Algorithmic Fairness in Brain-Computer Interfaces for Motor Imagery Detection

BRUNO ZORZET; DIEGO H. MILONE; PETERSON, VICTORIA; RODRIGO ECHEVESTE

San Luis

Congreso; Encuentro SAN 2023; 2023

Sociedad Argentina de investigaciones en Neurociencia

Brain-Computer Interfaces (BCIs) can transmit information between individuals andcomputers by monitoring their electrical brain activity using electroencephalogram (EEG)in real-time. The interpretation of these signals using artificial intelligence (AI)algorithms enables the categorization of mental states. However, addressing potentialbiases that may result from such algorithms, which can favor certain population groupsover others, is an important case of study in algorithmic fairness that has not receivedmuch attention in the field of BCI.In this study, we present experiments that help to understand the potential presence ofbias with respect to sex on EEG signal decoding for motor imagery detection in BCI. Weevaluated multiple databases and AI models. Our findings suggest the possibility thatthese disparities in performance are linked to the detection of sex-related information inEEG signals by AI models. This discovery exposes the urgency to mitigate biases in AIbased BCIs before deployment, to ensure equity in performance as well as to prevent theamplification of inequalities.