Decoding imagined movement in people with multiple sclerosis for brain-computer interface translation.

Area of Science:

• Neuroscience
• Biomedical Engineering
• Rehabilitation Science

Background:

• Multiple sclerosis (MS) is a central nervous system disorder causing fatigue and limb impairment, impacting quality of life.
• Current brain-computer interface (BCI) research in MS primarily focuses on P300 responses or attempted movement signals.
• Limited research exists on decoding imagined movements in individuals with MS.

Purpose of the Study:

• To investigate the feasibility of decoding imagined movements in people with MS using electroencephalography (EEG).
• To compare the performance of BCI in individuals with MS versus neurotypical controls.
• To identify effective frequency bands and latencies for decoding motor imagery in MS.

Main Methods:

• Collected EEG data from 8 participants with MS and 10 neurotypical controls.
• Participants performed imagined hand and foot movements under a go no-go protocol.
• Classified imagined movements versus rest and versus other movements using regularised linear discriminant analysis.

Main Results:

• Classification accuracy exceeded 70% for imagined movement vs. rest in all MS participants.
• No significant difference in classification accuracy was found between MS participants and controls.
• Decodable information was identified in alpha and beta frequency bands at similar latencies for both groups.

Conclusions:

• This study demonstrates the feasibility of decoding imagined movements in people with MS using BCI.
• Motor imagery-based BCI offers a potential alternative to P300-based BCIs for MS.
• Findings support further research into BCI for MS rehabilitation and managing disease progression.