Single-Trial Classification of Error-Related Potentials in People with Motor Disabilities: A Study in Cerebral Palsy, Stroke, and Amputees

Abstract

Brain-computer interface performance may be reduced over time, but adapting the classifier could reduce this problem. Error-related potentials (ErrPs) could label data for continuous adaptation. However, this has scarcely been investigated in populations with severe motor impairments. The aim of this study was to detect ErrPs from single-trial EEG in offline analysis in participants with cerebral palsy, an amputation, or stroke, and determine how much discriminative information different brain regions hold. Ten participants with cerebral palsy, eight with an amputation, and 25 with a stroke attempted to perform 300–400 wrist and ankle movements while a sham BCI provided feedback on their performance for eliciting ErrPs. Pre-processed EEG epochs were inputted in a multi-layer perceptron artificial neural network. Each brain region was used as input individually (Frontal, Central, Temporal Right, Temporal Left, Parietal, and Occipital), the combination of the Central region with each of the adjacent regions, and all regions combined. The Frontal and Central regions were most important, and adding additional regions only improved performance slightly. The average classification accuracies were 84 ± 4%, 8 7± 4%, and 85 ± 3% for cerebral palsy, amputation, and stroke participants. In conclusion, ErrPs can be detected in participants with motor impairments; this may have implications for developing adaptive BCIs or automatic error correction.

A deep neural network and transfer learning combined method for cross-task classification of error-related potentials

“…The study by Kumar et al ( 2021 ) employed a methodology that combined xDAWN spatial filtering and SVM to categorize ErrPs. Similarly, Usama et al ( 2022 ) utilized an LDA classification approach to distinguish single-trial ErrPs elicited by stroke patients.…”

“…Subsequently, Kumar et al ( 2021 ) proposed a double transfer learning strategy utilizing CNNs to classify ErrPs in stroke survivors. Similarly, Usama et al ( 2022 ) employed an ANN to classify single-trial ErrPs generated by stroke patients. Lastly, Gao et al ( 2022 ) presented a CNN architecture incorporating an attention structure for the classification of ErrPs.…”