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 neuro-feedback 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.