Modification of cortical activation pattern after long-term BCI training and its impact on decoding model...

Area of Science:

• Neuroscience
• Biomedical Engineering
• Rehabilitation Medicine

Background:

• Inter-session variability in brain signals is a significant challenge for brain-computer interfaces (BCIs).
• This variability affects model performance and may indicate long-term brain adaptation in patients undergoing BCI training.
• Understanding physiological drift is crucial for improving BCI stability and effectiveness.

Purpose of the Study:

• To investigate physiological drift in BCIs by analyzing brain activity evolution across sessions.
• To quantify the relationship between physiological drift and BCI decoder performance.
• To explore the potential of BCI-induced brain modifications for rehabilitation.

Main Methods:

• Analysis of spatial patterns of synchronization and desynchronization across a wide frequency range.
• Application of a linear regression model to quantify drift and residual variability.
• Correlation analysis between physiological variability and decoder performance.

Main Results:

• Quantification of physiological drift and its impact on BCI performance.
• Demonstration of coherence between physiological changes and decoder outcomes.
• Identification of BCI-driven long-term modifications in brain activation patterns.

Conclusions:

• Physiological drift significantly impacts BCI performance, necessitating strategies for adaptation.
• BCI training can induce measurable long-term changes in brain activity, supporting its role in rehabilitation.
• This research contributes to developing more robust and reliable BCI systems for clinical applications.