STN area detection using K-NN classifiers for MER recordings in Parkinson patients during neurostimulator implant surgery

Abstract

Deep Brain Stimulation (DBS) applies electric pulses into the subthalamic nucleus (STN) improving tremor and other symptoms associated to Parkinson's disease. Accurate STN detection for proper location and implant of the stimulating electrodes is a complex task and surgeons are not always certain about final location. Signals from the STN acquired during DBS surgery are obtained with microelectrodes, having specific characteristics differing from other brain areas. Using supervised learning, a trained model based on previous microelectrode recordings (MER) can be obtained, being able to successfully classify the STN area for new MER signals. The K Nearest Neighbours (K-NN) algorithm has been successfully applied to STN detection. However, the use of the fuzzy form of the K-NN algorithm (KNN-F) has not been reported. This work compares the STN detection algorithm of K-NN and KNN-F. Real MER recordings from eight patients where previously classified by neurophysiologists, defining 15 features. Sensitivity and specificity for the classifiers are obtained, Wilcoxon signed rank non-parametric test is used as statistical hypothesis validation. We conclude that the performance of KNN-F classifier is higher than K-NN with p<0.01 in STN specificity.