A Survey of Non-Invasive EEG-Based Brain-Computer Interfaces in the Medical Domain

Brain-computer interface (BCI) facilitates direct communication between the brain and external devices by converting brain signals into control commands. Advancements in the fields of neuroscience and artificial intelligence have led to rapid evolution of BCI systems as solutions in medical applications. Non-invasive techniques such as Electroencephalography (EEG), Magnetoencephalography (MEG), Functional Magnetic Resonance Imaging (fMRI) and Functional Near Infrared Spectroscopy (fNIRS) are popular due to their safety and accessibility. EEG-based BCI systems have demonstrated potential in assessing and treating neurological disorders. This survey article initially provides a simplified overview of signal acquisition techniques, feature extraction methods and classification algorithms employed in EEG-based BCI systems. Subsequently, it combines insights and findings from various studies on non-invasive EEG-based BCI systems in the medical domain highlighting ongoing work, emerging trends, and key research gaps, with an aim to provide a reference framework for developing future clinical BCI solutions.