Data mining techniques to detect motor fluctuations in Parkinson's disease.

The purpose of this paper is to present preliminary evidence that data mining and artificial intelligence systems may allow one to recognize the presence and severity of motor fluctuations in patients with Parkinson's disease (PD). We hypothesize that movement disorders in late-stage PD present with identifiable and predictable features that can be derived from accelerometer (ACC) and surface electromyographic (EMG) signals recorded during the execution of a standardized set of motor assessment tasks. Although this paper focuses on a specific clinical application requiring advanced analysis techniques, the approach can be generalized to numerous applications in which data mining and other techniques can be used to analyze large data sets derived from wearable sensors.