Neurophysiological constraints of control parameters for a brain computer interface system to support post-stroke motor rehabilitation

The Promotɶr is an all-in-one Brain Computer Interface (BCI)-system developed at Fondazione Santa Lucia (Rome, Italy) to support hand motor imagery practice after stroke. In this paper we focus on the optimization of control parameters for the BCI training. We compared two procedures for the feature selection: in the first, features were selected by means of a manual procedure (requiring “skilled users”), in the second a semiautomatic method, developed by us combining physiological and machine learning approaches, guided the feature selection. EEG-based BCI data set collected from 13 stroke patients were analyzed to the aim. No differences were found between the two procedures (paired-samples t-test, p=0.13). Results suggest that the semiautomatic procedure could be applied to support the manual feature selection, allowing no-skilled users to approach BCI technology for motor rehabilitation of stroke patients.