Abstract
AbstractBackgroundThe availability of reliable biomarkers of Parkinson’s disease (PD) progression is critical to the understanding of the disease and development of treatment options. Magnetic Resonance Imaging (MRI) provides a promising source of PD biomarkers, however, neuroimaging results have been shown to be markedly sensitive to analytical conditions and population sampling, which motivates investigations of their robustness. This study is part of a project to investigate the replicability of 11 structural MRI measures of PD identified in a recent review.ObjectiveThis paper attempts to reproduce (similar data, similar analysis) and replicate (variations in data and analysis) the design of the machine learning (ML) model described in [1] to predict PD progression from T1-weighted MRIs.MethodsWe used the Parkinson’s Progression Markers Initiative dataset (PPMI,ppmi-info.org) used in [1] and we followed as closely as possible the original methods. We also investigated slight methodological variations in cohort selection, feature extraction, ML model design, and evaluation techniques.ResultsThe Area under the ROC Curve (AUC) achieved by our model closely reproducing the original study remained lower than 0.5. Across all tested models, we obtained a peak AUC of 0.685, which is better than chance performance but remained lower than the AUC value of 0.795 reported in [1].ConclusionWe managed to train a model that predicts disease progression with a performance better than chance on a cohort extracted from the PPMI dataset, using methods adapted from [1]. However, the performance of this model remains substantially lower than the one reported in [1]. Our difficulties to reproduce or replicate the original work are likely explained by the relatively low sample size in the original study. We provide recommendations on how to improve the reproducibility of MRI-based ML models of PD in the future.
Publisher
Cold Spring Harbor Laboratory