Predicting learning stages during the serial reaction time task using event-related potentials

Learning a sequence of movements is akin to the acquisition of a motor skill. We investigated event-related potentials (ERPs) changes, particularly the error-related negativity (ERN) and P200 components, as participants learned a motor sequence using a serial reaction time task. Unlike previous studies that investigated error-related negativity for only incorrect motor responses, we tracked ERN changes for all responses. We found that ERN decreased significantly from early to later stages of learning. We also observed a significant change in the P200 component associated with increased selective attention to relevant stimuli as learning occurred. Scalp topography showed the differences in neural activity during motor sequence learning in the frontal, central, and parietal regions. We then employed machine learning to identify the best predictors of motor learning stages. Using random forest, we found the most discriminating pattern for early versus late learning phases. The combination of three electrodes, including 'C3-C4-P3', obtained the maximum accuracy of 82% while classifying EEG signals corresponding to early and late stages of learning. Our study demonstrates that ERN and P200 signals can serve as temporal neural markers for motor skill learning.