Non-equivalence of sub-tasks of the Rey-Osterrieth Complex Figure Test with convolutional neural networks to discriminate mild cognitive impairment.

BACKGROUND: The Rey-Osterrieth Complex Figure Test (RCFT) is a tool to evaluate cognitive function. Despite its usefulness, its scoring criteria are as complicated as its figure, leading to a low reliability. Therefore, this study aimed to determine the feasibility of using the convolutional neural network (CNN) model based on the RCFT as a screening tool for mild cognitive impairment (MCI) and investigate the non-equivalence of sub-tasks of the RCFT. METHODS: A total of 354 RCFT images (copy and recall conditions) were obtained from 103 healthy controls (HCs) and 74 patients with amnestic MCI (a-MCI). The CNN model was trained to predict MCI based on the RCFT-copy and RCFT-recall images. To evaluate the CNN model's performance, accuracy, sensitivity, specificity, and F1-score were measured. To compare discriminative power, the area under the curve (AUC) was calculated by the receiver operating characteristic (ROC) curve analysis. RESULTS: The CNN model based on the RCFT-recall was the most accurate in discriminating a-MCI (accuracy: RCFT-copy = 0.846, RCFT-recall = 0.872, MoCA-K = 0.818). Furthermore, the CNN model based on the RCFT could better discriminate MCI than the MoCA-K (AUC: RCFT-copy = 0.851, RCFT-recall = 0.88, MoCA-K = 0.848). The CNN model based on the RCFT-recall was superior to the RCFT-copy. CONCLUSION: These findings suggest the feasibility of using the CNN model based on the RCFT as a surrogate for a conventional screening tool for a-MCI and demonstrate the superiority of the CNN model based on the RCFT-recall to the RCFT-copy.

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.

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.

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.

Virtual reality-based cognitive training in parallel with functional near-infrared spectroscopy-derived neurofeedback might improve cognitive function and neural efficiency in patients with mild cognitive impairmentFunctional near-infrared spectroscopy-derived neurofeedback would be considered as an effective tool for understanding neural efficiency underlying improved cognitive function.Rehabilitation professionals need to integrate virtual reality-based cognitive training and functional near-infrared spectroscopy-derived neurofeedback into their practice to enhance cognitive rehabilitation outcomes for patients with mild cognitive impairment.

Performance of ChatGPT on the National Korean Occupational Therapy Licensing Examination.

Background: ChatGPT is an artificial intelligence-based large language model (LLM). ChatGPT has been widely applied in medicine, but its application in occupational therapy has been lacking. Objective: This study examined the accuracy of ChatGPT on the National Korean Occupational Therapy Licensing Examination (NKOTLE) and investigated its potential for application in the field of occupational therapy. Methods: ChatGPT 3.5 was used during the five years of the NKOTLE with Korean prompts. Multiple choice questions were entered manually by three dependent encoders, and scored according to the number of correct answers. Results: During the most recent five years, ChatGPT did not achieve a passing score of 60% accuracy and exhibited interrater agreement of 0.6 or higher. Conclusion: ChatGPT could not pass the NKOTLE but demonstrated a high level of agreement between raters. Even though the potential of ChatGPT to pass the NKOTLE is currently inadequate, it performed very close to the passing level even with only Korean prompts.

Effects of Digital Psychotherapy on Suicide: A Systematic Review and Meta-Analysis.

Previous studies reported that digital psychotherapy was a clinically beneficial intervention for suicide ideation. However, the effects of digital psychotherapy on other aspects of suicide beyond ideation remain unclear. Therefore, this study investigated the effects of digital psychotherapy on suicide and depression. Articles were identified by searching Cochrane, Google Scholar, Medline, PubMed, Web of Science, and PsycINFO in line with the PRISMA statement, yielding nine randomized controlled trials. The difference between conditions regarding suicide and depression in the effect size of the individual article was calculated using Hedges' g. Most digital psychotherapy interventions were based on cognitive behavioral therapy and delivered via apps or the web for at least six weeks. Suicide outcomes primarily focused on suicide ideation. The findings showed digital psychotherapy achieved a significantly larger effect size for suicide (g = 0.488, p < 0.001) and depression (g = 0.316, p < 0.001), compared to controls. Specifically, digital psychotherapy showed a significant effect on both suicide ideation (g = 0.478, p < 0.001) and other suicidal variables (g = 0.330, p < 0.001). These results suggest the effectiveness of digital psychotherapy in reducing suicide and depression compared to traditional face-to-face therapy. Future research should consider a wider range of outcomes and examine the long-term effectiveness of digital psychotherapy to better understand its effects on suicide prevention.

Unveiling Neurocognitive Disparities in Encoding and Retrieval between Paper and Digital Tablet-Based Learning.

The widespread use of mobile devices and laptops has replaced traditional paper-based learning and the question of how the brain efficiency of digital tablet-based learning differs from that of paper-based learning remains unclear. The purpose of this study was to investigate the difference in brain efficiency for learning between paper-based and digital tablet-based learning by measuring activity in the prefrontal cortex (PFC) using functional near-infrared spectroscopy. Thirty-two subjects were randomly assigned to the paper-based learning or the digital tablet-based learning group. Subjects in each group performed a memory task that required memorizing a three-minute novel (encoding phase) on a paper or digital tablet, followed by a test in which they answered four multiple-choice questions based on the novel's content. To compare both groups, behavioral performance on the test (retrieval phase) and activity in the PFC were measured. As a result, no significant difference in behavioral performance between both groups was observed (p > 0.05). However, the paper-based learning group showed significantly lower activity in the PFC in the encoding phase than the digital tablet-based learning group (p < 0.05) but not in the retrieval phase. The current study demonstrated that brain efficiency in encoding is higher in subjects with paper-based learning than those with digital tablet-based learning. This finding has important implications for education, particularly in terms of the pros and cons of electronic document-based learning.