Objective: To develop a prognostic model using multiple longitudinal measures to predict temporal clinical progression in early PD.

Background: Predicting time to Parkinson’s disease (PD) progression may enable better adaptive and targeted treatment planning for patients.

Method: Predictive longitudinal measures of PD progression were identified by the joint modeling method. Features of multiple longitudinal measures were extracted by multivariate functional principal component analysis methods and used as covariates in Cox proportional hazards models. The optimal model was selected based on data from the Parkinson’s Progression Marker Initiative (PPMI) study. External validation was conducted on the Longitudinal and Biomarker Study in PD (LABS-PD) study.

Results: The proposed prognostic model with longitudinal information of selected clinical measures showed significant advantages in predicting PD temporal progression in comparison to a model with only baseline information (iAUC=0.807 vs 0.753). The modeling results were used to develop a prognostic index for categorizing PD patients into low, mid, and high risk groups to facilitate a treatment decision early in the disease process.

Conclusion: Incorporating longitudinal information of multiple clinical measures significantly enhances predictive performance of prognostic models. Furthermore, the proposed prognostic index enables clinicians to classify patients into different risk groups, which could be adaptively updated as new longitudinal information becomes available. Modeling of this type allows clinicians to utilize observational datasets that inform on disease natural history and specifically, for precision medicine, allows insertion of a patient’s clinical data to calculate prognostic estimates at the individual case level.

« Back to MDS Virtual Congress 2021

MDS Abstracts - https://www.mdsabstracts.org/abstract/prognostic-modeling-of-parkinsons-disease-progression-using-early-longitudinal-patterns-of-change/