Predicting Parkinson's disease trajectory using clinical and neuroimaging baseline measures

Abstract

Introduction: Predictive biomarkers of Parkinson's Disease progression are needed to expedite neuroprotective treatment development and facilitate prognoses for patients. This work uses measures derived from resting-state functional magnetic resonance imaging, including regional homogeneity (ReHo) and fractional amplitude of low frequency fluctuations (fALFF), to predict an individual's current and future severity over up to 4 years and to elucidate the most prognostic brain regions.

Methods: ReHo and fALFF are measured for 82 Parkinson's Disease subjects and used to train machine learning predictors of baseline clinical and future severity at 1 year, 2 years, and 4 years follow-up as measured by the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Predictive performance is measured with nested cross-validation, validated on an external dataset, and again validated through leave-one-site-out cross-validation. Important predictive features are identified.

Results: The models explain up to 30.4% of the variance in current MDS-UPDRS scores, 55.8% of the variance in year 1 scores, and 47.1% of the variance in year 2 scores (p < 0.0001). For distinguishing high and low-severity individuals at each timepoint (MDS-UPDRS score above or below the median, respectively), the models achieve positive predictive values up to 79% and negative predictive values up to 80%. Higher ReHo and fALFF in several regions, including components of the default motor network, predicted lower severity across current and future timepoints.

Conclusion: These results identify an accurate prognostic neuroimaging biomarker which may be used to better inform enrollment in trials of neuroprotective treatments and enable physicians to counsel their patients.

Keywords: Functional MRI; Machine learning; Neuroimaging; Parkinson's disease; Prognosis.

Figure 1:

Predicted versus ground truth scores for predicting year 1 MDS-UPDRS total score from baseline (a) ReHo and (b) fALFF, for predicting year 2 MDS-UPDRS total score from baseline (c) ReHo and (d) fALFF, and for predicting year 4 MDS-UPDRS total score from baseline (e) ReHo and (f) fALFF.

Figure 2:

Important features learned by each model to predict MDS-UPDRS score. The median feature importance among the LOOCV iterations is shown. Left: the most important features are illustrated, sorted by absolute importance. For brevity, features with zero or comparatively low importance are not shown. Red bars indicate a positive association between the feature and MDS-UPDRS score, and blue bars indicate a negative association. Importance values are normalized to the range of 0–1. Right: the imaging features are visualized in brain space, overlaid on a standard MNI template, with red and blue again reflecting positive and negative associations between the feature and disease severity. The intensity of the color indicates the strength of association.