Effects of Personalized Cognitive Training with the Machine Learning Algorithm on Neural Efficiency in Healthy Younger Adults


To date, neural efficiency, an ability to economically utilize mental resources, has not been investigated after cognitive training. The purpose of this study was to provide customized cognitive training and confirm its effect on neural efficiency by investigating prefrontal cortex (PFC) activity using functional near-infrared spectroscopy (fNIRS). Before training, a prediction algorithm based on the PFC activity with logistic regression was used to predict the customized difficulty level with 86% accuracy by collecting data when subjects performed four kinds of cognitive tasks. In the next step, the intervention study was designed using one pre-posttest group. Thirteen healthy adults participated in the virtual reality (VR)-based spatial cognitive training, which was conducted four times a week for 30 min for three weeks with customized difficulty levels for each session. To measure its effect, the trail-making test (TMT) and hemodynamic responses were measured for executive function and PFC activity. During the training, VR-based spatial cognitive performance was improved, and hemodynamic values were gradually increased as the training sessions progressed. In addition, after the training, the performance on the trail-making task (TMT) demonstrated a statistically significant improvement, and there was a statistically significant decrease in the PFC activity. The improved performance on the TMT coupled with the decreased PFC activity could be regarded as training-induced neural efficiency. These results suggested that personalized cognitive training could be effective in improving executive function and neural efficiency.

International Journal of Environmental Research and Public Health