PROJECT SUMMARY By 2050, 88 million (20%) Americans will be ≥ age 65, representing a doubling of the population along with 25% of all drivers being an older adult. Given that there exists a long preclinical stage of Alzheimer's disease (AD) lasting around 20 years, there is a need to develop low-cost modifiable behavioral interventions. The proposed study expands on the substantial work by two teams: 1) Amissa Health’s NIH SBIR-funded research platform that allows for remote patient monitoring through commodity smartwatches (e.g., an Apple Watch) and 2) The NIH/NIA-funded DRIVES Project from Washington University School of Medicine in St. Louis that uses in-vehicle driving loggers to capture driving behaviors in individuals with and without preclinical AD. This study aims to investigate the relationship between health-related data collected from the Amissa Platform and Apple Watch among older adults coupled with driving behavior data to classify preclinical AD status. Aim 1 focuses on assessing the relationship between health-related data collected from the Amissa Platform and Apple Watch and cognitive function in older adults with and without preclinical AD. A cohort of cognitively normal older adults (≥ age 65, n=50) will be recruited from an existing DRIVES Project. The participant preclinical AD status will have been determined using amyloid tracers via Positron Emission Tomography (PET). In addition, neuropsychological assessments will be administered to participants to comprehensively evaluate cognitive functions such as memory, attention, executive functions, and visuospatial abilities. Health-related parameters, such as heart rate, oxygen saturation, sleep patterns, and physical activity, will be continuously recorded using the Apple Watch and AmissaWear. The data will be analyzed to identify relationships in health- related parameters and cognition by preclinical AD status. The goal of Aim 2 is to determine whether health-related data from the Amissa Platform and Apple Watch, combined with real-world driving behavior data, collected from in-vehicle loggers, can predict preclinical AD status. Participants from Aim 1 will be equipped with DRIVES chips to continuously capture driving performance metrics, including speed, acceleration, braking, and lane deviations. The second Aim will integrate the collected wearable health sensor data with driving data with the goal of developing a robust machine learning model to predict preclinical AD status. This model aims to augment the existing neuropsychological assessment techniques with lower-biased health sensor and driving behavior data and to better estimate cognitive decline and driving risks among older drivers. This innovative research project introduces novel approaches, including the use of popular smartwatches for data collection, a centralized biometric database for AD research, and the integration of health and driving data. It aims to provide accessible and stigma-free data collecti...