Interpretable Symptom-Based Machine Learning for Parkinson's Disease Prediction: A Feasibility Study

Background: Parkinson's disease (PD) has a prolonged prodromal phase during which non-motor symptoms (NMS) may emerge years before the appearance of classical motor signs. This makes NMS a promising and clinically accessible source of information for early risk stratification. Objective: In this study, we investigated whether NMS alone can serve as reliable predictors of PD risk using clinical data from the Parkinson's Progression Markers Initiative (PPMI) cohort. Methods: We developed a stacked ensemble machine learning framework that integrates feature-level modelling, a global multivariate model, and a patient-similarity component to capture complementary patterns within NMS profiles. The model was trained using leakage-controlled patient-level validation and evaluated on an independent held-out test set. Results: The final ensemble achieved strong predictive performance, with an area under the ROC curve of 0.955, sensitivity of 0.929, and specificity of 0.900. Explainability analysis further showed that olfactory dysfunction, gastrointestinal symptoms, urinary and other autonomic features, and selected cognitive measures were among the most influential predictors. These findings support the hypothesis that NMS are not merely associated features of PD, but can function as meaningful predictors of disease risk even without imaging or biomarker inputs. Additionally, the final validated model is implemented as a web-based research prototype to demonstrate real-time translational feasibility. Conclusion: Overall, this study highlights the predictive value of NMS for PD risk assessment and supports their use in research-oriented early screening frameworks.