Studying the Effects of Deep Brain Stimulation and Medication on the\n Dynamics of STN-LFP Signals for Human Behavior Analysis

Le résumé fourni par la source

This paper presents the results of our recent work on studying the effects of\ndeep brain stimulation (DBS) and medication on the dynamics of brain local\nfield potential (LFP) signals used for behavior analysis of patients with\nParkinson s disease (PD). DBS is a technique used to alleviate the severe\nsymptoms of PD when pharmacotherapy is not very effective. Behavior recognition\nfrom the LFP signals recorded from the subthalamic nucleus (STN) has\napplication in developing closed-loop DBS systems, where the stimulation pulse\nis adaptively generated according to subjects performing behavior. Most of the\nexisting studies on behavior recognition that use STN-LFPs are based on the DBS\nbeing off. This paper discovers how the performance and accuracy of automated\nbehavior recognition from the LFP signals are affected under different\nparadigms of stimulation on/off. We first study the notion of beta power\nsuppression in LFP signals under different scenarios (stimulation on/off and\nmedication on/off). Afterward, we explore the accuracy of support vector\nmachines in predicting human actions (button press and reach) using the\nspectrogram of STN-LFP signals. Our experiments on the recorded LFP signals of\nthree subjects confirm that the beta power is suppressed significantly when the\npatients take medication (p-value<0.002) or stimulation (p-value<0.0003). The\nresults also show that we can classify different behaviors with a reasonable\naccuracy of 85% even when the high-amplitude stimulation is applied.\n

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.