Partitioning methods used in DBS treatments analysis results

Parkinson\´s disease is a neurodegenerative disorder and is associated with motor symptoms, including tremor. The DBS (Deep Brain Stimulation) involves electrode implantation into subcortical structures for long-term stimulation at frequencies greater than 100Hz. The mechanism by which chronic, electrical Deep Brain Stimulation with high frequency, suppresses tremor in Parkinson\´s disease is unknown, but might involve a gradual change in network properties controlling the generation of tremor. First, we performed linear and nonlinear analysis of the tremor signals to determine a set of parameters and rules for recognizing the behavior of the investigated patient and to characterize the typical responses for several forms of DBS. Second, we found patterns for homogeneous group for data reduction. We used Data Mining and Knowledge discovery techniques to reduce the number of data. Then, we found "clusters" the most well-known used and commonly partitioning methods used: K-means and K-medoids. To support such predictions, we develop a model of the tremor, to perform tests determining the DBS reducing the tremor or inducing tolerance and lesion if the stimulation is chronic.