The purpose of this project is to develop data mining and artificial intelligence systems to recognize the presence and severity of motor fluctuations in patients with Parkinson's disease (PD). Such a system would be valuable both for the clinical management of patients as well as for the conduct of trials of new treatments for PD. We hypothesize that movement disorders that accompany late-stage PD will present with identifiable and predictable features that can be derived from surface electromyographic (EMG) and accelerometer (ACC) signals recorded during the execution of a standardized set of motor assessment tasks. In the first phase of the project (R21) we will explore motor patterns associated with motor states (OFF, ON, DYSKINETIC). We will design methods that rely on data mining visualization techniques and vector quantization-projection algorithms for the identification of data clusters. Successful accomplishment of this exploratory phase will be followed by an R33 Phase in which we will develop a neuro-fuzzy system to provide clinical scores from automated analysis of the EMG and ACC features. Furthermore, we will perform a thorough analysis of motor pattems expressing the full complement of movement disorders associated with PD using fuzzy ARTMAP techniques. The approach will enable us to integrate clinical information into the quantitative EMG/ACC data analysis for the purpose of increasing our ability to identify the motor patterns associated with these disorders. Finally, Parkinsonian patients with motor fluctuations will be monitored before and after adjustment of their medications to assess the sensitivity of the technique to changes in the motor fluctuation patterns. Although this project focuses on a specific clinical application requiring advanced analysis techniques, the approach can be generalized to numerous applications in which data mining and other methods developed in this project can be used to analyze large data sets recorded using wearable sensors.
| Patel, Shyamal; Lorincz, Konrad; Hughes, Richard et al. (2009) Monitoring motor fluctuations in patients with Parkinson's disease using wearable sensors. IEEE Trans Inf Technol Biomed 13:864-73 |
