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

Is virtual reality-based cognitive training in parallel with functional near-infrared spectroscopy-derived neurofeedback beneficial to improve cognitive function in older adults with mild cognitive impairment?

PURPOSE

Cognitive training in parallel with functional near-infrared spectroscopy (fNIRS)-derived neurofeedback has been identified to be beneficial in enhancing cognitive function in patients with mild cognitive impairment (MCI). However, effects of virtual reality (VR)-based cognitive training ensuring ecological validity in parallel with fNIRS-derived neurofeedback on neural efficiency has received little attention. This study investigated effects of VR-based cognitive training in parallel with fNIRS-derived neurofeedback on cognitive function and neural efficiency in patients with MCI.

METHOD

Ninety participants were randomly assigned into the active group (AG) receiving VR-based cognitive training in parallel with fNIRS-derived neurofeedback, the sham group (SG), or wait-list group (CG). The AG and SG group performed each intervention for fifteen minutes a session, for eight sessions. The Trail Making Test Part B and Backward Digit Span Test were used for outcomes. In addition, activity in the dorsolateral prefrontal cortex (DLPFC) during cognitive testing using fNIRS was measured.

RESULTS

After the eight sessions, the AG achieved greater improvements in all outcomes than the other groups. In addition, the AG showed a lower DLPFC activity during cognitive testing than the other groups.

CONCLUSIONS

VR-based cognitive training in parallel with fNIRS-derived neurofeedback is superior to enhancing cognitive function and neural efficiency.

Classification of Mild Cognitive Impairment Using Functional Near-Infrared Spectroscopy-Derived Biomarkers With Convolutional Neural Networks

OBJECTIVE

To date, early detection of mild cognitive impairment (MCI) has mainly depended on paper-based neuropsychological assessments. Recently, biomarkers for MCI detection have gained a lot of attention because of the low sensitivity of neuropsychological assessments. This study proposed the functional near-infrared spectroscopy (fNIRS)-derived data with convolutional neural networks (CNNs) to identify MCI.

METHODS

Eighty-two subjects with MCI and 148 healthy controls (HC) performed the 2-back task, and their oxygenated hemoglobin (HbO2) changes in the prefrontal cortex (PFC) were recorded during the task. The CNN model based on fNIRS-derived spatial features with HbO2 slope within time windows was trained to classify MCI. Thereafter, the 5-fold cross-validation approach was used to evaluate the performance of the CNN model.

RESULTS

Significant differences in averaged HbO2 values between MCI and HC groups were found, and the CNN model could better discriminate MCI with over 89.57% accuracy than the Korean version of the Montreal Cognitive Assessment (MoCA) (89.57%). Specifically, the CNN model based on HbO2 slope within the time window of 20-60 seconds from the left PFC (96.09%) achieved the highest accuracy.

CONCLUSION

These findings suggest that the fNIRS-derived spatial features with CNNs could be a promising way for early detection of MCI as a surrogate for a conventional screening tool and demonstrate the superiority of the fNIRS-derived spatial features with CNNs to the MoCA.

Mental workload classification using convolutional neural networks based on fNIRS-derived prefrontal activity

BACKGROUND

Functional near-infrared spectroscopy (fNIRS) is a tool to assess brain activity during cognitive testing. Despite its usefulness, its feasibility in assessing mental workload remains unclear. This study was to investigate the potential use of convolutional neural networks (CNNs) based on functional near-infrared spectroscopy (fNIRS)-derived signals to classify mental workload in individuals with mild cognitive impairment.

METHODS

Spatial images by constructing a statistical activation map from the prefrontal activity of 120 subjects with MCI performing three difficulty levels of the N-back task (0, 1, and 2-back) were used for CNNs. The CNNs were evaluated using a 5 and 10-fold cross-validation method.

RESULTS

As the difficulty level of the N-back task increased, the accuracy decreased and prefrontal activity increased. In addition, there was a significant difference in the accuracy and prefrontal activity across the three levels (p's < 0.05). The accuracy of the CNNs based on fNIRS-derived spatial images evaluated by 5 and 10-fold cross-validation in classifying the difficulty levels ranged from 0.83 to 0.96.

CONCLUSION

fNIRS could also be a promising tool for measuring mental workload in older adults with MCI despite their cognitive decline. In addition, this study demonstrated the feasibility of the classification performance of the CNNs based on fNIRS-derived signals from the prefrontal cortex.

Feasibility of Virtual Shopping Budget-Management Training on Executive Functions in Healthy Young Adults: A Pilot Study

To date, budget management in virtual shopping training has not been given much importance. The main objective of this study was to investigate the effects of virtual shopping budget-management training on executive functions and brain activation. Sixteen participants were randomly assigned to the experimental group that received virtual shopping budget-management training or the waitlist control group for a total of 16 sessions. To examine the effects of virtual shopping budget-management training on brain activation, HbO2 was measured in the prefrontal cortex via functional near-infrared spectroscopy (fNIRS) during the Trail Making Test Part B (TMT-B) and Stroop test. Mann-Whitney and Wilcoxon signed-rank tests were used to compare outcomes between and within the two groups. The virtual shopping budget-management training showed no significant difference in all outcomes between both groups (p > 0.05). No significant differences were observed in HbO2 levels during both TMT-B (p > 0.05) and the Stroop test (p > 0.05). However, in the pre-post comparisons, there was a significant difference in the TMT-B (p < 0.05) and Stroop test (p < 0.05) in the experimental group. In this study, although we did not find a distinct advantage in training, it confirmed its potential for clinical benefits in healthy young adults through training.

Effects of Personalized Cognitive Training Using Mental Workload Monitoring on Executive Function in Older Adults With Mild Cognitive Impairment

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.