Fall risk, mild cognitive impairment (MCI), and frailty are three interrelated health conditions that diminish quality of life for older adults and put them at higher risk for adverse outcomes, including hospitalization, disability, and death. A common characteristic shared by these conditions is a decline in motor function, most often manifested by degradation in balance and gait performance. Comprehensive early detection of motor declines may offer our best chance of addressing these geriatric conditions. While there is growing interest in using sensors to measure movement and balance, currently available technologies are prohibitively expensive or do not capture multiple aspects of movement. As a solution, we have developed the Mizzou Point-of-Care Assessment System (MPASS), which integrates measurements from multiple sensors to provide an objective, comprehensive dataset of human movement and cognitive performance. The total cost of the testing platform is under $1,500 and MPASS motor function assessments typically take less than 15 minutes. Our goal is to integrate the MPASS with artificial intelligence (AI) approaches to translate the system into a clinically effective tool that quickly, affordably, and accurately assesses risk for falling, MCI, and frailty, in real-world clinical and community settings. Specifically, we will collect data on MPASS motor function, cognitive testing, fall history, and frailty for 30 persons with MCI and 50 community dwelling adults. We will then employ AI to develop prediction algorithms that distinguish persons with MCI, fall risk, and frailty. Finally, we will develop clinically usable outputs based on the prediction algorithms.
22 авг 2024
