Personalized Brain-Computer Interface Models for Motor Rehabilitation
This work addresses stroke rehabilitation by proposing a method to optimize TES parameters for individual patients, though it is incremental as it fuses existing BCI and TES research lines.
The study tackled the problem of limited effect sizes in transcranial electrical stimulation (TES) for stroke rehabilitation by developing personalized brain-computer interface (BCI) models that decode brain rhythms from EEG to predict motor performance during 3D reaching movements, capturing substantial across-subject heterogeneity.
We propose to fuse two currently separate research lines on novel therapies for stroke rehabilitation: brain-computer interface (BCI) training and transcranial electrical stimulation (TES). Specifically, we show that BCI technology can be used to learn personalized decoding models that relate the global configuration of brain rhythms in individual subjects (as measured by EEG) to their motor performance during 3D reaching movements. We demonstrate that our models capture substantial across-subject heterogeneity, and argue that this heterogeneity is a likely cause of limited effect sizes observed in TES for enhancing motor performance. We conclude by discussing how our personalized models can be used to derive optimal TES parameters, e.g., stimulation site and frequency, for individual patients.