Guiding deep brain stimulation contact selection using local field potentials sensed by a chronically implanted device in Parkinson's disease patients

Abstract

We have found that a set of support vector machines operating upon local field potentials sensed from an implanted DBS lead can identify the contact chosen by the physician for the patient's STN DBS therapy with 91% accuracy. The finding is based on a small data set and thus subject to change with further data collection and cross-validation. Nevertheless, the results suggest that an algorithm for selecting an effective contact for STN DBS based on the signals sensed from the DBS lead may be feasible.