Integrating Biomarkers From Virtual Reality and Magnetic Resonance Imaging for the Early Detection of Mild Cognitive Impairment Using a Multimodal Learning Approach: Validation Study.

BACKGROUND: Early detection of mild cognitive impairment (MCI), a transitional stage between normal aging and Alzheimer disease, is crucial for preventing the progression of dementia. Virtual reality (VR) biomarkers have proven to be effective in capturing behaviors associated with subtle deficits in instrumental activities of daily living, such as challenges in using a food-ordering kiosk, for early detection of MCI. On the other hand, magnetic resonance imaging (MRI) biomarkers have demonstrated their efficacy in quantifying observable structural brain changes that can aid in early MCI detection. Nevertheless, the relationship between VR-derived and MRI biomarkers remains an open question. In this context, we explored the integration of VR-derived and MRI biomarkers to enhance early MCI detection through a multimodal learning approach. OBJECTIVE: We aimed to evaluate and compare the efficacy of VR-derived and MRI biomarkers in the classification of MCI while also examining the strengths and weaknesses of each approach. Furthermore, we focused on improving early MCI detection by leveraging multimodal learning to integrate VR-derived and MRI biomarkers. METHODS: The study encompassed a total of 54 participants, comprising 22 (41%) healthy controls and 32 (59%) patients with MCI. Participants completed a virtual kiosk test to collect 4 VR-derived biomarkers (hand movement speed, scanpath length, time to completion, and the number of errors), and T1-weighted MRI scans were performed to collect 22 MRI biomarkers from both hemispheres. Analyses of covariance were used to compare these biomarkers between healthy controls and patients with MCI, with age considered as a covariate. Subsequently, the biomarkers that exhibited significant differences between the 2 groups were used to train and validate a multimodal learning model aimed at early screening for patients with MCI among healthy controls. RESULTS: The support vector machine (SVM) using only VR-derived biomarkers achieved a sensitivity of 87.5% and specificity of 90%, whereas the MRI biomarkers showed a sensitivity of 90.9% and specificity of 71.4%. Moreover, a correlation analysis revealed a significant association between MRI-observed brain atrophy and impaired performance in instrumental activities of daily living in the VR environment. Notably, the integration of both VR-derived and MRI biomarkers into a multimodal SVM model yielded superior results compared to unimodal SVM models, achieving higher accuracy (94.4%), sensitivity (100%), specificity (90.9%), precision (87.5%), and F1-score (93.3%). CONCLUSIONS: The results indicate that VR-derived biomarkers, characterized by their high specificity, can be valuable as a robust, early screening tool for MCI in a broader older adult population. On the other hand, MRI biomarkers, known for their high sensitivity, excel at confirming the presence of MCI. Moreover, the multimodal learning approach introduced in our study provides valuable insights into the improvement of early MCI detection by integrating a diverse set of biomarkers.

Exploring the Relationship between Behavioral and Neurological Impairments Due to Mild Cognitive Impairment: Correlation Study between Virtual Kiosk Test and EEG-SSVEP.

Amnestic mild cognitive impairment (aMCI) is a transitional stage between normal aging and Alzheimer's disease, making early screening imperative for potential intervention and prevention of progression to Alzheimer's disease (AD). Therefore, there is a demand for research to identify effective and easy-to-use tools for aMCI screening. While behavioral tests in virtual reality environments have successfully captured behavioral features related to instrumental activities of daily living for aMCI screening, further investigations are necessary to establish connections between cognitive decline and neurological changes. Utilizing electroencephalography with steady-state visual evoked potentials, this study delved into the correlation between behavioral features recorded during virtual reality tests and neurological features obtained by measuring neural activity in the dorsal stream. As a result, this multimodal approach achieved an impressive screening accuracy of 98.38%.

Prevalence of motor neuron diseases in gout patients: a nationwide population-based cohort study.

BACKGROUND: Increased uric acid may have a protective effect in motor neuron diseases (MNDs). The association between gout, characterized by hyperuricemia, and MNDs was not investigated previously. To estimate the prevalence of MNDs in gout patients using the Health Insurance and Review Assessment (HIRA) database, a nationwide database of South Korea. METHODS: The current descriptive study was conducted using the HIRA database. Subjects diagnosed with gout from 2011 to 2018 were included in this study. Among them, the annual prevalence of MNDs was analyzed, stratified by age and sex. Comorbidities including the Charlson Comorbidity Index score and type of prescribed gout-related drug were also demonstrated. RESULTS: The age-adjusted prevalence of MNDs per 105 persons ranged from 0.598 (95% confidence interval (CI): - 0.231-1.426) to 2.534 (95% CI: 1.100-3.968) between 2011 and 2018. Compared to previous reports, the prevalence of MNDs, especially amyotrophic lateral sclerosis (ALS), in gout patients was significantly lower than in the general population. None of the female gout patients were diagnosed with MNDs. Cerebrovascular accidents, vascular risk factors including hypertension, dyslipidemia, and diabetic complications, and the use of uric acid-lowering agents were more common in gout patients with MNDs than in those without MNDs. CONCLUSION: This study adds to the evidence of MND prevalence in gout patients. Gout might have a protective effect against the risk of MNDs.

Digital Marker for Early Screening of Mild Cognitive Impairment Through Hand and Eye Movement Analysis in Virtual Reality Using Machine Learning: First Validation Study.

BACKGROUND: With the global rise in Alzheimer disease (AD), early screening for mild cognitive impairment (MCI), which is a preclinical stage of AD, is of paramount importance. Although biomarkers such as cerebrospinal fluid amyloid level and magnetic resonance imaging have been studied, they have limitations, such as high cost and invasiveness. Digital markers to assess cognitive impairment by analyzing behavioral data collected from digital devices in daily life can be a new alternative. In this context, we developed a "virtual kiosk test" for early screening of MCI by analyzing behavioral data collected when using a kiosk in a virtual environment. OBJECTIVE: We aimed to investigate key behavioral features collected from a virtual kiosk test that could distinguish patients with MCI from healthy controls with high statistical significance. Also, we focused on developing a machine learning model capable of early screening of MCI based on these behavioral features. METHODS: A total of 51 participants comprising 20 healthy controls and 31 patients with MCI were recruited by 2 neurologists from a university hospital. The participants performed a virtual kiosk test-developed by our group-where we recorded various behavioral data such as hand and eye movements. Based on these time series data, we computed the following 4 behavioral features: hand movement speed, proportion of fixation duration, time to completion, and the number of errors. To compare these behavioral features between healthy controls and patients with MCI, independent-samples 2-tailed t tests were used. Additionally, we used these behavioral features to train and validate a machine learning model for early screening of patients with MCI from healthy controls. RESULTS: In the virtual kiosk test, all 4 behavioral features showed statistically significant differences between patients with MCI and healthy controls. Compared with healthy controls, patients with MCI had slower hand movement speed (t49=3.45; P=.004), lower proportion of fixation duration (t49=2.69; P=.04), longer time to completion (t49=-3.44; P=.004), and a greater number of errors (t49=-3.77; P=.001). All 4 features were then used to train a support vector machine to distinguish between healthy controls and patients with MCI. Our machine learning model achieved 93.3% accuracy, 100% sensitivity, 83.3% specificity, 90% precision, and 94.7% F1-score. CONCLUSIONS: Our research preliminarily suggests that analyzing hand and eye movements in the virtual kiosk test holds potential as a digital marker for early screening of MCI. In contrast to conventional biomarkers, this digital marker in virtual reality is advantageous as it can collect ecologically valid data at an affordable cost and in a short period (5-15 minutes), making it a suitable means for early screening of MCI. We call for further studies to confirm the reliability and validity of this approach.

Classification of Diffuse Glioma Subtype from Clinical-Grade Pathological Images Using Deep Transfer Learning.

Diffuse gliomas are the most common primary brain tumors and they vary considerably in their morphology, location, genetic alterations, and response to therapy. In 2016, the World Health Organization (WHO) provided new guidelines for making an integrated diagnosis that incorporates both morphologic and molecular features to diffuse gliomas. In this study, we demonstrate how deep learning approaches can be used for an automatic classification of glioma subtypes and grading using whole-slide images that were obtained from routine clinical practice. A deep transfer learning method using the ResNet50V2 model was trained to classify subtypes and grades of diffuse gliomas according to the WHO's new 2016 classification. The balanced accuracy of the diffuse glioma subtype classification model with majority voting was 0.8727. These results highlight an emerging role of deep learning in the future practice of pathologic diagnosis.

Dependence of the viewing angle control property of a guest-host liquid crystal cell on the extinction coefficient of the mixture.

The theoretical prediction of a display viewing angle control using a guest-host (GH) liquid crystal (LC) cell has been reported by Chen et al. [Jpn. J. Appl. Phys.48, 062401 (2009)JJAPA50021-492210.1143/JJAP.48.062401]. We experimentally confirmed the viewing angle control property of the GH cell and also investigated its dependence on the extinction coefficient of the GH mixture. The GH cell with a negative dielectric anisotropy and a vertical orientation was attached on front of the display panel, resulting in narrow viewing (NV) property at the field-off state. The GH molecules were switched to a planar orientation, which is also orthogonal to the polarization direction of light at the field-on state, showing wide viewing (WV) property. We varied the concentration of a guest dichroic dye in a host LC and measured the extinction coefficients of the mixtures. We simulated the viewing control property using the measured extinction coefficients and found that the horizontal viewing angle can be controlled using the GH cell, but the vertical viewing angle cannot be controlled. Then, we experimentally confirmed the horizontal viewing angle control using the GH cell. The extinction between the NV and the WV states was increased with a greater extinction coefficient of the GH molecules, but the transmittance was decreased.

Effects of aspirin and clopidogrel on neural stem cells.

Cerebral infarction causes severe morbidity and mortality. Most patients with cerebral infarction should take antiplatelet drugs daily, so the effects of those drugs on the regeneration of the brain need to be investigated. Aspirin and clopidogrel are the most widely used antiplatelet drugs for the prevention of ischemic stroke. We investigated the effects of aspirin and clopidogrel on neural stem cells (NSCs). NSCs were dissociated from fetal rat cortex and cultured with basic fibroblast growth factor and N2 medium. To measure the effects of aspirin and clopidogrel on NSCs, NSCs were treated with several concentrations of aspirin, clopidogrel bisulfate, and clopidogrel resinate for 24 h. After the treatment, we measured cell viability by cell counting kit-8, MTT (3-[4,5-dimethylthiazol-2-yl]-2,5-diphenyltetrazolium bromide) assay, trypan blue staining, flow cytometry, and lactate dehydrogenase assay. To evaluate their effects on NSC proliferation, we performed BrdU cell proliferation assay and colony-forming unit assay. We compared the intracellular protein level in the NSCs treated with aspirin and two types of clopidogrel, by proteomics analysis. Various viability tests showed that clopidogrel resinate and clopidogrel bisulfate did not affect the viability and proliferation of NSCs whereas aspirin decreased them even at low concentrations which are clinically relevant. Moreover, through the proteomics, it was confirmed that the toxicity of aspirin to NSCs might be associated with the alteration of several intracellular proteins. Taken together, these results suggest that clopidogrel resinate and clopidogrel bisulfate are safe but aspirin could be toxic to NSCs. Therefore, when these antiplatelet agents are prescribed over the long-term, the finding that aspirin could be toxic to NSCs should be considered.

Modeling long-term human activeness using recurrent neural networks for biometric data.

BACKGROUND: With the invention of fitness trackers, it has been possible to continuously monitor a user's biometric data such as heart rates, number of footsteps taken, and amount of calories burned. This paper names the time series of these three types of biometric data, the user's "activeness", and investigates the feasibility in modeling and predicting the long-term activeness of the user. METHODS: The dataset used in this study consisted of several months of biometric time-series data gathered by seven users independently. Four recurrent neural network (RNN) architectures-as well as a deep neural network and a simple regression model-were proposed to investigate the performance on predicting the activeness of the user under various length-related hyper-parameter settings. In addition, the learned model was tested to predict the time period when the user's activeness falls below a certain threshold. RESULTS: A preliminary experimental result shows that each type of activeness data exhibited a short-term autocorrelation; and among the three types of data, the consumed calories and the number of footsteps were positively correlated, while the heart rate data showed almost no correlation with neither of them. It is probably due to this characteristic of the dataset that although the RNN models produced the best results on modeling the user's activeness, the difference was marginal; and other baseline models, especially the linear regression model, performed quite admirably as well. Further experimental results show that it is feasible to predict a user's future activeness with precision, for example, a trained RNN model could predict-with the precision of 84%-when the user would be less active within the next hour given the latest 15 min of his activeness data. CONCLUSIONS: This paper defines and investigates the notion of a user's "activeness", and shows that forecasting the long-term activeness of the user is indeed possible. Such information can be utilized by a health-related application to proactively recommend suitable events or services to the user.

Investigating the Impact of Possession-Way of a Smartphone on Action Recognition.

For the past few decades, action recognition has been attracting many researchers due to its wide use in a variety of applications. Especially with the increasing number of smartphone users, many studies have been conducted using sensors within a smartphone. However, a lot of these studies assume that the users carry the device in specific ways such as by hand, in a pocket, in a bag, etc. This paper investigates the impact of providing an action recognition system with the information of the possession-way of a smartphone, and vice versa. The experimental dataset consists of five possession-ways (hand, backpack, upper-pocket, lower-pocket, and shoulder-bag) and two actions (walking and running) gathered by seven users separately. Various machine learning models including recurrent neural network architectures are employed to explore the relationship between the action recognition and the possession-way recognition. The experimental results show that the assumption of possession-ways of smartphones do affect the performance of action recognition, and vice versa. The results also reveal that a good performance is achieved when both actions and possession-ways are recognized simultaneously.

Activation of the phosphatidylinositol 3-kinase pathway plays important roles in reduction of cerebral infarction by cilnidipine.

Cerebral infarction causes permanent neuronal loss inducing severe morbidity and mortality. Because hypertension is the main risk factor for cerebral infarction and most patients with hypertension take antihypertensive drugs daily, the neuroprotective effects and mechanisms of anti-hypertensive drugs need to be investigated. Cilnidipine, a long-acting, new generation 1,4-dihydropyridine inhibitor of both L- and N-type calcium channels, was reported to reduce oxidative stress. In this study, we investigated whether cilnidipine has therapeutic effects in an animal model of cerebral infarction. After determination of the most effective dose of cilnidipine, a total of 128 rats were subjected to middle cerebral artery occlusion. Neurobehavioral function test and brain MRI were performed, and rats with similar sized infarcts were randomized to either the cilnidipine group or the control group. Cilnidipine treatment was performed with reperfusion after 2-h occlusion. Western blots and immunohistochemistry were also performed after 24-h occlusion. Initial infarct volume on diffusion-weighted MRI was not different between the cilnidipine group and the control group; however, fluid-attenuated inversion recovery MRI at 24 h showed significantly reduced infarct volume in the cilnidipine group compared with the control group. Cilnidipine treatment significantly decreased the number of triphosphate nick end labeling-positive cells compared to the control group. Western blot and immunohistochemistry showed increased expression of phosphorylated Akt (Ser473), phosphorylated glycogen synthase kinase-3ß, and Bcl-2 and decreased expression of Bax and cleaved caspase-3. These results suggest that cilnidipine, which is used for the treatment of hypertension, has neuroprotective effects in the ischemic brain through activation of the PI3K pathway. We investigated whether cilnidipine has neuroprotective effects on ischemic stroke in an animal model. We have demonstrated that the neuroprotective effect of cilnidipine is associated with the activation of the PI3K pathway. Considering the daily use of antihypertensive drugs for patients with hypertension, cilnidipine could be beneficial for patients with ischemic stroke.

Codon-based encoding for DNA sequence analysis.

With the exponential growth of biological sequence data (DNA or Protein Sequence), DNA sequence analysis has become an essential task for biologist to understand the features, functions, structures, and evolution of species. Encoding DNA sequences is an effective method to extract the features from DNA sequences. It is commonly used for visualizing DNA sequences and analyzing similarities/dissimilarities between different species or cells. Although there have been many encoding approaches proposed for DNA sequence analysis, we require more elegant approaches for higher accuracy. In this paper, we propose a noble encoding approach for measuring the degree of similarity/dissimilarity between different species. Our approach can preserve the physiochemical properties, positional information, and the codon usage bias of nucleotides. An extensive performance study shows that our approach provides higher accuracy than existing approaches in terms of the degree of similarity.

Increased VEGF and decreased SDF-1α in patients with silent brain infarction are associated with better prognosis after first-ever acute lacunar stroke.

BACKGROUND: Pre-existing silent brain infarctions (SBIs) have been reported to be associated with better outcomes after first-ever symptomatic ischemic stroke, although the mechanism of this remains unclear. We investigated the association between SBIs, outcomes of acute lacunar infarction, and biomarkers including vascular endothelial growth factor (VEGF), stromal cell-derived factor-1α (SDF-1α), macrophage migration inhibitory factor (MIF), and high-mobility group box-1 (HMGB1). METHODS: A total of 68 consecutive patients diagnosed with first-ever lacunar infarction (<20 mm) within 24 hours of symptom onset were included in this study. Clinical, laboratory, and imaging data were obtained. Plasma levels of VEGF, SDF-1α, MIF, and HMGB1 were assessed using Enzyme-Linked Immunosorbent Assay kits. RESULTS: SBIs were noted in 31 of the 68 patients. Although the initial National Institutes of Health Stroke Scale scores were not related with the presence of SBIs (P = .313), patients with SBIs had better outcomes at 3 months (P = .029). Additionally, plasma VEGF levels were higher (P = .035) and SDF-1α levels were lower (P < .001) in patients with SBIs. Logistic regression analysis indicated that VEGF and SDF-1α were independently associated with the presence of SBIs. CONCLUSIONS: SBIs are associated with favorable outcomes in patients with first-ever acute lacunar infarction and higher levels of VEGF, and lower levels of SDF-1α in these patients may contribute to their more favorable prognosis.

Validity of the Korean version of the fear of Alzheimer's disease scale for the assessment of anticipatory dementia.

Anticipatory dementia is related to anxiety, which is a clinical predictor of early conversion to Alzheimer's disease. The Fear of Alzheimer's Disease Scale (FADS) is a reliable and valid instrument to address anticipatory dementia. The aim of the present investigation was to develop the Korean version of the Fear of Alzheimer's Disease Scale (K-FADS) and to verify its reliability and validity. We developed the K-FADS to consist of 30 items with total scores ranging from 0 to 120, as in the original FADS. One hundred eight healthy volunteer participants, drawn from 3 different university hospitals, were evaluated. The K-FADS revealed good reliability (Cronbach α=0.96) and good validity as compared to the Korean version of the State-Trait Anxiety Inventory Form (r=0.242, P=0.013). Test-retest reliability was excellent, as the intra-class correlation coefficient comparing the retest to test was 0.98 (95% confidence interval, 0.96-0.99). Our results show that the K-FADS is a suitable and valuable scale to assess anticipatory dementia in elderly Koreans.

Link-based similarity measures using reachability vectors.

We present a novel approach for computing link-based similarities among objects accurately by utilizing the link information pertaining to the objects involved. We discuss the problems with previous link-based similarity measures and propose a novel approach for computing link based similarities that does not suffer from these problems. In the proposed approach each target object is represented by a vector. Each element of the vector corresponds to all the objects in the given data, and the value of each element denotes the weight for the corresponding object. As for this weight value, we propose to utilize the probability of reaching from the target object to the specific object, computed using the "Random Walk with Restart" strategy. Then, we define the similarity between two objects as the cosine similarity of the two vectors. In this paper, we provide examples to show that our approach does not suffer from the aforementioned problems. We also evaluate the performance of the proposed methods in comparison with existing link-based measures, qualitatively and quantitatively, with respect to two kinds of data sets, scientific papers and Web documents. Our experimental results indicate that the proposed methods significantly outperform the existing measures.

Effect of Anti-Aging Standard Forest Healing Program With Multiple Visits to a Forest Facility on Cognition in Older Age Patients.

Background and purpose: The anti-aging standard forest healing program (ASFHP), which uses forest therapy, was reported to be effective in improving psychological, physical, and cognitive functions. However, there are several challenges to directly visiting the forest. This study aimed to investigate the impact of multi-session ASFHP with forest visit on the mental and physical health of the older people with visits to forest facilities and compared them with those of the same program conducted indoors. Methods: Individuals aged over 70 years with concerns about cognitive decline were recruited at dementia relief centers and divided into control and experimental groups. A total of 33 people were administered ASFHP under the supervision of a forest therapy instructor. The control group stayed indoors, while the experimental group visited a forest healing center and repeated the program 20 weeks. Results: The multiple-session ASFHP positively affected cognitive impairment screening test (CIST) total scores (p=0.002), memory (p=0.014), Korean version of the Repeatable Battery for the Assessment of Neuropsychological Status total scores (p<0.001), immediate recall (p=0.001), visuospatial/construction (p<0.001), language (p<0.001), forest healing standard questionnaire total scores (p=0.002), and cognitive function (p=0.019), regardless of location. The forest visits during the ASFHP showed positive effects on orientation (p=0.035), delayed recall (p=0.042), emotional stability (p=0.032), physical activity (p=0.005), and health (p=0.022). The CIST scores of the memory domain were the strongest indicator of the multiple-session ASFHP effects. Conclusions: The 20-week multi-session ASFHP with forest visit showed effects on cognitive improvement and physical and emotional stability compared to indoor education.

Three Virtual Reality Environments for the Assessment of Executive Functioning Using Performance Scores and Kinematics: An Embodied and Ecological Approach to Cognition.

Virtual reality (VR) is an attractive technology for cognitive assessment, as it provides a more embodied experience compared with typical test situations, such as those using paper and pencil. In addition, VR can immerse individuals in complex situations similar to real-life ones, thereby improving the ecological validity (i.e., face validity) of the assessment. VR also offers improved scoring of tests as it facilitates the tracking of kinematic information and the temporal tracking of activities. This study assesses the correlation between scores on executive function assessments using standard neuropsychological tasks in paper-and-pencil format, on a tablet, and in three immersive VR environments, each designed to involve specific aspects of executive function. This study also aims to assess the correlation between these performance scores and a set of kinematic measures (speed, duration, and distance traveled by the hand) collected in VR. The outcomes, including performance scores and kinematic measures, correlate both with traditional assessment methods (such as paper and pencil, and computerized 2D tests) and with each other, suggesting their potential usefulness in clinical and research contexts. The discussion focuses on the advantages of embodied, situated, and spatialized tests for cognitive assessment and the benefits of kinematic tracking in VR tests for the quality of this assessment.

Impact of the COVID-19 pandemic on mortality and loss to follow-up among patients with dementia receiving anti-dementia medications.

The coronavirus disease 2019 (COVID-19) pandemic has profoundly impacted vulnerable groups, such as patients with dementia. We examined changes in mortality and loss to follow-up in patients with dementia using data from the Korean National Health Insurance Service research database. Patients with dementia who visited a medical institution with a recorded dementia-related diagnostic code, including Alzheimer's disease, and who received anti-dementia medication between February 2018 and January 2020 were included in this study. We divided patients with dementia receiving anti-dementia medications into two cohorts: those newly diagnosed with dementia between February 2018 and January 2019 (n = 62,631) and those diagnosed between February 2019 and January 2020 (n = 54,494). Then, we conducted a one-year follow-up of their records, tracking the cohort diagnosed between February 2018 and January 2019 from February 2019 to January 2020, as well as the cohort diagnosed between February 2019 and January 2020 from February 2020 to January 2021. There was a significant increase in follow-up loss among patients newly diagnosed with dementia during the COVID-19 outbreak, from 42.04% in 2019 to 45.89% in 2020. Female sex, younger age, fewer comorbidities, diagnosis of dementia at the Department of Neurology or Psychiatry, and higher income were associated with decreased follow-up loss and mortality. This study highlights the importance of paying extra attention to patients with dementia receiving anti-dementia medications, particularly during pandemics, given their increased risk of loss to follow-up.

A Two-Year Observational Study to Evaluate Conversion Rates from High- and Low-Risk Patients with Amnestic Mild Cognitive Impairment to Probable Alzheimer's Disease in a Real-World Setting.

Background: Predicting conversion to probable Alzheimer&s disease (AD) from amnestic mild cognitive impairment (aMCI) is difficult but important. A nomogram was developed previously for determining the risk of 3-year probable AD conversion in aMCI. Objective: To compare the probable AD conversion rates with cognitive and neurodegenerative changes for 2 years from high- and low risk aMCI groups classified using the nomogram. Methods: This prospective, multicenter, observational study was conducted in Korea. A total of patients were classified as high- or low-risk aMCI according to the nomogram and followed-up for 2 years to compare the annual conversion rate to probable AD and brain structure changes between the two groups. Results: In total, 176 (high-risk, 85; low-risk, 91) and 160 (high-risk, 77; low-risk, 83) patients completed the 1-year and 2-year follow-up, respectively. The probable AD conversion rate was significantly higher in the high-risk (Year 1, 28.9%; Year 2, 46.1%) versus low-risk group (Year 1, 0.0%; Year 2, 4.9%, both p < 0.0001). Mean changes from baseline in Seoul Neuropsychological Screening Battery-Dementia Version, Clinical Dementia Rating-Sum of Box, and Korean version of the Instrumental Activities of Daily Living scores and cortical atrophy index at Years 1 and 2 were significantly greater in the high-risk group (p < 0.0001). Conclusions: The high-risk aMCI group, as determined by the nomogram, had a higher conversion rate to probable AD and faster cognitive decline and neurodegeneration change than the low-risk group. These real-world results have clinical implications that help clinicians in accurately predicting patient outcomes and facilitating early decision-making.Trial Registration: ClinicalTrials.gov (NCT03448445).

Multi-task learning approach for utilizing temporal relations in natural language understanding tasks.

Various studies have been conducted on multi-task learning techniques in natural language understanding (NLU), which build a model capable of processing multiple tasks and providing generalized performance. Most documents written in natural languages contain time-related information. It is essential to recognize such information accurately and utilize it to understand the context and overall content of a document while performing NLU tasks. In this study, we propose a multi-task learning technique that includes a temporal relation extraction task in the training process of NLU tasks such that the trained model can utilize temporal context information from the input sentences. To utilize the characteristics of multi-task learning, an additional task that extracts temporal relations from given sentences was designed, and the multi-task model was configured to learn in combination with the existing NLU tasks on Korean and English datasets. Performance differences were analyzed by combining NLU tasks to extract temporal relations. The accuracy of the single task for temporal relation extraction is 57.8 and 45.1 for Korean and English, respectively, and improves up to 64.2 and 48.7 when combined with other NLU tasks. The experimental results confirm that extracting temporal relations can improve its performance when combined with other NLU tasks in multi-task learning, compared to dealing with it individually. Also, because of the differences in linguistic characteristics between Korean and English, there are different task combinations that positively affect extracting the temporal relations.

Residents need competence not confidence: A retrospective evaluation of the new competency education program for Korean neurology residents.

The objective of our study was to scrutinize the learning experiences of Korean neurology residents, with an emphasis on the implications of the novel competency-based curriculum implemented in 2021. We hypothesized that this revised curriculum could modulate residents' cognitive conduct, primarily the manifestation of overconfidence, in distinctive ways across different stages of training. Our investigative framework was three-fold. Initially, we began with a qualitative inquiry involving in-depth interviews with a purposively selected cohort of eight residents from four training sites. This approach facilitated comprehensive insight into their perceptions of their competence and confidence across the continuum of a four-year residency program. Subsequently, we incorporated the K-NEPA13 assessment instrument, administered to the residents and their overseeing supervisors. This stage aimed to dissect potential cognitive biases, particularly overconfidence and consistency, within the resident population. The final study involved a comprehensive survey administered to a group of 97 Korean neurology residents, allowing us to consolidate and validate our preceding findings. Our findings revealed that junior residents portrayed heightened confidence in their clinical capabilities compared to their senior peers. Intriguingly, junior residents also displayed a stronger inclination towards reevaluating their clinical judgments, a behavior we hypothesize is stimulated by the recently introduced competency-based curriculum. We identified cognitive divergence between junior and senior residents, with the latter group favoring more consistent and linear cause-and-effect reasoning, while the former demonstrated receptiveness to introspection and reconsideration. We speculate this adaptability might be engendered by the supervisor assignment protocol intrinsic to the new curriculum. Our study highlights the essentiality of incorporating cognitive behaviors when devising medical education strategies. Acknowledging and addressing these diverse cognitive biases, and instilling a spirit of adaptability, can nurture a culture that persists in continuous learning and self-reflection among trainee doctors.