Predicting optimal deep brain stimulation parameters for Parkinson’s disease using functional MRI and machine learning

Abstract

Commonly used for Parkinson’s disease (PD), deep brain stimulation (DBS) produces marked clinical benefits when optimized. However, assessing the large number of possible stimulation settings (i.e., programming) requires numerous clinic visits. Here, we examine whether functional magnetic resonance imaging (fMRI) can be used to predict optimal stimulation settings for individual patients. We analyze 3 T fMRI data prospectively acquired as part of an observational trial in 67 PD patients using optimal and non-optimal stimulation settings. Clinically optimal stimulation produces a characteristic fMRI brain response pattern marked by preferential engagement of the motor circuit. Then, we build a machine learning model predicting optimal vs. non-optimal settings using the fMRI patterns of 39 PD patients with a priori clinically optimized DBS (88% accuracy). The model predicts optimal stimulation settings in unseen datasets: a priori clinically optimized and stimulation-naïve PD patients. We propose that fMRI brain responses to DBS stimulation in PD patients could represent an objective biomarker of clinical response. Upon further validation with additional studies, these findings may open the door to functional imaging-assisted DBS programming.

Neuromodulatory treatments for psychiatric disease: A comprehensive survey of the clinical trial landscape

“…Trials span 37 countries and six continents, and recent data indicates this work is becoming increasingly international. A trend towards greater focus on treatment mechanisms and therapeutic biomarkers is also evident in the increasing proportion of studies that examine neurobiological correlates; this fits with the growing emphasis on optimizing and personalizing therapy that has been observed in the broader neuromodulation literature [22,[39][40][41][42][43][44]. Overall, our results paint an encouraging portrait of circuit-based psychiatry, depicting this once moribund field in a state of rapid and dynamic expansion.…”

Deep Brain Stimulation of the Habenula: Systematic Review of the Literature and Clinical Trial Registries

“…These research modalities can be complemented by functional and molecular neuroimaging techniques such as positron emission tomography (PET), single photon emission computed tomography (SPECT), and functional magnetic resonance imaging (fMRI), which can be readily performed in patients and which capture information simultaneously from across the brain, thereby explicating the network-level effects of DBS (92)(93)(94)(95). Indeed, recent fMRI studies have characterized brain-wide fingerprints of optimal subthalamic DBS for PD with respect to stimulation parameters such as contact, voltage, and frequency (96,97). To this end, Zhang and colleagues used fMRI at various settings compared to a healthy control group (65) while Wang and colleagues conducted LFP recordings paired with a systematic assessment of the effects of stimulation (66).…”

Deep Brain Stimulation for Tremor: Update on Long-Term Outcomes, Target Considerations and Future Directions

“…Functional imaging is another modality possibly shifting the current programming approach. Recently, functional MRI (fMRI) has been proposed as a biomarker of clinical DBS response [164]. Boutet et al used fMRI data to identify brain activity patterns associated with clinical benefits.…”