Classification of different reaching movements from the same limb using EEG.

OBJECTIVE: Brain-computer-interfaces (BCIs) have been proposed not only as assistive technologies but also as rehabilitation tools for lost functions. However, due to the stochastic nature, poor spatial resolution and signal to noise ratio from electroencephalography (EEG), multidimensional decoding has been the main obstacle to implement non-invasive BCIs in real-live rehabilitation scenarios. This study explores the classification of several functional reaching movements from the same limb using EEG oscillations in order to create a more versatile BCI for rehabilitation. APPROACH: Nine healthy participants performed four 3D center-out reaching tasks in four different sessions while wearing a passive robotic exoskeleton at their right upper limb. Kinematics data were acquired from the robotic exoskeleton. Multiclass extensions of Filter Bank Common Spatial Patterns (FBCSP) and a linear discriminant analysis (LDA) classifier were used to classify the EEG activity into four forward reaching movements (from a starting position towards four target positions), a backward movement (from any of the targets to the starting position and rest). Recalibrating the classifier using data from previous or the same session was also investigated and compared. MAIN RESULTS: Average EEG decoding accuracy were significantly above chance with 67%, 62.75%, and 50.3% when decoding three, four and six tasks from the same limb, respectively. Furthermore, classification accuracy could be increased when using data from the beginning of each session as training data to recalibrate the classifier. SIGNIFICANCE: Our results demonstrate that classification from several functional movements performed by the same limb is possible with acceptable accuracy using EEG oscillations, especially if data from the same session are used to recalibrate the classifier. Therefore, an ecologically valid decoding could be used to control assistive or rehabilitation mutli-degrees of freedom (DoF) robotic devices using EEG data. These results have important implications towards assistive and rehabilitative neuroprostheses control in paralyzed patients.

Neurofeedback and brain-computer interface clinical applications.

Most of the research devoted to BMI development consists of methodological studies comparing different online mathematical algorithms, ranging from simple linear discriminant analysis (LDA) (Dornhege et al., 2007) to nonlinear artificial neural networks (ANNs) or support vector machine (SVM) classification. Single cell spiking for the reconstruction of hand movements requires different statistical solutions than electroencephalography (EEG)-rhythm classification for communication. In general, the algorithm for BMI applications is computationally simple and differences in classification accuracy between algorithms used for a particular purpose are small. Only a very limited number of clinical studies with neurological patients are available, most of them single case studies. The clinical target populations for BMI-treatment consist primarily of patients with amyotrophic lateral sclerosis (ALS) and severe CNS damage including spinal cord injuries and stroke resulting in substantial deficits in communication and motor function. However, an extensive body of literature started in the 1970s using neurofeedback training. Such training implemented to control various EEG-measures provided solid evidence of positive effects in patients with otherwise pharmacologically intractable epilepsy, attention deficit disorder, and hyperactivity ADHD. More recently, the successful introduction and testing of real-time fMRI and a NIRS-BMI opened an exciting field of interest in patients with psychopathological conditions.