Multi-objective data-driven optimization for improving deep brain stimulation in Parkinson’s disease

Abstract

Objective. Deep brain stimulation (DBS) is an effective treatment for Parkinson’s disease (PD) but its success depends on a time-consuming process of trial-and-error to identify the optimal stimulation settings for each individual patient. Data-driven optimization algorithms have been proposed to efficiently find the stimulation setting that maximizes a quantitative biomarker of symptom relief. However, these algorithms cannot efficiently take into account stimulation settings that may control symptoms but also cause side effects. Here we demonstrate how multi-objective data-driven optimization can be used to find the optimal trade-off between maximizing symptom relief and minimizing side effects. Approach. Cortical and motor evoked potential data collected from PD patients during intraoperative stimulation of the subthalamic nucleus were used to construct a framework for designing and prototyping data-driven multi-objective optimization algorithms. Using this framework, we explored how these techniques can be applied clinically, and characterized the design features critical for solving this optimization problem. Our two optimization objectives were to maximize cortical evoked potentials, a putative biomarker of therapeutic benefit, and to minimize motor potentials, a biomarker of motor side effects. Main Results. Using this in silico design framework, we demonstrated how the optimal trade-off between two objectives can substantially reduce the stimulation parameter space by 61 ± 19%. The best algorithm for identifying the optimal trade-off between the two objectives was a Bayesian optimization approach with an area under the receiver operating characteristic curve of up to 0.94 ± 0.02, which was possible with the use of a surrogate model and a well-tuned acquisition function to efficiently select which stimulation settings to sample. Significance. These findings show that multi-objective optimization is a promising approach for identifying the optimal trade-off between symptom relief and side effects in DBS. Moreover, these approaches can be readily extended to newly discovered biomarkers, adapted to DBS for disorders beyond PD, and can scale with the development of more complex DBS devices.

Optimization of closed-loop electrical stimulation enables robust cerebellar-directed seizure control

“…It is also important to stress that while extreme caution should be taken when translating the specific settings identified in our study to another population, our results do 1) highlight the potential for robust, consistent, seizure inhibition via cerebellar stimulation, and 2) illustrate that Bayesian optimization can be a successful framework for determining effective stimulation parameters. Such a framework can be applied across settings 59,60,76,77 , including potentially clinical settings, and improvement of interfaces collecting and relaying clinical seizure information is on-going 78 . In our animals, a large number of seizures (over a thousand) were required to adequately map the space and identify minima.…”

“…First, we optimized only for seizure duration, but other aspects of stimulation, including potential unwanted side effects, can also be very important. For this, in addition to building such considerations directly into the optimization process 59,76 , it may be possible to use unwanted side effects to bound the space examined (akin to e.g. empirically setting limits for DBS for Parkinson’s disease 82 ).…”

“…An automated data driven approach to determining optimal stimulation settings would reduce the burden on clinicians and likely improve patient outcomes. This is true for epilepsy patients, and for patients receiving or exploring electrical stimulation for a range of neurological disorders and disabilities, including Parkinson’s 61,76 , Essential Tremor 63,85 , chronic pain 86,87 , Obsessive Compulsive Disorder 88,89 , and Depression 90,91 . Our work highlights the potential benefits of a Bayesian optimization approach.…”

StimFit—A Data‐Driven Algorithm for Automated Deep Brain Stimulation Programming

“…Whereas many previous approaches to guide DBS parameter selection were based on visual, 15,19,45,46 kinematic, 32 or electrophysiological feedback, 47 this study proposes a fully automated algorithm, which suggests optimal stimulation settings based on neuroimaging data. The model underlying our approach is based on the properties of the E-field in the target area, which crucially considers directionality of the voltage gradient.…”

“…This might be of special interest considering the aforementioned strategy to engage multiple symptom-specific targets in PD but could also be of importance for optimization problems that simultaneously use multiple input modalities, as suggested in recent publications. 27,47 Limitations First, the assessment of monopolar review data, which have been used for training our model, has certain limitations. Those include a short wash-in period, imposing the risk of introducing bias toward short-term effects.…”