STEP-PD: Stage-Aware and Explainable Parkinson's Disease Severity Classification Using Multimodal Clinical Assessments

TL;DR

This paper introduces STEP-PD, a machine learning framework that classifies Parkinson's disease severity using multimodal clinical assessments, achieving high accuracy and interpretability with SHAP explanations.

Contribution

It presents a novel, stage-aware classification method leveraging all follow-up assessments and explainability techniques for better PD severity prediction.

Findings

XGBoost achieved over 95% accuracy in binary classifications.

Three-class severity classification reached 94.14% accuracy and 0.8775 Macro-F1.

Explainability revealed a shift from motor to axial and balance features.

Abstract

Parkinson's disease (PD) is a progressive disorder in which symptom burden and functional impairment evolve over time, making severity staging essential for clinical monitoring and treatment planning. However, many computational studies emphasize binary PD detection and do not fully use repeated follow-up clinical assessments for stage-aware prediction. This study proposes STEP-PD, a severity-aware machine learning framework to classify PD severity using clinically interpretable boundaries. It leverages all available visits from the Parkinson's Progression Markers Initiative (PPMI) and integrates routinely collected subjective questionnaires and objective clinician-assessed measures. Disease severity is defined using Hoehn and Yahr staging and grouped into three clinically meaningful categories: Healthy, Mild PD (stages 1-2), and Moderate-to-Severe PD (stages 3-5). Three binary classification problems and a three-class severity task were evaluated using stratified cross-validation with imbalance-aware training. To enhance interpretability, SHAP was used to provide global explanations and local patient-level waterfall explanations. Across all tasks, XGBoost achieved the strongest and most stable performance, with accuracies of 95.48% (Healthy vs. Mild), 99.44% (Healthy vs. Moderate-to-Severe), and 96.78% (Mild vs. Moderate-to-Severe), and 94.14% accuracy with 0.8775 Macro-F1 for three-class severity classification. Explainability results highlight a shift from early motor features to progression-related axial and balance impairments. These findings show that multimodal clinical assessments within the PPMI cohort can support accurate and interpretable visit-level PD severity stratification.