Predicting Inter-session Performance of SMR-Based Brain-Computer Interface Using the Spectral Entropy of Resting-State EEG.

Currently most subjects can control the sensorimotor rhythm-based brain-computer interface (SMR-BCI) successfully after several training procedures. However, 15-30% of subjects cannot achieve SMR-BCI control even after long-term training, and they are termed as "BCI inefficiency". This study focuses on the investigation of reliable SMR-BCI performance predictor. 40 subjects participated in the first experimental session and 26 of them returned in the second session, each session consists of an eyes closed/open resting-state EEG recording run and four EEG recording runs with hand motor imagery. We found spectral entropy derived from eyes closed resting-state EEG of channel C3 has a high correlation with SMR-BCI performance (r = 0.65). Thus, we proposed to use it as a biomarker to predict individual SMR-BCI performance. Receiver operating characteristics analysis and leave-one-out cross-validation demonstrated that the spectral entropy predictor provide outstanding classification capability for high and low aptitude BCI users. To our knowledge, there has been no discussion about the reliability of inter-session prediction in previous studies. We further evaluated the inter-session prediction performance of the spectral entropy predictor, and the results showed that the average classification accuracy of inter-session prediction up to 89%. The proposed predictor is convenient to obtain because it derived from single channel resting-state EEG, it could be used to identify potential SMR-BCI inefficiency subjects from novel users. But there are still limitations because Kübler et al. have shown that some BCI users may need eight or more sessions before they develop classifiable SMR activity.