The influence of central neuropathic pain in paraplegic patients on performance of a motor imagery based brain computer interface

A. Vuckovic, M.A. Hasan, B. Osuagwu, M. Fraser, D.B. Allan, B.A. Conway, B. Nasseroleslami

Research output: Contribution to journalArticle

  • 3 Citations

Abstract

The aim of this study was to test how the presence of central neuropathic pain (CNP) influences the performance of a motor imagery based Brain Computer Interface (BCI). In this electroencephalography (EEG) based study, we tested BCI classification accuracy and analysed event related desynchronisation (ERD) in 3 groups of volunteers during imagined movements of their arms and legs. The groups comprised of nine able-bodied people, ten paraplegic patients with CNP (lower abdomen and legs) and nine paraplegic patients without CNP. We tested two types of classifiers: a 3 channel bipolar montage and classifiers based on common spatial patterns (CSPs), with varying number of channels and CSPs. Paraplegic patients with CNP achieved higher classification accuracy and had stronger ERD than paraplegic patients with no pain for all classifier configurations. Highest 2-class classification accuracy was achieved for CSP classifier covering wider cortical area: 82 ± 7% for patients with CNP, 82 ± 4% for able-bodied and 78 ± 5% for patients with no pain. Presence of CNP improves BCI classification accuracy due to stronger and more distinct ERD. Results of the study show that CNP is an important confounding factor influencing the performance of motor imagery based BCI based on ERD.
LanguageEnglish
Pages2170-2180
Number of pages11
JournalClinical Neurophysiology
Volume126
Issue number11
Early online date30 Jan 2015
DOIs
StatePublished - 1 Nov 2015

Fingerprint

Brain-Computer Interfaces
Imagery (Psychotherapy)
Neuralgia
Leg
Pain
Abdomen
Electroencephalography
Volunteers
Arm

Keywords

  • EEG
  • motor imagery
  • paraplegia
  • central neuropathic pain
  • event related synchronisation/desynchronisation

Cite this

Vuckovic, A. ; Hasan, M.A. ; Osuagwu, B. ; Fraser, M. ; Allan, D.B. ; Conway, B.A. ; Nasseroleslami, B./ The influence of central neuropathic pain in paraplegic patients on performance of a motor imagery based brain computer interface. In: Clinical Neurophysiology. 2015 ; Vol. 126, No. 11. pp. 2170-2180
@article{00a3172ccffe462dafb94665035c4fb3,
title = "The influence of central neuropathic pain in paraplegic patients on performance of a motor imagery based brain computer interface",
abstract = "The aim of this study was to test how the presence of central neuropathic pain (CNP) influences the performance of a motor imagery based Brain Computer Interface (BCI). In this electroencephalography (EEG) based study, we tested BCI classification accuracy and analysed event related desynchronisation (ERD) in 3 groups of volunteers during imagined movements of their arms and legs. The groups comprised of nine able-bodied people, ten paraplegic patients with CNP (lower abdomen and legs) and nine paraplegic patients without CNP. We tested two types of classifiers: a 3 channel bipolar montage and classifiers based on common spatial patterns (CSPs), with varying number of channels and CSPs. Paraplegic patients with CNP achieved higher classification accuracy and had stronger ERD than paraplegic patients with no pain for all classifier configurations. Highest 2-class classification accuracy was achieved for CSP classifier covering wider cortical area: 82 ± 7{\%} for patients with CNP, 82 ± 4{\%} for able-bodied and 78 ± 5{\%} for patients with no pain. Presence of CNP improves BCI classification accuracy due to stronger and more distinct ERD. Results of the study show that CNP is an important confounding factor influencing the performance of motor imagery based BCI based on ERD.",
keywords = "EEG, motor imagery, paraplegia, central neuropathic pain, event related synchronisation/desynchronisation",
author = "A. Vuckovic and M.A. Hasan and B. Osuagwu and M. Fraser and D.B. Allan and B.A. Conway and B. Nasseroleslami",
year = "2015",
month = "11",
day = "1",
doi = "10.1016/j.clinph.2014.12.033",
language = "English",
volume = "126",
pages = "2170--2180",
journal = "Clinical Neurophysiology",
issn = "1388-2457",
number = "11",

}

The influence of central neuropathic pain in paraplegic patients on performance of a motor imagery based brain computer interface. / Vuckovic, A.; Hasan, M.A.; Osuagwu, B.; Fraser, M.; Allan, D.B.; Conway, B.A.; Nasseroleslami, B.

In: Clinical Neurophysiology, Vol. 126, No. 11, 01.11.2015, p. 2170-2180.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The influence of central neuropathic pain in paraplegic patients on performance of a motor imagery based brain computer interface

AU - Vuckovic,A.

AU - Hasan,M.A.

AU - Osuagwu,B.

AU - Fraser,M.

AU - Allan,D.B.

AU - Conway,B.A.

AU - Nasseroleslami,B.

PY - 2015/11/1

Y1 - 2015/11/1

N2 - The aim of this study was to test how the presence of central neuropathic pain (CNP) influences the performance of a motor imagery based Brain Computer Interface (BCI). In this electroencephalography (EEG) based study, we tested BCI classification accuracy and analysed event related desynchronisation (ERD) in 3 groups of volunteers during imagined movements of their arms and legs. The groups comprised of nine able-bodied people, ten paraplegic patients with CNP (lower abdomen and legs) and nine paraplegic patients without CNP. We tested two types of classifiers: a 3 channel bipolar montage and classifiers based on common spatial patterns (CSPs), with varying number of channels and CSPs. Paraplegic patients with CNP achieved higher classification accuracy and had stronger ERD than paraplegic patients with no pain for all classifier configurations. Highest 2-class classification accuracy was achieved for CSP classifier covering wider cortical area: 82 ± 7% for patients with CNP, 82 ± 4% for able-bodied and 78 ± 5% for patients with no pain. Presence of CNP improves BCI classification accuracy due to stronger and more distinct ERD. Results of the study show that CNP is an important confounding factor influencing the performance of motor imagery based BCI based on ERD.

AB - The aim of this study was to test how the presence of central neuropathic pain (CNP) influences the performance of a motor imagery based Brain Computer Interface (BCI). In this electroencephalography (EEG) based study, we tested BCI classification accuracy and analysed event related desynchronisation (ERD) in 3 groups of volunteers during imagined movements of their arms and legs. The groups comprised of nine able-bodied people, ten paraplegic patients with CNP (lower abdomen and legs) and nine paraplegic patients without CNP. We tested two types of classifiers: a 3 channel bipolar montage and classifiers based on common spatial patterns (CSPs), with varying number of channels and CSPs. Paraplegic patients with CNP achieved higher classification accuracy and had stronger ERD than paraplegic patients with no pain for all classifier configurations. Highest 2-class classification accuracy was achieved for CSP classifier covering wider cortical area: 82 ± 7% for patients with CNP, 82 ± 4% for able-bodied and 78 ± 5% for patients with no pain. Presence of CNP improves BCI classification accuracy due to stronger and more distinct ERD. Results of the study show that CNP is an important confounding factor influencing the performance of motor imagery based BCI based on ERD.

KW - EEG

KW - motor imagery

KW - paraplegia

KW - central neuropathic pain

KW - event related synchronisation/desynchronisation

UR - http://www.sciencedirect.com/science/article/pii/S1388245715000620

U2 - 10.1016/j.clinph.2014.12.033

DO - 10.1016/j.clinph.2014.12.033

M3 - Article

VL - 126

SP - 2170

EP - 2180

JO - Clinical Neurophysiology

T2 - Clinical Neurophysiology

JF - Clinical Neurophysiology

SN - 1388-2457

IS - 11

ER -