Feasibility of source-level motor imagery classification for people with multiple sclerosis.

There is limited work investigating Brain-Computer Interface (BCI) technology in people with Multiple Sclerosis (pwMS), a neurodegenerative disorder of the central nervous system. Present work is limited to recordings at the scalp, which may be significantly altered by changes within the cortex due to volume conduction. The recordings obtained from the sensors, therefore, combine disease-related alterations and task-relevant neural signals, as well as signals from other regions of the brain that are not relevant. The current study aims to unmix signals affected by MS progression and BCI task-relevant signals using estimated source activity to improve classification accuracy. Approach. Data was collected from eight participants with a range of MS severity and ten neurotypical participants. This dataset was used to report the classification accuracy of imagined movements of the hands and feet at the sensor-level and the source-level in the current study. K-means clustering of equivalent current dipoles was conducted to unmix temporally independent signals. The location of these dipoles was compared between MS and control groups and used for classification of imagined movement. Linear discriminant analysis classification was performed at each time-frequency point to highlight differences in frequency band delay. Main Results. Source-level signal acquisition significantly improved decoding accuracy of imagined movement vs. rest and movement vs. movement classification in pwMS and controls. There was no significant difference found in alpha (7-13 Hz) and beta (13-30 Hz) band classification delay between the neurotypical control and MS group, including imagery of limbs with weakness or paralysis. Significance. This study is the first to demonstrate the advantages of source-level analysis for BCI applications in pwMS. The results highlight the potential for enhanced clinical outcomes and emphasize the need for longitudinal studies to assess the impact of MS progression on BCI performance, which is crucial for effective clinical translation of BCI technology. .