Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SCOPE-PD: Explainable AI on Subjective and Clinical Objective Measurements of Parkinson's Disease for Precision Decision-Making

Md Mezbahul Islam, John Michael Templeton, Masrur Sobhan, Christian Poellabauer, Ananda Mohan Mondal

TL;DR

This paper addresses the challenge of early Parkinson's disease diagnosis by integrating subjective patient-reported data with objective clinician assessments into a multimodal, explainable AI framework called SCOPE-PD. Using the PPMI baseline dataset, it builds and compares five ML models across subjective, objective, and combined feature sets, with SHAP used to provide local and global explanations of predictions. Random Forest on the combined dataset delivers the highest performance (accuracy ≈ 0.987 with near-perfect AUC values) and reveals tremor, bradykinesia, and facial expression as key contributors, while SHAP explanations translate these signals into interpretable risk weights for individuals. The work demonstrates how explainable AI can enhance clinical decision-making in PD by delivering accurate predictions alongside clinically meaningful, patient-specific rationales, though it notes the need for external validation and longitudinal data before deployment.

Abstract

Parkinson's disease (PD) is a chronic and complex neurodegenerative disorder influenced by genetic, clinical, and lifestyle factors. Predicting this disease early is challenging because it depends on traditional diagnostic methods that face issues of subjectivity, which commonly delay diagnosis. Several objective analyses are currently in practice to help overcome the challenges of subjectivity; however, a proper explanation of these analyses is still lacking. While machine learning (ML) has demonstrated potential in supporting PD diagnosis, existing approaches often rely on subjective reports only and lack interpretability for individualized risk estimation. This study proposes SCOPE-PD, an explainable AI-based prediction framework, by integrating subjective and objective assessments to provide personalized health decisions. Subjective and objective clinical assessment data are collected from the Parkinson's Progression Markers Initiative (PPMI) study to construct a multimodal prediction framework. Several ML techniques are applied to these data, and the best ML model is selected to interpret the results. Model interpretability is examined using SHAP-based analysis. The Random Forest algorithm achieves the highest accuracy of 98.66 percent using combined features from both subjective and objective test data. Tremor, bradykinesia, and facial expression are identified as the top three contributing features from the MDS-UPDRS test in the prediction of PD.

SCOPE-PD: Explainable AI on Subjective and Clinical Objective Measurements of Parkinson's Disease for Precision Decision-Making

TL;DR

This paper addresses the challenge of early Parkinson's disease diagnosis by integrating subjective patient-reported data with objective clinician assessments into a multimodal, explainable AI framework called SCOPE-PD. Using the PPMI baseline dataset, it builds and compares five ML models across subjective, objective, and combined feature sets, with SHAP used to provide local and global explanations of predictions. Random Forest on the combined dataset delivers the highest performance (accuracy ≈ 0.987 with near-perfect AUC values) and reveals tremor, bradykinesia, and facial expression as key contributors, while SHAP explanations translate these signals into interpretable risk weights for individuals. The work demonstrates how explainable AI can enhance clinical decision-making in PD by delivering accurate predictions alongside clinically meaningful, patient-specific rationales, though it notes the need for external validation and longitudinal data before deployment.

Abstract

Parkinson's disease (PD) is a chronic and complex neurodegenerative disorder influenced by genetic, clinical, and lifestyle factors. Predicting this disease early is challenging because it depends on traditional diagnostic methods that face issues of subjectivity, which commonly delay diagnosis. Several objective analyses are currently in practice to help overcome the challenges of subjectivity; however, a proper explanation of these analyses is still lacking. While machine learning (ML) has demonstrated potential in supporting PD diagnosis, existing approaches often rely on subjective reports only and lack interpretability for individualized risk estimation. This study proposes SCOPE-PD, an explainable AI-based prediction framework, by integrating subjective and objective assessments to provide personalized health decisions. Subjective and objective clinical assessment data are collected from the Parkinson's Progression Markers Initiative (PPMI) study to construct a multimodal prediction framework. Several ML techniques are applied to these data, and the best ML model is selected to interpret the results. Model interpretability is examined using SHAP-based analysis. The Random Forest algorithm achieves the highest accuracy of 98.66 percent using combined features from both subjective and objective test data. Tremor, bradykinesia, and facial expression are identified as the top three contributing features from the MDS-UPDRS test in the prediction of PD.
Paper Structure (14 sections, 1 equation, 5 figures, 3 tables)

This paper contains 14 sections, 1 equation, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Dataset and Methodology
  3. Data Description
  4. Data Preprocessing
  5. Handling missing data
  6. Converting survey responses into feature values
  7. Normalizing feature values
  8. Classification Algorithms for PD Prediction
  9. Model Explainability using SHAP
  10. Results and Discussion
  11. Experimental Results of Machine Learning Models
  12. Interpretation of ML Predictions for PD
  13. Discussion
  14. Conclusion

Figures (5)

  • Figure 1: Overall Study Framework including Data Description, Data Preprocessing, Classification Algorithms, and Explanation Technique and Precision Clinical Decision. EPW: Epworth Sleepiness Scale; MDS-UPDRS: Movement Disorder Society Unified Parkinson's Disease Rating Scale; REM: Rapid Eye Movement; SCOPA-AUT: Scales for Outcomes in Parkinson’s disease - Autonomic Dysfunction; QUIP: Questionnaire for Impulsive-Compulsive Disorders; LN: Letter-Number; MOCA: Montreal Cognitive Assessment.
  • Figure 2: Cohort description after data preprocessing.
  • Figure 3: Out-of-Fold (OOF) confusion matrix (normalized) for the best ML model. RF achieved the highest accuracy with all three types of features—subjective, objective, and combined.
  • Figure 4: Global feature contribution: Top 10 features contributing towards HC and PD cohorts. a. Subjective features. b. Objective features. c. Combined features.
  • Figure 5: Local feature contribution: Top 10 local features contributing to a specific PD patient.