Accelerating diagnosis of Parkinson's disease through risk prediction

Abstract

Background: Characterization of prediagnostic Parkinson's Disease (PD) and early prediction of subsequent development are critical for preventive interventions, risk stratification and understanding of disease pathology. This study aims to characterize the role of the prediagnostic period in PD and, using selected features from this period as novel interception points, construct a prediction model to accelerate the diagnosis in a real-world setting.

Methods: We constructed two sets of machine learning models: a retrospective approach highlighting exposures up to 5 years prior to PD diagnosis, and an alternative model that prospectively predicted future PD diagnosis from all individuals at their first diagnosis of a gait or tremor disorder, these being features that appeared to represent the initiation of a differential diagnostic window.

Results: We found many novel features captured by the retrospective models; however, the high accuracy was primarily driven from surrogate diagnoses for PD, such as gait and tremor disorders, suggesting the presence of a distinctive differential diagnostic period when the clinician already suspected PD. The model utilizing a gait/tremor diagnosis as the interception point, achieved a validation AUC of 0.874 with potential time compression to a future PD diagnosis of more than 300 days. Comparisons of predictive diagnoses between the prospective and prediagnostic cohorts suggest the presence of distinctive trajectories of PD progression based on comorbidity profiles.

Conclusions: Overall, our machine learning approach allows for both guiding clinical decisions such as the initiation of neuroprotective interventions and importantly, the possibility of earlier diagnosis for clinical trials for disease modifying therapies.

Keywords: Gait; Parkinson’s disease; Prediagnostic; Predictive medicine; Prodromal; Tremor.

Fig. 1

Area under the ROC Curve predicting PD onset at various points prior to PD diagnosis. a Logistic Regression vs. Neural Network in Claims b EMR vs. Claims Logistic Regression

Fig. 2

Frequency of phenotypes relative to PD diagnosis date (cases)/matched baseline date (controls). Each point represents the frequency of the phenotype among the population in the year defined at the point: a tremor frequency of 0.08 at day 730 implies that 8.0% of PD cases had a tremor diagnosis between 730 and 365 days prior to their PD diagnosis. The data in subfigures represent the population diagnosed with a (a) gait disorder, b tremor disorders, c constipation, or d breast cancer testing. Details of the ICD/CPT codes associated with each subfigure are presented in Supplementary Table 2