Dataset Information

Machine-learning identifies Parkinson's disease patients based on resting-state between-network functional connectivity.

ABSTRACT: OBJECTIVE:Evaluation of a data-driven, model-based classification approach to discriminate idiopathic Parkinson's disease (PD) patients from healthy controls (HC) based on between-network connectivity in whole-brain resting-state functional MRI (rs-fMRI). METHODS:Whole-brain rs-fMRI (EPI, TR = 2.2?s, TE = 30?ms, flip angle = 90°. resolution = 3.1 × 3.1 × 3.1?mm, acquisition time ? 11?min) was assessed in 42 PD patients (medical OFF) and 47 HC matched for age and gender. Between-network connectivity based on full and L2-regularized partial correlation measures were computed for each subject based on canonical functional network architectures of two cohorts at different levels of granularity (Human Connectome Project: 15/25/50/100/200 networks; 1000BRAINS: 15/25/50/70 networks). A Boosted Logistic Regression model was trained on the correlation matrices using a nested cross-validation (CV) with 10 outer and 10 inner folds for an unbiased performance estimate, treating the canonical functional network architecture and the type of correlation as hyperparameters. The number of boosting iterations was fixed at 100. The model with the highest mean accuracy over the inner folds was trained using an non-nested 10-fold 20-repeats CV over the whole dataset to determine feature importance. RESULTS:Over the outer folds the mean accuracy was found to be 76.2% (median 77.8%, SD 18.2, IQR 69.4 - 87.1%). Mean sensitivity was 81% (median 80%, SD 21.1, IQR 75 - 100%) and mean specificity was 72.7% (median 75%, SD 20.4, IQR 66.7 - 80%). The 1000BRAINS 50-network-parcellation, using full correlations, performed best over the inner folds. The top features predominantly included sensorimotor as well as sensory networks. CONCLUSION:A rs-fMRI whole-brain-connectivity, data-driven, model-based approach to discriminate PD patients from healthy controls shows a very good accuracy and a high sensitivity. Given the high sensitivity of the approach, it may be of use in a screening setting. ADVANCES IN KNOWLEDGE:Resting-state functional MRI could prove to be a valuable, non-invasive neuroimaging biomarker for neurodegenerative diseases. The current model-based, data-driven approach on whole-brain between-network connectivity to discriminate Parkinson's disease patients from healthy controls shows promising results with a very good accuracy and a very high sensitivity.

SUBMITTER: Rubbert C

PROVIDER: S-EPMC6732922 | biostudies-literature | 2019 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine-learning identifies Parkinson's disease patients based on resting-state between-network functional connectivity.

Rubbert Christian C Mathys Christian C Jockwitz Christiane C Hartmann Christian J CJ Eickhoff Simon B SB Hoffstaedter Felix F Caspers Svenja S Eickhoff Claudia R CR Sigl Benjamin B Teichert Nikolas A NA Südmeyer Martin M Turowski Bernd B Schnitzler Alfons A Caspers Julian J

The British journal of radiology 20190514 1101

<h4>Objective</h4>Evaluation of a data-driven, model-based classification approach to discriminate idiopathic Parkinson's disease (PD) patients from healthy controls (HC) based on between-network connectivity in whole-brain resting-state functional MRI (rs-fMRI).<h4>Methods</h4>Whole-brain rs-fMRI (EPI, TR = 2.2 s, TE = 30 ms, flip angle = 90°. resolution = 3.1 × 3.1 × 3.1 mm, acquisition time ≈ 11 min) was assessed in 42 PD patients (medical OFF) and 47 HC matched for age and gender. Between-ne ...[more]

PMID: 30994036

Similar Datasets

Project description:IntroductionAlthough the putamen has a significant role in reward-seeking and motivated behaviors, including eating and food-seeking, minorities' diminished returns (MDRs) suggest that individual-level risk and protective factors have weaker effects for Non-Hispanic Black than Non-Hispanic White individuals. However, limited research is available on the relevance of MDRs in terms of the role of putamen functional connectivity on body mass index (BMI).PurposeBuilding on the MDRs framework and conceptualizing race and socioeconomic status (SES) indicators as social constructs, we explored racial and SES differences in the associations between putamen functional connectivity to the salience network and children's BMI.MethodsFor this cross-sectional study, we used functional magnetic resonance imaging (fMRI) data of 6473 9-10-year-old Non-Hispanic Black and Non-Hispanic White children from the Adolescent Brain Cognitive Development (ABCD) study. The primary independent variable was putamen functional connectivity to the salience network, measured by fMRI. The primary outcome was the children's BMI. Age, sex, neighborhood income, and family structure were the covariates. Race, family structure, parental education, and household income were potential moderators. For data analysis, we used mixed-effect models in the overall sample and by race.ResultsHigher right putamen functional connectivity to the salience network was associated with higher BMI in Non-Hispanic White children. The same association was missing for Non-Hispanic Black children. While there was no overall association in the pooled sample, a significant interaction was found, suggesting that the association between right putamen functional connectivity to the salience network and children's BMI was modified by race. Compared to Non-Hispanic White children, Non-Hispanic Black children showed a weaker association between right putamen functional connectivity to the salience network and BMI. While parental education and household income did not moderate our association of interest, marital status altered the associations between putamen functional connectivity to the salience network and children's BMI. These patterns were observed for right but not left putamen. Other/Mixed Race children also showed a pattern similar to Non-Hispanic Black children.ConclusionsThe association between right putamen functional connectivity to the salience network and children's BMI may depend on race and marital status but not parental education and household income. While right putamen functional connectivity to the salience network is associated with Non-Hispanic White children's BMI, Non-Hispanic Black children' BMI remains high regardless of their putamen functional connectivity to the salience network. This finding is in line with MDRs, which attributes diminished effects of individual-risk and protective factors for Non-Hispanic Black children to racism, stratification, and segregation.

Dataset Information

Machine-learning identifies Parkinson's disease patients based on resting-state between-network functional connectivity.

Publications

Machine-learning identifies Parkinson's disease patients based on resting-state between-network functional connectivity.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure