ABSTRACT
Introduction: The diagnosis of Alzheimer's disease (AD) is sometimes difficult for nonspecialists, resulting in misdiagnosis. A missed diagnosis can lead to improper management and poor outcomes. Moreover, nonspecialists lack a simple diagnostic model with high accuracy for AD diagnosis. Methods: Randomly assigned data, including training data, of 6000 patients and test data of 1932 from 7932 patients who visited our memory clinic between 2009 and 2021 were introduced into the artificial intelligence (AI)-based AD diagnostic model, which we had developed. Results: The AI-based AD diagnostic model used age, sex, Hasegawa's Dementia Scale-Revised, the Mini-Mental State Examination, the educational level, and the voxel-based specific regional analysis system for Alzheimer's disease (VSRAD) score. It had a sensitivity, specificity, and c-static value of 0.954, 0.453, and 0.819, respectively. The other AI-based model that did not use the VSRAD had a sensitivity, specificity, and c-static value of 0.940, 0.504, and 0.817, respectively. Discussion: We created an AD diagnostic model with high sensitivity for AD diagnosis using only data acquired in daily clinical practice. By using these AI-based models, nonspecialists could reduce missed diagnoses and contribute to the appropriate use of medical resources.
ABSTRACT
This study investigated the changes in physical inactivity of university students during the COVID-19 pandemic, with reference to their academic calendar. We used the daily step counts recorded by a smartphone application (iPhone Health App) from April 2020 to January 2021 (287 days) for 603 participants. The data for 287 days were divided into five periods based on their academic calendar. The median value of daily step counts across each period was calculated. A k-means clustering analysis was performed to classify the 603 participants into subgroups to demonstrate the variability in the physical inactivity responses. The median daily step counts, with a 7-day moving average, dramatically decreased from 5000 to 2000 steps/day in early April. It remained at a lower level (less than 2000 steps/day) during the first semester, then increased to more than 5000 steps/day at the start of summer vacation. The clustering analysis demonstrated the variability in physical inactivity responses. The inactive students did not recover daily step counts throughout the year. Consequently, promoting physical activity is recommended for inactive university students over the course of the whole semester.