An exploration of EEG features during recovery following stroke - implications for BCI-mediated neurorehabilitation therapy

Darren J Leamy, Juš Kocijan, Katarina Domijan, Joseph Duffin, Richard Ap Roche, Sean Commins, Ronan Collins, Tomas E Ward, Darren J Leamy, Juš Kocijan, Katarina Domijan, Joseph Duffin, Richard Ap Roche, Sean Commins, Ronan Collins, Tomas E Ward

Abstract

Background: Brain-Computer Interfaces (BCI) can potentially be used to aid in the recovery of lost motor control in a limb following stroke. BCIs are typically used by subjects with no damage to the brain therefore relatively little is known about the technical requirements for the design of a rehabilitative BCI for stroke.

Methods: 32-channel electroencephalogram (EEG) was recorded during a finger-tapping task from 10 healthy subjects for one session and 5 stroke patients for two sessions approximately 6 months apart. An off-line BCI design based on Filter Bank Common Spatial Patterns (FBCSP) was implemented to test and compare the efficacy and accuracy of training a rehabilitative BCI with both stroke-affected and healthy data.

Results: Stroke-affected EEG datasets have lower 10-fold cross validation results than healthy EEG datasets. When training a BCI with healthy EEG, average classification accuracy of stroke-affected EEG is lower than the average for healthy EEG. Classification accuracy of the late session stroke EEG is improved by training the BCI on the corresponding early stroke EEG dataset.

Conclusions: This exploratory study illustrates that stroke and the accompanying neuroplastic changes associated with the recovery process can cause significant inter-subject changes in the EEG features suitable for mapping as part of a neurofeedback therapy, even when individuals have scored largely similar with conventional behavioural measures. It appears such measures can mask this individual variability in cortical reorganization. Consequently we believe motor retraining BCI should initially be tailored to individual patients.

Figures

Figure 1
Figure 1
Kapandji thumb opposition scores. A score of 0 indicates no opposition, a score of 10 indicates maximal opposition.
Figure 2
Figure 2
Experimental protocol. Experimental protocol diagram showing timings of each trial along with the timing of the window of data used in CSP analysis.
Figure 3
Figure 3
FBCSP BCI system diagram. Simplified diagram of the off-line Brain-Computer Interface implementation used.
Figure 4
Figure 4
Selected CSP feature frequency ranges. Histogram of frequency ranges of selected CSP features following Marginal Relevance ranking for each for the groups Healthy, Stroke Early and Stroke Late.
Figure 5
Figure 5
Stroke CSP plots. Plots of the highest-ranking common spatial patterns (columns of W−1) for each stroke dataset along with the frequency range the CSP plot belongs to.
Figure 6
Figure 6
Healthy CSP plots. Plots of the highest-ranking common spatial patterns (columns of W−1) for each healthy dataset along with the frequency range the CSP plot belongs to.

References

    1. Pfurtscheller G, Muller-Putz GR, Scherer R, Neuper C. Rehabilitation with brain-computer interface systems. Computer. 2008;41(10):58–65.
    1. Wang C, Phua KS, Ang KK, Guan C, Zhang H, Lin R, Sui Geok Chua, K, Ang BT, Kuah CWK. A feasibility study of non-invasive motor-imagery BCI-based robotic rehabilitation for Stroke patients. Neural Engineering, 2009. NER ’09. 4th International IEEE/EMBS Conference on 2009. pp. 271–274.
    1. Carabalona R, Castiglioni P, Gramatica F. Brain-computer interfaces and neurorehabilitation. Stud Health Technol Inform. 2009;145:160–176.
    1. Silvoni S, Ramos-Murguialday A, Cavinato M, Volpato C, Cisotto G, Turolla A, Piccione F, Birbaumer N. Brain-computer interface in stroke: a review of progress. Clin EEG Neurosci Official J EEG Clin Neurosci Soc ENCS. 2011;42(4):245–52. doi: 10.1177/155005941104200410.
    1. Ang CS, Sakel M, Pepper MG, Phillips MP. Use of brain computer interfaces in neurological rehabilitation. Br J Neurosci Nurs. 2011;7(3):523–528.
    1. Soekadar SR, Birbaumer N, Cohen LG. Brain-computer-interfaces in the rehabilitation of stroke and neurotrauma. Psychology. 2011;48(6):1–19.
    1. Rebsamen B, Teo CL, Zeng Q, Ang VMH, Burdet E, Guan C, Zhang H, Laugier C. Controlling a wheelchair indoors using thought. Intell Syst, IEEE. 2007;22(2):18–24.
    1. Graimann B, Pfurtscheller G, Allison B, Nijboer F, Broermann U. In: BrainComputer Interfaces. Graimann B, Pfurtscheller G, Allison B R, editor. Heidelberg: Springer Berlin; 2010. Brain - computer interfaces for communication and control in locked-in patients - brain-computer interfaces - the frontiers collection; pp. 185–201.
    1. Nakatani S, Araki N, Mabuchi K. A BCI Rehabilitation System for paralyzed patients. The 51st Annual Conference of Japanese Society for Medical and Biological Engineering, Volume 1. 2012. pp. 1H2–1H4.
    1. Lin CT, Euler C, Mekhtarian A, Gil A, Hern L, Prince D, Shen Y, Horvath J. A brian-computer interface for intelligent wheelchair mobility. Health Care Exchanges (PAHCE), Pan Am. 2011. p. 316.
    1. Dimyan MA, Cohen LG. Neuroplasticity in the context of motor rehabilitation after stroke. Nat Rev Neurol. 2011;7(2):76–85. doi: 10.1038/nrneurol.2010.200.
    1. Sharma N, Pomeroy VM, Baron JC. Motor imagery: a backdoor to the motor system after stroke? Stroke. 2006;37(7):1941–1952. doi: 10.1161/01.STR.0000226902.43357.fc.
    1. Ward TE, Soraghan CJ, Matthews F, Markham C. A concept for extending the applicability of constraint-induced movement therapy through motor cortex activity feedback using a neural prosthesis. Comput Intell Neurosci 2007. p. 51363.
    1. Barbour VL, Mead GE. Fatigue after stroke: the patient’s perspective. Stroke Res Treat 2012. p. 863031.
    1. Michael K. Fatigue and stroke. Rehabil Nurs Official J Assoc Rehabil Nurs. 2002;27(3):89–94. doi: 10.1002/j.2048-7940.2002.tb01995.x.
    1. Lerdal A, Bakken LN, Kouwenhoven SE, Pedersen G, Kirkevold M, Finset A, Kim HS. Poststroke fatigue–a review. J Pain Symptom Manage. 2009;38(6):928–949. doi: 10.1016/j.jpainsymman.2009.04.028.
    1. Duncan F, Wu S, Mead GE. Frequency and natural history of fatigue after stroke: a systematic review of longitudinal studies. J Psychosom Res. 2012;73(1):18–27. doi: 10.1016/j.jpsychores.2012.04.001.
    1. Duffin JT, Collins DR, Coughlan T, O’Neill D, Roche RAP, Commins S. Subtle memory and attentional deficits revealed in an Irish stroke patient sample using domain-specific cognitive tasks. J. Clin. Exp. Neuropsychol. 2012;34(8):864–875. doi: 10.1080/13803395.2012.690368.
    1. Kapandji A. Clinical test of apposition and counter-apposition of the thumb. Annales de Chirurgie de la Main Organe Officiel des Soc de Chirurgie de la Main. 1986;5(1):67–73. doi: 10.1016/S0753-9053(86)80053-9.
    1. Swartz Center for Computational Neuroscience (SCCN) EEGLAB v9.0.2.3. [ ]
    1. Rasmussen CE, Williams CKI. Gaussian processes for machine learning. [ ]
    1. Ang KK, Chin ZY, Zhang H, Guan C. Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on. Hongkong: IEEE; 2008. Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface; pp. 2390–2397.
    1. Ramoser H, Muller Gerking J, Pfurtscheller G. Optimal spatial filtering of single trial EEG during imagined hand movement. Rehab Eng, IEEE Trans. 2000;8(4):441–446. doi: 10.1109/86.895946.
    1. Blankertz B, Tomioka R, Lemm S, Kawanabe M, Müller K-R. Optimizing spatial filters for robust EEG single-trial analysis. IEEE Signal Process Mag. 2008;25(1):41–56.
    1. Dudoit S, Fridlyand J, Speed TP. Comparison of discrimination methods for the classification of tumors using gene expression data. J Am Stat Assoc. 2002;97(457):77–87. doi: 10.1198/016214502753479248.
    1. Seeger M. Gaussian processes for machine learning. Int J Neural Syst. 2004;14:2004.
    1. Rasmussen CE, Williams CKI. Gaussian Processes for Machine Learning. Massachusetts: MIT Press; 2006.
    1. Faul S, Gregorcic G, Boylan G, Marnane W, Lightbody G, Connolly S. Gaussian process modeling of EEG for the detection of neonatal seizures. IEEE Trans Bio-Med Eng. 2007;54(12):2151–2162.
    1. Leamy DJ, Ward T, Kocijan J. 7th IASTED International Conference, Biomedical Engineering (BioMED 2010), February 17–19. Innsbruck: Austria; 2010. Using Gaussian Process Models for Near-Infrafred Spectroscopy Data Interpolation.
    1. Williams CKI, Barber D. Bayesian classification with Gaussian processes. IEEE Trans Pattern Anal Mach Intell. 1998;20(12):1342–1351. doi: 10.1109/34.735807.
    1. Kocijan J, Hvala N. Sequencing batch-reactor control using Gaussian-process models. Bioresour Technol. 2013;137:340–348.
    1. Kaiser V, Kreilinger A, Müller-Putz GR, Neuper C. First steps toward a motor imagery based stroke bci: New strategy to set up a classifier. Front Neurosci. 2011;5:86.
    1. Arvaneh M, Guan C, Ang KK, Quek C. Optimizing the channel selection and classification accuracy in eeg-based bci. IEEE Trans Biomed Eng. 2011;58(6):1865–1873.

Source: PubMed

Sponsor e collaboratori

Condizioni mediche

Interventi farmacologici

3
Sottoscrivi