Project Summary/Abstract Fall is the leading cause of injury among elderly. One in three adults over 65 falls each year. Of those who fall, 20% to 30% suffer moderate to severe injuries and increase their risk of early death. In 2015, the total medical costs related to fall injuries for people 65 and older was over $50 billion. Currently, there are devices that use motion sensors (accelerometers) to detect imminent falls and inflate micro-airbags located in garments worn by the users to protect from injury. The literature has shown that wearable solutions based on motion sensing have low detection accuracy and suffer from false-positive events (the airbag may erroneously deploy during daily activities after interpreting abrupt movements as falls). GraceFall, Inc. (GFI) will develop a patent protected fall detection device based on a sensor-fusion algorithm that combines brain (EEG) and body motion signals to allow reliable fall prediction and injury protection. Our initial findings, along with supporting literature, show that a reliable EEG signal preceding an unexpected loss of balance could be the key to developing a complete, reliable, ergonomic solution for fall detection and injury prevention, and would have a major impact on maintaining mobility and quality of life in our aging population. Accelerometers reflect body movement and it is difficult to distinguish between loss of stability and other non-fall related activities. The key difference between intended actions and unintended loss of balance is the appearance of a “startle” response that can be captured on most EEG channels. Using EEG sensors will allow us to identify the difference between a fall and other acceleration scenarios. Our goal is to create a device that primarily uses these reliable brain responses, coupled with motion sensors, to accurately detect loss of balance and stability, thereby preventing injuries due to falling. The goal of the proposed Phase I project is to provide a proof of concept for a future product. Using existing fall protection products that rely on motion sensing to detect an imminent fall, we will identify scenarios in which these products have either false-positive (the airbag erroneously deploying in daily activities after interpreting an abrupt movement as a fall) or false-negative (the airbag not deploying in a real fall scenario) events. We will simulate these same scenarios on human subjects (Aim 1) and we will characterize the physiological parameters of the startle response in an elderly population (Aim 2) to refine the sensor fusion algorithm. The purpose of this proposal is proof of concept that adding a sensor fusion algorithm that combines the EEG information with the acceleration data, improves the performance and reliability of the protection system.