Abstract

Background: It is challenging for current statistical models to predict clinical progression of Parkinson's disease (PD) because of the involvement of multi-domains and longitudinal data. Methods: Past univariate longitudinal or multivariate analyses from cross-sectional trials have limited power to predict individual outcomes or a single moment. The multivariate generalized linear mixed-effect model (GLMM) under the Bayesian framework was proposed to study multi-domain longitudinal outcomes obtained at baseline, 18-, and 36-month. The outcomes included motor, non-motor, and postural instability scores from the MDS-UPDRS, and demographic and standardized clinical data were utilized as covariates. The dynamic prediction was performed for both internal and external subjects using the samples from the posterior distributions of the parameter estimates and random effects, and also the predictive accuracy was evaluated based on the root of mean square error (RMSE), absolute bias (AB) and the area under the receiver operating characteristic (ROC) curve. Results: First, our prediction model identified clinical data that were differentially associated with motor, non-motor, and postural stability scores. Second, the predictive accuracy of our model for the training data was assessed, and improved prediction was gained in particularly for non-motor (RMSE and AB: 2.89 and 2.20) compared to univariate analysis (RMSE and AB: 3.04 and 2.35). Third, the individual-level predictions of longitudinal trajectories for the testing data were performed, with ~80% observed values falling within the 95% credible intervals. Conclusions: Multivariate general mixed models hold promise to predict clinical progression of individual outcomes in PD. Trial registration: The data was obtained from Dr. Xuemei Huang's NIH grant R01 NS060722, part of NINDS PD Biomarker Program (PDBP). All data was entered within 24 h of collection to the Data Management Repository (DMR), which is publically available (https://pdbp.ninds.nih.gov/data-management).

Original languageEnglish (US)
Article number147
JournalBMC Medical Research Methodology
Volume17
Issue number1
DOIs
StatePublished - Sep 25 2017

Fingerprint

Parkinson Disease
National Institute of Neurological Disorders and Stroke
Organized Financing
Statistical Models
ROC Curve
Multivariate Analysis
Biomarkers
Demography

All Science Journal Classification (ASJC) codes

  • Epidemiology
  • Health Informatics

Cite this

@article{e59e7aebc220484bafc15f56a5e0a8e5,
title = "Predicting the multi-domain progression of Parkinson's disease: A Bayesian multivariate generalized linear mixed-effect model",
abstract = "Background: It is challenging for current statistical models to predict clinical progression of Parkinson's disease (PD) because of the involvement of multi-domains and longitudinal data. Methods: Past univariate longitudinal or multivariate analyses from cross-sectional trials have limited power to predict individual outcomes or a single moment. The multivariate generalized linear mixed-effect model (GLMM) under the Bayesian framework was proposed to study multi-domain longitudinal outcomes obtained at baseline, 18-, and 36-month. The outcomes included motor, non-motor, and postural instability scores from the MDS-UPDRS, and demographic and standardized clinical data were utilized as covariates. The dynamic prediction was performed for both internal and external subjects using the samples from the posterior distributions of the parameter estimates and random effects, and also the predictive accuracy was evaluated based on the root of mean square error (RMSE), absolute bias (AB) and the area under the receiver operating characteristic (ROC) curve. Results: First, our prediction model identified clinical data that were differentially associated with motor, non-motor, and postural stability scores. Second, the predictive accuracy of our model for the training data was assessed, and improved prediction was gained in particularly for non-motor (RMSE and AB: 2.89 and 2.20) compared to univariate analysis (RMSE and AB: 3.04 and 2.35). Third, the individual-level predictions of longitudinal trajectories for the testing data were performed, with ~80{\%} observed values falling within the 95{\%} credible intervals. Conclusions: Multivariate general mixed models hold promise to predict clinical progression of individual outcomes in PD. Trial registration: The data was obtained from Dr. Xuemei Huang's NIH grant R01 NS060722, part of NINDS PD Biomarker Program (PDBP). All data was entered within 24 h of collection to the Data Management Repository (DMR), which is publically available (https://pdbp.ninds.nih.gov/data-management).",
author = "Ming Wang and Zheng Li and Lee, {Eun Young} and Mechelle Lewis and Lijun Zhang and Sterling, {Nicholas W.} and Daymond Wagner and Paul Eslinger and Guangwei Du and Xuemei Huang",
year = "2017",
month = "9",
day = "25",
doi = "10.1186/s12874-017-0415-4",
language = "English (US)",
volume = "17",
journal = "BMC Medical Research Methodology",
issn = "1471-2288",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Predicting the multi-domain progression of Parkinson's disease

T2 - A Bayesian multivariate generalized linear mixed-effect model

AU - Wang, Ming

AU - Li, Zheng

AU - Lee, Eun Young

AU - Lewis, Mechelle

AU - Zhang, Lijun

AU - Sterling, Nicholas W.

AU - Wagner, Daymond

AU - Eslinger, Paul

AU - Du, Guangwei

AU - Huang, Xuemei

PY - 2017/9/25

Y1 - 2017/9/25

N2 - Background: It is challenging for current statistical models to predict clinical progression of Parkinson's disease (PD) because of the involvement of multi-domains and longitudinal data. Methods: Past univariate longitudinal or multivariate analyses from cross-sectional trials have limited power to predict individual outcomes or a single moment. The multivariate generalized linear mixed-effect model (GLMM) under the Bayesian framework was proposed to study multi-domain longitudinal outcomes obtained at baseline, 18-, and 36-month. The outcomes included motor, non-motor, and postural instability scores from the MDS-UPDRS, and demographic and standardized clinical data were utilized as covariates. The dynamic prediction was performed for both internal and external subjects using the samples from the posterior distributions of the parameter estimates and random effects, and also the predictive accuracy was evaluated based on the root of mean square error (RMSE), absolute bias (AB) and the area under the receiver operating characteristic (ROC) curve. Results: First, our prediction model identified clinical data that were differentially associated with motor, non-motor, and postural stability scores. Second, the predictive accuracy of our model for the training data was assessed, and improved prediction was gained in particularly for non-motor (RMSE and AB: 2.89 and 2.20) compared to univariate analysis (RMSE and AB: 3.04 and 2.35). Third, the individual-level predictions of longitudinal trajectories for the testing data were performed, with ~80% observed values falling within the 95% credible intervals. Conclusions: Multivariate general mixed models hold promise to predict clinical progression of individual outcomes in PD. Trial registration: The data was obtained from Dr. Xuemei Huang's NIH grant R01 NS060722, part of NINDS PD Biomarker Program (PDBP). All data was entered within 24 h of collection to the Data Management Repository (DMR), which is publically available (https://pdbp.ninds.nih.gov/data-management).

AB - Background: It is challenging for current statistical models to predict clinical progression of Parkinson's disease (PD) because of the involvement of multi-domains and longitudinal data. Methods: Past univariate longitudinal or multivariate analyses from cross-sectional trials have limited power to predict individual outcomes or a single moment. The multivariate generalized linear mixed-effect model (GLMM) under the Bayesian framework was proposed to study multi-domain longitudinal outcomes obtained at baseline, 18-, and 36-month. The outcomes included motor, non-motor, and postural instability scores from the MDS-UPDRS, and demographic and standardized clinical data were utilized as covariates. The dynamic prediction was performed for both internal and external subjects using the samples from the posterior distributions of the parameter estimates and random effects, and also the predictive accuracy was evaluated based on the root of mean square error (RMSE), absolute bias (AB) and the area under the receiver operating characteristic (ROC) curve. Results: First, our prediction model identified clinical data that were differentially associated with motor, non-motor, and postural stability scores. Second, the predictive accuracy of our model for the training data was assessed, and improved prediction was gained in particularly for non-motor (RMSE and AB: 2.89 and 2.20) compared to univariate analysis (RMSE and AB: 3.04 and 2.35). Third, the individual-level predictions of longitudinal trajectories for the testing data were performed, with ~80% observed values falling within the 95% credible intervals. Conclusions: Multivariate general mixed models hold promise to predict clinical progression of individual outcomes in PD. Trial registration: The data was obtained from Dr. Xuemei Huang's NIH grant R01 NS060722, part of NINDS PD Biomarker Program (PDBP). All data was entered within 24 h of collection to the Data Management Repository (DMR), which is publically available (https://pdbp.ninds.nih.gov/data-management).

UR - http://www.scopus.com/inward/record.url?scp=85029893487&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029893487&partnerID=8YFLogxK

U2 - 10.1186/s12874-017-0415-4

DO - 10.1186/s12874-017-0415-4

M3 - Article

C2 - 28946857

AN - SCOPUS:85029893487

VL - 17

JO - BMC Medical Research Methodology

JF - BMC Medical Research Methodology

SN - 1471-2288

IS - 1

M1 - 147

ER -