Although a variety of cognitive training has been performed, its optimally personalized delivery is still unknown. This study established the mental workload classification model using a convolutional neural network based on functional near-infrared spectroscopy-derived data. The dorsolateral prefrontal cortex (DLPFC) while thirty individuals with mild cognitive impairment (MCI) performed spatial working memory testing was found to be a considerable indicator to classify 3 levels of mental workload with an accuracy of over 86%. In the next step, forty subjects with MCI were randomly allocated into the experimental group (EG) that received cognitive training with mental workload-based difficulty adjustment or the control group (CG) that received conventional cognitive training. To compare both groups, the Trail Making Test Part B (TMT-B) and hemodynamic responses in the DLPFC during the TMT-B were measured. After the 16 training sessions, the EG subjects achieved a greater improvement in the TMT-B than the CG subjects (p < 0.05). Also, the EG subject showed a significantly lower DLPFC activity during the TMT-B than the CG subject (p < 0.05). In sum, the EG subjects better performed executive function with lower energy from the DLPFC. These findings imply that the importance of mental workload monitoring to provide personalized cognitive training.
Keywords: Cognition; Cognitive Dysfunction; Machine Learning; Prefrontal Cortex.
Copyright © 2023. Korean Society for Neurorehabilitation.