Creative Commons source reading · Neuromodulation and neural interfaces
Predicting optimal deep brain stimulation parameters for Parkinson's disease using functional MRI and machine learning.
Alexandre Boutet; Radhika Madhavan; Gavin J B Elias; Suresh E Joel; Robert Gramer; Manish Ranjan; Vijayashankar Paramanandam; David Xu; Jurgen Germann; Aaron Loh; Suneil K Kalia; Mojgan Hodaie; Bryan Li; Sreeram Prasad; Ailish Coblentz; Renato P Munhoz; Jeffrey Ashe; Walter Kucharczyk; Alfonso Fasano; Andres M Lozano
Originally published in Nature communications · 2021-05-24
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
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.
Discussion
Following the satisfactory resolution of safety concerns in prior studies7,9,14, we acquired a large cohort of prospective 3 T fMRI in PD-DBS patients and demonstrated a characteristic pattern of brain responses to clinically optimal stimulation. By contrasting these patterns with those obtained during non-optimal stimulation, we trained and validated a ML model to classify whether a given stimulation setting could be considered clinically optimal in terms of DBS contact and voltage (Fig. 5).
Editorial reading guide
- How were patients or cases selected, and what did the authors use as a comparator?
- Which outcomes, complications and follow-up intervals determine how far the findings apply?
