Abstract: Cognitive frailty (the combined presence of physical frailty and cognitive impairment) is a strong and independent predictor of cognitive decline. The International Association of Gerontology and Geriatrics and the International Academy on Nutrition and Aging have recommended the use of cognitive frailty assessment to track the progression of mild cognitive impairment (MCI) towards dementia, Alzheimer's disease (AD), and loss of independence. However, there is no practical assessment tool for measuring cognitive frailty remotely, such as during a telehealth visit. Telehealth video-conferencing between patient and physician is growing in popularity, is increasingly accepted by healthcare payers, and is especially attractive to older adults who may not easily be able to travel to the clinic. Therefore, there is an unmet need for a software-based solution for remote assessment of cognitive frailty that can be integrated into existing telehealth systems. Based on a Direct Phase II SBIR grant award from the National Institute on Aging (NIA), BioSensics LLC and Baylor College of Medicine developed and commercialized Frailty Meter (FM), a novel wearable technology for frailty assessment. FM works by quantifying frailty phenotypes including weakness, slowness, range-of- motion, and exhaustion during a 20-second rapid repetitive elbow flexion-extension task. When applied under dual-task conditions (e.g., while performing a working memory task) FM can be used to assess cognitive impairment. FM is well suited for use in a clinical environment because it is simple to administer and, unlike other measures of frailty, it does not require a walking test. However, because FM is based on wearable sensors there are technical, logistical, and cost-associated challenges associated with its usage in a telehealth setting. To address these limitations, we propose to develop a video-based solution that uses image processing algorithms to replicate the measurements taken by the wearable sensor in FM. To increase market penetration, this software solution will be provided as a plug-in module that developers can easily integrate into their video-based telehealth platform, regardless of whether the system runs on a tablet or a custom-developed telehealth kiosk. During Phase I, we will develop image processing algorithms to enable real-time motion tracking of the upper arm and forearm during the FM task. From this data we will extract elbow rotational velocity (the measurement needed for FM analysis) and validate this measure against the sensor-based device. We will also develop a prototype tablet platform for video conferencing and remote cognitive frailty assessment that we can use in our planned clinical studies during Phase II. The clinical studies in Phase II will validate the effectiveness of this platform for tracking longitudinal changes in cognitive-motor impairment as a marker of dementia severity and the progression from MCI toward AD.

R41AG061951

2018-09-30

2020-08-31