Millions of Americans live with incurable chronic conditions such as stroke, traumatic brain injury, and Parkinson's disease (PD). These degenerative neurological conditions cause difficulty in the performance of daily life activities such as walking and self-care, limit independence, and lead to depressed quality of life. There are currently no quantitative tools that allow us to understand how these individuals are affected by their conditions on a daily basis, and how rehabilitation and medication affect these people in the long term. The advent of novel technologies such as smart phones and smart watches facilitates exciting new opportunities. These tools allow us to quantitatively monitor, and to positively affect the behaviors of such individuals. This award supports research that will determine how to measure the movements and behaviors of these individuals, and then tests a technique that uses real-time feedback and stimuli to minimize the disease symptoms. We evaluate our approach in individuals suffering from PD, a particularly debilitating disease. Research results will provide much richer information on how people respond to therapy and medication, and may prove useful in other populations of people aging with and into disability. The approach, which integrates engineering and medicine, will help broaden the participation of underrepresented groups in science, technology, engineering, and mathematics research.
Wearable sensing and telehealth are promising tools for revolutionizing healthcare outside of the clinical setting. However, the adaptation of these technologies to specific populations in remote settings remains a challenge. The current research approach focuses on individuals living with the chronic effects of Parkinson's Disease (PD). We propose a system that combines wearable sensors and smart phones to assist these individuals with a particularly debilitating syndrome, freezing of gait. This research will fill the knowledge gap of how to monitor and affect the symptoms of these individuals in ambient settings. We leverage electronic sensor design, machine learning, and signal processing approaches to: (1) determine user-specific models of movement from worn sensor data; (2) develop algorithms to predict onset of user symptoms; and (3) provide context-dependent external stimuli to alleviate symptoms. These methods may generalize to other individuals living with the chronic disability.
