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.

The course-recommender system (CRS), designed to aid students’ course-selection decision-making process by suggesting courses aligned with their interests and grades, plays a crucial role in fulfilling curricular requirements, enhancing career opportunities, and fostering intellectual growth. Recent advancements in artificial intelligence (AI) have empowered CRSs to deliver personalized recommendations by considering individual contexts. However, the impact of AI-based CRS on students’ course-selection decision-making process (inter alia, search and evaluation phases) is an open question. Understanding student perceptions and expectations of AI-based CRSs is key to optimizing their decision-making process in course selection. For this purpose, we employed speed dating with storyboards to gather insights from 24 students on five different types of AI-based CRS. The results revealed that students expected AI-based CRSs to play an assistive role in the search phase, helping them efficiently complete time-consuming search tasks in less time. Conversely, during the evaluation phase, students expected AI-based CRSs to play a leading role as a benchmark to address their uncertainty about course suitability, learning value, and serendipity. These findings underscore the adaptive nature of AI-based CRSs, which adjust according to the intricacies of students’ course-selection decision-making process, fostering fruitful collaboration between students and AI.

The imperative for early mild cognitive impairment (MCI) detection is underscored by the limitations of traditional biomarkers, high cost and invasiveness, and they often fail to capture behavioral changes in MCI patients associated with impaired instrumental activities of daily living (IADL). This study introduces a cost-effective, non-invasive alternative using digital markers, “virtual kiosk test”, which involves performing IADL tasks such as ordering food via a kiosk in virtual reality (VR) to detect MCI at an early stage. Involving 20 healthy controls and 31 MCI patients, four key behavioral features within VR digital markers effectively differentiate groups: hand movement speed, proportion of fixation duration, time to completion, and the number of errors. A machine learning model demonstrated high effectiveness with 93.3% accuracy, 100% sensitivity, 83.3% specificity, 90% precision, and a 94.7% F1-score in group differentiation. Findings suggest that observing behaviors via the virtual kiosk test within 5 minutes can be an efficient approach for early MCI detection, acting as reliable VR digital markers.

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%.

Mild cognitive impairment (MCI) is a transitional stage between normal aging and Alzheimer’s disease (AD), which is a progressive and irreversible condition. Detecting MCI at an early stage is crucial as it offers the last opportunity to intervene and potentially prevent the progression to AD. Therefore, there is a need for research on identifying biomarkers that can effectively screen for MCI. Recent research suggests that declines in perception and action occur prior to neurodegenerative changes, highlighting the need for biomarkers that assess the ventral and dorsal streams responsible for processing this information. Among the various biomarkers, electroencephalography with steady-state visual evoked potential (EEG-SSVEP) has shown significant promise, providing real-time, high-resolution monitoring of brain activities in response to flicker stimulation and offering a measure of cognitive decline linked to MCI. Despite this, studies examining the visual pathway for early MCI detection are limited. In this study, we conducted research involving 24 healthy controls and 25 MCI patients to develop and validate a machine learning model for the early detection of MCI based on EEG-SSVEP data. Initially, we extracted 166 EEG-SSVEP biomarkers through a comprehensive analysis, including lobe power ratio, lobe connectivity ratio, and band connectivity ratio to assess visual pathway’s response to stimuli and neural activity across frequency bands. These biomarkers were specialized in quantifying cognitive decline within the visual pathway, specifically within the dorsal and ventral streams of the brain. By employing a biomarker selection method, we identified six key EEG-SSVEP biomarkers as the most relevant for distinguishing between healthy controls and MCI patients. Subsequently, these six biomarkers were utilized to train a support vector machine for early detection of MCI. The results showed an accuracy rate of 95.69%, a sensitivity of 92.28%, and a specificity of 95.58%. This study offers valuable insights into enhancing the early detection of MCI by leveraging EEG-SSVEP data and machine learning to assess cognitive decline within the dorsal and ventral streams of the brain.

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.