Applying Combined Action Observation and Motor Imagery to Enhance Classification Performance in a Brain–Computer Interface System for Stroke Patients

Abstract

Motor imagery (MI) and action observation (AO) are mental practices commonly applied in brain-computer interface (BCI) systems for stroke rehabilitation. However, previous studies have reported that combined AO and MI (AOMI) is more effective than MI or AO alone in terms of enhanced eventrelated desynchronization (ERD), which expresses cortical excitability and improves the classification performance of the BCI system in healthy subjects. Nonetheless, evidence the use of this strategy in stroke patients is still lacking. Hence, this study aimed to investigate the effect of AOMI on classification performance and ERD in chronic stroke patients. Ten chronic stroke participants were recruited for this study. Each participant was asked to perform both MI (control condition) and AOMI (experimental condition) tasks. For the MI task, the participants requested to perform MI while gazing at a static arrow picture. For the AOMI task, the participants were given a video-guided movement while executing MI. An array of 16 Ag/AgCl electrodes were used to record electroencephalographic (EEG) data during the mental tasks to analyze ERD amplitudes. Common spatial patterns (CSPs) combined with support vector machines (SVMs) were employed to evaluate the classification performance (offline analysis) of the baseline and imagery classes under each condition. Our results indicated that the ERD values and classification accuracy in AOMI were significantly greater than those under MI conditions. Moreover, a significant negative correlation between ERD values and classification performance was also found. In other words, enhanced ERD values (more negative values) also increased classification performance.

Applying Action Observation During a Brain-Computer Interface on Upper Limb Recovery in Chronic Stroke Patients

“…Furthermore, the use of video-guided movement during the MI task may boost task attention and guide participants to execute MI more easily, resulting in a significant increase in ERD [14,34]. Moreover, our previous study involving chronic stroke patients revealed that AOMI was superior to MI in terms of enhancing ERD, resulting in improved offline classification performance [34]. Similarly, the classification model in this study was based on ERD features.…”

“…Additionally, we also found that AOMI-based BCI training was more effective than MI-based BCI training in terms of encouraging the participants to produce more ERD over time. The increased ERD during AOMI-based BCI training may be caused by the automatic activation of the mirror neuron system, which is spontaneously excited by observation of body movement [24,25,33,34]. Furthermore, the use of video-guided movement during the MI task may boost task attention and guide participants to execute MI more easily, resulting in a significant increase in ERD [14,34].…”

“…The increased ERD during AOMI-based BCI training may be caused by the automatic activation of the mirror neuron system, which is spontaneously excited by observation of body movement [24,25,33,34]. Furthermore, the use of video-guided movement during the MI task may boost task attention and guide participants to execute MI more easily, resulting in a significant increase in ERD [14,34]. Moreover, our previous study involving chronic stroke patients revealed that AOMI was superior to MI in terms of enhancing ERD, resulting in improved offline classification performance [34].…”

“…The participants in the AOMI-based BCI group were asked to perform the AOMI task, whereas the participants in the MI-based BCI group were requested to execute the MI task. The AOMI and MI paradigms were derived from our previous work [34]. Before participants performed the AOMI or MI task; the researcher instructed them on how to perform kinesthetic MI.…”

“…In addition, there is a proposal to combine MI and AO. Multimodal brain imaging studies have revealed that combined action observation and motor imagery (AOMI) activates motor execution-related brain regions more effectively than either technique alone [28][29][30][31][32][33][34]. AOMI involves imagining a movement while watching the imagined action shown on a computer display.…”