Design and optimization of an EEG-based brain machine interface (BMI) to an upper-limb exoskeleton for stroke survivors

Nikunj A. Bhagat, Anusha Venkatakrishnan, Berdakh Abibullaev, Edward J. Artz, Nuray Yozbatiran, Amy A. Blank, James French, Christof Karmonik, Robert G. Grossman, Marcia K. O'Malley, Gerard E. Francisco, Jose L. Contreras-Vidal

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

This study demonstrates the feasibility of detecting motor intent from brain activity of chronic stroke patients using an asynchronous electroencephalography (EEG)-based brain machine interface (BMI). Intent was inferred from movement related cortical potentials (MRCPs) measured over an optimized set of EEG electrodes. Successful intent detection triggered the motion of an upper-limb exoskeleton (MAHI Exo-II), to guide movement and to encourage active user participation by providing instantaneous sensory feedback. Several BMI design features were optimized to increase system performance in the presence of single-trial variability of MRCPs in the injured brain: (1) an adaptive time window was used for extracting features during BMI calibration; (2) training data from two consecutive days were pooled for BMI calibration to increase robustness to handle the day-to-day variations typical of EEG, and (3) BMI predictions were gated by residual electromyography (EMG) activity from the impaired arm, to reduce the number of false positives. This patient-specific BMI calibration approach can accommodate a broad spectrum of stroke patients with diverse motor capabilities. Following BMI optimization on day 3, testing of the closed-loop BMI-MAHI exoskeleton, on 4th and 5th days of the study, showed consistent BMI performance with overall mean true positive rate (TPR) = 62.7 ± 21.4% on day 4 and 67.1 ± 14.6% on day 5. The overall false positive rate (FPR) across subjects was 27.74 ± 37.46% on day 4 and 27.5 ± 35.64% on day 5; however for two subjects who had residual motor function and could benefit from the EMG-gated BMI, the mean FPR was quite low (<10%). On average, motor intent was detected -367 ± 328 ms before movement onset during closed-loop operation. These findings provide evidence that closed-loop EEG-based BMI for stroke patients can be designed and optimized to perform well across multiple days without system recalibration.

Original languageEnglish
Article number122
JournalFrontiers in Neuroscience
Volume10
Issue numberMAR
DOIs
Publication statusPublished - Mar 31 2016
Externally publishedYes

Fingerprint

Brain-Computer Interfaces
Upper Extremity
Survivors
Electroencephalography
Stroke
Calibration
Electromyography
Sensory Feedback
Brain
Feasibility Studies
Electrodes
Arm

Keywords

  • Brain machine interface (BMI)
  • Motor intent detection
  • Movement related cortical potentials (MRCPs)
  • Robotic exoskeleton
  • Stroke rehabilitation

ASJC Scopus subject areas

  • Neuroscience(all)

Cite this

Bhagat, N. A., Venkatakrishnan, A., Abibullaev, B., Artz, E. J., Yozbatiran, N., Blank, A. A., ... Contreras-Vidal, J. L. (2016). Design and optimization of an EEG-based brain machine interface (BMI) to an upper-limb exoskeleton for stroke survivors. Frontiers in Neuroscience, 10(MAR), [122]. https://doi.org/10.3389/fnins.2016.00122

Design and optimization of an EEG-based brain machine interface (BMI) to an upper-limb exoskeleton for stroke survivors. / Bhagat, Nikunj A.; Venkatakrishnan, Anusha; Abibullaev, Berdakh; Artz, Edward J.; Yozbatiran, Nuray; Blank, Amy A.; French, James; Karmonik, Christof; Grossman, Robert G.; O'Malley, Marcia K.; Francisco, Gerard E.; Contreras-Vidal, Jose L.

In: Frontiers in Neuroscience, Vol. 10, No. MAR, 122, 31.03.2016.

Research output: Contribution to journalArticle

Bhagat, NA, Venkatakrishnan, A, Abibullaev, B, Artz, EJ, Yozbatiran, N, Blank, AA, French, J, Karmonik, C, Grossman, RG, O'Malley, MK, Francisco, GE & Contreras-Vidal, JL 2016, 'Design and optimization of an EEG-based brain machine interface (BMI) to an upper-limb exoskeleton for stroke survivors', Frontiers in Neuroscience, vol. 10, no. MAR, 122. https://doi.org/10.3389/fnins.2016.00122
Bhagat, Nikunj A. ; Venkatakrishnan, Anusha ; Abibullaev, Berdakh ; Artz, Edward J. ; Yozbatiran, Nuray ; Blank, Amy A. ; French, James ; Karmonik, Christof ; Grossman, Robert G. ; O'Malley, Marcia K. ; Francisco, Gerard E. ; Contreras-Vidal, Jose L. / Design and optimization of an EEG-based brain machine interface (BMI) to an upper-limb exoskeleton for stroke survivors. In: Frontiers in Neuroscience. 2016 ; Vol. 10, No. MAR.
@article{e3b5feeea87e42d8a425168831b7d24a,
title = "Design and optimization of an EEG-based brain machine interface (BMI) to an upper-limb exoskeleton for stroke survivors",
abstract = "This study demonstrates the feasibility of detecting motor intent from brain activity of chronic stroke patients using an asynchronous electroencephalography (EEG)-based brain machine interface (BMI). Intent was inferred from movement related cortical potentials (MRCPs) measured over an optimized set of EEG electrodes. Successful intent detection triggered the motion of an upper-limb exoskeleton (MAHI Exo-II), to guide movement and to encourage active user participation by providing instantaneous sensory feedback. Several BMI design features were optimized to increase system performance in the presence of single-trial variability of MRCPs in the injured brain: (1) an adaptive time window was used for extracting features during BMI calibration; (2) training data from two consecutive days were pooled for BMI calibration to increase robustness to handle the day-to-day variations typical of EEG, and (3) BMI predictions were gated by residual electromyography (EMG) activity from the impaired arm, to reduce the number of false positives. This patient-specific BMI calibration approach can accommodate a broad spectrum of stroke patients with diverse motor capabilities. Following BMI optimization on day 3, testing of the closed-loop BMI-MAHI exoskeleton, on 4th and 5th days of the study, showed consistent BMI performance with overall mean true positive rate (TPR) = 62.7 ± 21.4{\%} on day 4 and 67.1 ± 14.6{\%} on day 5. The overall false positive rate (FPR) across subjects was 27.74 ± 37.46{\%} on day 4 and 27.5 ± 35.64{\%} on day 5; however for two subjects who had residual motor function and could benefit from the EMG-gated BMI, the mean FPR was quite low (<10{\%}). On average, motor intent was detected -367 ± 328 ms before movement onset during closed-loop operation. These findings provide evidence that closed-loop EEG-based BMI for stroke patients can be designed and optimized to perform well across multiple days without system recalibration.",
keywords = "Brain machine interface (BMI), Motor intent detection, Movement related cortical potentials (MRCPs), Robotic exoskeleton, Stroke rehabilitation",
author = "Bhagat, {Nikunj A.} and Anusha Venkatakrishnan and Berdakh Abibullaev and Artz, {Edward J.} and Nuray Yozbatiran and Blank, {Amy A.} and James French and Christof Karmonik and Grossman, {Robert G.} and O'Malley, {Marcia K.} and Francisco, {Gerard E.} and Contreras-Vidal, {Jose L.}",
year = "2016",
month = "3",
day = "31",
doi = "10.3389/fnins.2016.00122",
language = "English",
volume = "10",
journal = "Frontiers in Neuroscience",
issn = "1662-4548",
publisher = "Frontiers Research Foundation",
number = "MAR",

}

TY - JOUR

T1 - Design and optimization of an EEG-based brain machine interface (BMI) to an upper-limb exoskeleton for stroke survivors

AU - Bhagat, Nikunj A.

AU - Venkatakrishnan, Anusha

AU - Abibullaev, Berdakh

AU - Artz, Edward J.

AU - Yozbatiran, Nuray

AU - Blank, Amy A.

AU - French, James

AU - Karmonik, Christof

AU - Grossman, Robert G.

AU - O'Malley, Marcia K.

AU - Francisco, Gerard E.

AU - Contreras-Vidal, Jose L.

PY - 2016/3/31

Y1 - 2016/3/31

N2 - This study demonstrates the feasibility of detecting motor intent from brain activity of chronic stroke patients using an asynchronous electroencephalography (EEG)-based brain machine interface (BMI). Intent was inferred from movement related cortical potentials (MRCPs) measured over an optimized set of EEG electrodes. Successful intent detection triggered the motion of an upper-limb exoskeleton (MAHI Exo-II), to guide movement and to encourage active user participation by providing instantaneous sensory feedback. Several BMI design features were optimized to increase system performance in the presence of single-trial variability of MRCPs in the injured brain: (1) an adaptive time window was used for extracting features during BMI calibration; (2) training data from two consecutive days were pooled for BMI calibration to increase robustness to handle the day-to-day variations typical of EEG, and (3) BMI predictions were gated by residual electromyography (EMG) activity from the impaired arm, to reduce the number of false positives. This patient-specific BMI calibration approach can accommodate a broad spectrum of stroke patients with diverse motor capabilities. Following BMI optimization on day 3, testing of the closed-loop BMI-MAHI exoskeleton, on 4th and 5th days of the study, showed consistent BMI performance with overall mean true positive rate (TPR) = 62.7 ± 21.4% on day 4 and 67.1 ± 14.6% on day 5. The overall false positive rate (FPR) across subjects was 27.74 ± 37.46% on day 4 and 27.5 ± 35.64% on day 5; however for two subjects who had residual motor function and could benefit from the EMG-gated BMI, the mean FPR was quite low (<10%). On average, motor intent was detected -367 ± 328 ms before movement onset during closed-loop operation. These findings provide evidence that closed-loop EEG-based BMI for stroke patients can be designed and optimized to perform well across multiple days without system recalibration.

AB - This study demonstrates the feasibility of detecting motor intent from brain activity of chronic stroke patients using an asynchronous electroencephalography (EEG)-based brain machine interface (BMI). Intent was inferred from movement related cortical potentials (MRCPs) measured over an optimized set of EEG electrodes. Successful intent detection triggered the motion of an upper-limb exoskeleton (MAHI Exo-II), to guide movement and to encourage active user participation by providing instantaneous sensory feedback. Several BMI design features were optimized to increase system performance in the presence of single-trial variability of MRCPs in the injured brain: (1) an adaptive time window was used for extracting features during BMI calibration; (2) training data from two consecutive days were pooled for BMI calibration to increase robustness to handle the day-to-day variations typical of EEG, and (3) BMI predictions were gated by residual electromyography (EMG) activity from the impaired arm, to reduce the number of false positives. This patient-specific BMI calibration approach can accommodate a broad spectrum of stroke patients with diverse motor capabilities. Following BMI optimization on day 3, testing of the closed-loop BMI-MAHI exoskeleton, on 4th and 5th days of the study, showed consistent BMI performance with overall mean true positive rate (TPR) = 62.7 ± 21.4% on day 4 and 67.1 ± 14.6% on day 5. The overall false positive rate (FPR) across subjects was 27.74 ± 37.46% on day 4 and 27.5 ± 35.64% on day 5; however for two subjects who had residual motor function and could benefit from the EMG-gated BMI, the mean FPR was quite low (<10%). On average, motor intent was detected -367 ± 328 ms before movement onset during closed-loop operation. These findings provide evidence that closed-loop EEG-based BMI for stroke patients can be designed and optimized to perform well across multiple days without system recalibration.

KW - Brain machine interface (BMI)

KW - Motor intent detection

KW - Movement related cortical potentials (MRCPs)

KW - Robotic exoskeleton

KW - Stroke rehabilitation

UR - http://www.scopus.com/inward/record.url?scp=84964355686&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964355686&partnerID=8YFLogxK

U2 - 10.3389/fnins.2016.00122

DO - 10.3389/fnins.2016.00122

M3 - Article

VL - 10

JO - Frontiers in Neuroscience

JF - Frontiers in Neuroscience

SN - 1662-4548

IS - MAR

M1 - 122

ER -