Efficacy evaluation of neurofeedback applied for treatment of central neuropathic pain using machine learning

Abstract Brain-computer interface (BCI) is believed to be the translator of brain signals into actions based on model, built machine learning (ML) algorithms, incorporated in it. This study reports performance various ML algorithms evaluating efficacy neurofeedback applied for treatment central neuropathic pain (CNP). In first phase this study, we different classification electroencephalography (EEG) patterns, associated with CNP, obtained from three groups participants, during imagined movement their limbs, named as able-bodied (AB), paraplegic patients (PWP) and without (PNP) pain. second phase, tested accuracy BCI-classifier by applying new EEG data PWP participants who have completed training provided management Support vector Machine (SVM) algorithm gained higher accuracy, all groups, than other classifiers. However, highest 99 ± 0.49% was right hand motor imagery (AB vs PWP) group 61 electrodes. Conclusion, SVM achieved high CNP. Results show that BCI changes algorithm, electrodes combinations, set.