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

2026-04-19

AI Summary

This study addresses the limitation of existing Parkinson’s disease (PD) research, which predominantly focuses on binary classification and lacks fine-grained, interpretable staging of disease severity. To overcome this, the authors propose a stage-aware multi-task learning framework leveraging longitudinal multimodal clinical data from the PPMI cohort, categorizing subjects into three clinically meaningful stages—healthy, mild, and moderate-to-severe—according to the Hoehn & Yahr scale. For the first time, subjective questionnaire responses and objective clinical assessments are integrated within an XGBoost modeling pipeline, enhanced by stratified cross-validation and strategies to mitigate class imbalance. Model interpretability is provided through SHAP analysis at both global and individual levels. The approach achieves high performance across three binary classification tasks (95.48%, 99.44%, and 96.78% accuracy) and 94.14% accuracy (Macro-F1: 0.8775) in the three-class setting, demonstrating both strong predictive power and clinical interpretability.

Technology Category

• Machine Learning: Multimodal Learning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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.

Problem

• Parkinson's disease
• severity staging
• multimodal clinical assessments
• stage-aware classification
• disease progression

Innovation

• stage-aware classification
• multimodal clinical assessment
• explainable AI
• Parkinson's disease severity
• SHAP interpretability