Forty-five million people in the US suffer from an involuntary movement disorder. Accurate motor symptom tracking is crucial to improve therapy for those suffering from Parkinson’s disease, stroke, essential tremor, ALS, cerebral palsy, and other neurological disorders. However, monitoring these symptoms using the current standard of paper-and-pencil instruments, or visual observation, is impractical.
We have developed a generic software platform to monitor how the presence and severity of movement disorders change with treatment or as the disease progresses using only wearable sensor data. Our system is designed to use a minimum number of hybrid sensors that are capable of simultaneously detecting muscle activation and movement data. The application software combines advanced machine learning algorithms works with our ambulatory data acquisition systems to create continuous symptom tracking devices for Parkinson disease that can be currently used in a lab or clinical environment. Future work will expand the technology to track other neurological conditions, and develop a version for unsupervised home use.
Detailed descriptions can be found in the Publication List below.
Cole BT, Roy SH, De Luca CJ, and Nawab SH. Dynamical Learning and Tracking of Tremor and Dyskinesia from Wearable Sensors, IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 22 (5): 982-91, Sept 2014. PMID 24760943.