scalp EEG. The patient that resulted in the lowest degree of EEG pattern similarity had the highest VNS stimulation frequency and experienced a monthly seizure rate among the lowest of all six patients included in this study. The patient with the greatest degree of pattern similarity had the lowest VNS stimulation frequency, shortest VNS pulse width, and experienced the greatest monthly seizure rate of all six patients included in this study. It is possible that VNS exerts its therapeutic effect by mimicking a theorized seizure effect for which a seizure has been observed to "reset" the brain from an unfavorable preictal state to a more favorable interictal state. These encouraging results suggest that data mining tools may be able to extract EEG patterns which could be used as an electrographic marker of optimal VNS stimulation parameters.

AB - This study presents an application of support vector machines (S VMs) to the analysis of electroencephalograms (EEG) obtained from the scalp of patients with epilepsy implanted with the vagus nerve stimulator (VNS) used in VNS Therapy®. The purpose of this study is to devise a physiologic marker using scalp EEG for determining optimal VNS parameters. Scalp EEG recordings were obtained from six patients with history of intractable partial onset epilepsy treated with VNS as adjunctive therapy to medicines. Averaged scalp EEG samples were used as features for separation. SVM classification accuracy was used as a measure of EEG similarity to separate a time segment during the beginning of stimulation from all the successive non-overlapping time segments within a full VNS on/off cycle. This analysis was performed for all the automated VNS cycles occurring during approximately twenty-four hours of 25 channels of scalp EEG. The patient that resulted in the lowest degree of EEG pattern similarity had the highest VNS stimulation frequency and experienced a monthly seizure rate among the lowest of all six patients included in this study. The patient with the greatest degree of pattern similarity had the lowest VNS stimulation frequency, shortest VNS pulse width, and experienced the greatest monthly seizure rate of all six patients included in this study. It is possible that VNS exerts its therapeutic effect by mimicking a theorized seizure effect for which a seizure has been observed to "reset" the brain from an unfavorable preictal state to a more favorable interictal state. These encouraging results suggest that data mining tools may be able to extract EEG patterns which could be used as an electrographic marker of optimal VNS stimulation parameters.

KW - Data mining

KW - Epilepsy

KW - Quantitative EEG analysis

KW - Support vector machine

KW - Vagus nerve stimulation

UR - http://www.scopus.com/inward/record.url?scp=71449118662&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71449118662&partnerID=8YFLogxK

U2 - 10.1063/1.2817344

DO - 10.1063/1.2817344

M3 - Conference contribution

AN - SCOPUS:71449118662

SN - 9780735404670

VL - 953

SP - 206

EP - 219

BT - AIP Conference Proceedings

ER -