A Pilot Study on Data-Driven Adaptive Deep Brain Stimulation in Chronically Implanted Essential Tremor Patients.

Sebastián Castaño-Candamil,Andrew Ko,Michael Tangermann,Sarah S Cooper,Jeffrey Herron,Andrew Haddock,Howard J Chizeck,Benjamin I Ferleger

doi:10.3389/fnhum.2020.541625

Abstract

Deep brain stimulation (DBS) is an established therapy for Parkinson's disease (PD) and essential-tremor (ET). In adaptive DBS (aDBS) systems, online tuning of stimulation parameters as a function of neural signals may improve treatment efficacy and reduce side-effects. State-of-the-art aDBS systems use symptom surrogates derived from neural signals—so-called neural markers (NMs)—defined on the patient-group level, and control strategies assuming stationarity of symptoms and NMs. We aim at improving these aDBS systems with (1) a data-driven approach for identifying patient- and session-specific NMs and (2) a control strategy coping with short-term non-stationary dynamics. The two building blocks are implemented as follows: (1) The data-driven NMs are based on a machine learning model estimating tremor intensity from electrocorticographic signals. (2) The control strategy accounts for local variability of tremor statistics. Our study with three chronically implanted ET patients amounted to five online sessions. Tremor quantified from accelerometer data shows that symptom suppression is at least equivalent to that of a continuous DBS strategy in 3 out-of 4 online tests, while considerably reducing net stimulation (at least 24%). In the remaining online test, symptom suppression was not significantly different from either the continuous strategy or the no treatment condition. We introduce a novel aDBS system for ET. It is the first aDBS system based on (1) a machine learning model to identify session-specific NMs, and (2) a control strategy coping with short-term non-stationary dynamics. We show the suitability of our aDBS approach for ET, which opens the door to its further study in a larger patient population.

Highlights

Deep brain stimulation (DBS) is an established clinical treatment for refractory stages of Parkinson’s disease (PD), dystonia, and essential tremor (ET) (Krauss et al, 2004; RodriguezOroz et al, 2005; Baizabal-Carvallo et al, 2014)
The proposed adaptive DBS (aDBS) system is grounded on two main functional building blocks: (a) the estimation of ongoing tremor intensity based on individual spectral features extracted from ECoG signals, processed by a machine learning algorithm; and (b) a model-free control strategy, that adapts the stimulation amplitude based on temporally local statistics of tremor prediction
We propose two approaches for determining the control signals ui and ud, inspired by the threshold-based aDBS and proportional aDBS systems used in Little et al (2013), Rosa et al (2015), and Velisar et al (2019): In the data-driven binary aDBS (b-aDBS), only DBS “on” and “off ” states are considered, i.e., ui = −ud = AcDBS, where AcDBS corresponds to the patient-specific DBS amplitude optimized by a trained expert for clinical continuous DBS (cDBS) therapy

Summary

Introduction

Deep brain stimulation (DBS) is an established clinical treatment for refractory stages of Parkinson’s disease (PD), dystonia, and essential tremor (ET) (Krauss et al, 2004; RodriguezOroz et al, 2005; Baizabal-Carvallo et al, 2014). In a standard clinical context, DBS parameters (as amplitude, frequency, pulse width, and electric field shape) are periodically determined by a trained expert for each patient. This recurring yet infrequent adaptation, accounts for post-surgical transient states and disease progression.

Methods

Results

Conclusion