We propose to develop a wearable Personal Status Monitor for improving the medication management of Parkinson's Disease patients by monitoring the effects of the medication continuously during the day. New outcome measures are needed to supplement the self-reports currently in use that are ineffective in managing the complex and unpredictable nature of movement disorders in this population. The device we propose to develop can be worn unobtrusively by patients in their home to automatically provide the following clinically significant information: 1) the presence and severity of specific primary and secondary movement disorders associated with the disease, 2) the status of On-Off motor fluctuation in response to anti-Parkinson's medication, and 3) the mobility status of the patient. The patient will be monitored by specially designed electromyographic (EMG) and accelerometric (ACC) body-worn sensors. Their signals will be analyzed by a novel Artificial Intelligence knowledge-based signal processing method developed by our group specifically for this purpose. Success of the system will be based on classification accuracy compared to observation by experts. The proposal is composed of two projects. The first and dominant project will develop the underlying technological requirements for the PSM system's application to Parkinson's disease.
The aims will include acquisition hardware development in the form of hybrid EMG/ACC sensors. However, the emphasis will be on the development of the knowledge-based algorithms and their software implementation. The second project is designed to acquire the knowledge base needed in Project 1 through data collection experiments from control subjects and patients with Parkinson's disease. The experiments are designed to advance the algorithm development in a hierarchical manner starting from highly standardized activities to free-form activities which approximate real-world conditions. The development of the system will be constructed so that future versions can be adapted to other movement disorders. The successful development of this technology will be transferred for commercial development with the financial assistance of the Massachusetts Community Technology Foundation.
| Cole, Bryan T; Roy, Serge H; De Luca, Carlo J et al. (2014) Dynamical learning and tracking of tremor and dyskinesia from wearable sensors. IEEE Trans Neural Syst Rehabil Eng 22:982-91 |
| Roy, Serge H; Cole, Bryan T; Gilmore, L Don et al. (2013) High-resolution tracking of motor disorders in Parkinson's disease during unconstrained activity. Mov Disord 28:1080-7 |
| Cole, Bryan T; Ozdemir, Pinar; Nawab, S Hamid (2012) Dynamic SVM detection of tremor and dyskinesia during unscripted and unconstrained activities. Conf Proc IEEE Eng Med Biol Soc 2012:4927-30 |
| Roy, Serge H; Cole, Bryan T; Gilmore, L Donald et al. (2011) Resolving signal complexities for ambulatory monitoring of motor function in Parkinson's disease. Conf Proc IEEE Eng Med Biol Soc 2011:4832-5 |
| Nawab, S Hamid; Cole, Bryan T (2011) What is IPUS and how does it help resolve biosignal complexity? Conf Proc IEEE Eng Med Biol Soc 2011:4840-3 |
| Roy, Serge H; Cole, Bryan T; Gilmore, L Donald et al. (2011) Resolving signal complexities for ambulatory monitoring of motor function in Parkinson's disease. Conf Proc IEEE Eng Med Biol Soc 2011:4836-9 |
| Cole, Bryan T; Roy, Serge H; Nawab, S Hamid (2011) Detecting freezing-of-gait during unscripted and unconstrained activity. Conf Proc IEEE Eng Med Biol Soc 2011:5649-52 |
| Cole, Bryan T; Roy, Serge H; De Luca, Carlo J et al. (2010) Dynamic neural network detection of tremor and dyskinesia from wearable sensor data. Conf Proc IEEE Eng Med Biol Soc 2010:6062-5 |
| Roy, Serge H; Cheng, M Samuel; Chang, Shey-Sheen et al. (2009) A combined sEMG and accelerometer system for monitoring functional activity in stroke. IEEE Trans Neural Syst Rehabil Eng 17:585-94 |
