Dataset Information

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.

SUBMITTER: Boutet A

PROVIDER: S-EPMC8144408 | biostudies-literature | 2021 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Boutet Alexandre A Madhavan Radhika R Elias Gavin J B GJB Joel Suresh E SE Gramer Robert R Ranjan Manish M Paramanandam Vijayashankar V Xu David D Germann Jurgen J Loh Aaron A Kalia Suneil K SK Hodaie Mojgan M Li Bryan B Prasad Sreeram S Coblentz Ailish A Munhoz Renato P RP Ashe Jeffrey J Kucharczyk Walter W Fasano Alfonso A Lozano Andres M AM

Nature communications 20210524 1

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 op ...[more]

PMID: 34031407

Similar Datasets

Project description:BackgroundParkinson's disease is a common neurodegenerative disease, with depression being a common non-motor symptom. Bilateral subthalamic nucleus deep brain stimulation is an effective method for the treatment of Parkinson's disease. Thus, this study aimed to establish a nomogram of the possibility of achieving a better depression improvement rate after subthalamic nucleus deep brain stimulation in patients with Parkinson's disease.MethodsWe retrospectively analyzed 103 patients with Parkinson's disease who underwent subthalamic nucleus deep brain stimulation and were followed up for the improvement of their Hamilton Depression scale scores 1 year postoperatively. Univariate and multivariate logistic regression analyses were used to select factors affecting the improvement rate of depression. A nomogram was then developed to predict the possibility of achieving better depression improvement. Furthermore, the discrimination and fitting performance was evaluated using a calibration diagram, receiver operating characteristics, and decision curve analysis.ResultsThe mean and median improvement rates of Hamilton Depression scores were 13.1 and 33.3%, respectively. Among the 103 patients, 70.8% had an improved depression, 23.3% had a worsened depression, and 5.8% remained unchanged. Logistic multivariate regression analysis showed that age, preoperative Parkinson's Disease Questionnaire, Hamilton Anxiety, and Hamilton Depression scores were independent factors for the possibility of achieving a better depression improvement rate. Based on these results, a nomogram model was developed. The nomogram had a C-index of 0.78 (95% confidence interval: 0.69-0.87) and an area under the receiver operating characteristics of 0.78 (95% confidence interval: 0.69-0.87). The calibration plot and decision curve analysis further demonstrated goodness-of-fit between the nomogram predictions and actual observations.ConclusionWe developed a nomogram to predict the possibility of achieving good depression improvement 1 year after subthalamic nucleus deep brain stimulation in patients with Parkinson's disease, which showed a certain value in judging the expected depression improvement of these patients.

Project description:BackgroundSubthalamic deep brain stimulation (STN DBS) may relieve refractory motor complications in Parkinson's disease (PD) patients. Despite careful screening, it remains difficult to determine severity of alpha-synucleinopathy involvement which influences the risk of postoperative complications including cognitive deterioration. Quantitative electroencephalography (qEEG) reflects cognitive dysfunction in PD and may provide biomarkers of postoperative cognitive decline.ObjectiveTo develop an automated machine learning model based on preoperative EEG data to predict cognitive deterioration 1 year after STN DBS.MethodsSixty DBS candidates were included; 42 patients had available preoperative EEGs to compute a fully automated machine learning model. Movement Disorder Society criteria classified patients as cognitively stable or deteriorated at 1-year follow-up. A total of 16,674 EEG-features were extracted per patient; a Boruta algorithm selected EEG-features to reflect representative neurophysiological signatures for each class. A random forest classifier with 10-fold cross-validation with Bayesian optimization provided class-differentiation.ResultsTweny-five patients were classified as cognitively stable and 17 patients demonstrated cognitive decline. The model differentiated classes with a mean (SD) accuracy of 0.88 (0.05), with a positive predictive value of 91.4% (95% CI 82.9, 95.9) and negative predictive value of 85.0% (95% CI 81.9, 91.4). Predicted probabilities between classes were highly differential (hazard ratio 11.14 [95% CI 7.25, 17.12]); the risk of cognitive decline in patients with high probabilities of being prognosticated as cognitively stable (>0.5) was very limited.ConclusionsPreoperative EEGs can predict cognitive deterioration after STN DBS with high accuracy. Cortical neurophysiological alterations may indicate future cognitive decline and can be used as biomarkers during the DBS screening. © 2021 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets