https://www.mdu.se/

Stroke is a major cause of long-term disability, often resulting in severe motor impairments. Motor imagery has been proposed as a technique to engage motor networks and promote neuroplasticity, even in the absence of physical movement. Brain–computer interfaces (BCIs) can decode neural activity and provide feedback in a closed loop, supporting reinforcement-based motor learning. BCIs have shown modest but promising results, and their efficiency and usability can be improved by understanding how design choices influence human performance and clinical outcomes. Key challenges include achieving high signal precision through high-dimensional data, delivering real-time feedback under strict latency constraints, and managing non-stationary brain signals within and across sessions. This thesis presents an iterative and exploratory investigation of these challenges. Methods were first developed and validated in healthy participants and later implemented in a clinical intervention with stroke patients. Contributions include classification of motor imagery tasks involving one hand, characterization of motor signals in high-dimensional data, evaluation of system latency for real-time feedback, application of multivariate pattern analysis to capture temporal dynamics of the motor signal, introduction of a continuous metric for motor signal strength linked to visual representations, implementation of a method to set and maintain difficulty level during BCI training, evaluation of adaptive classification methods to maintain performance across sessions, and validation of these methods in a stroke case study. The findings advance understanding of how BCI design parameters affect usability and clinical relevance. By integrating neuroscience, machine learning, and principles of motor learning and neuroplasticity, this work contributes to the development of more effective and personalized BCI systems for stroke rehabilitation.