Predicting Parkinson's Disease Progression Using Statistical and Neural Mixed Effects Models: A Comparative Study on Longitudinal Biomarkers

2025-07-26

AI Summary

Modeling intra-individual correlations and patient-specific nonlinear progression patterns in longitudinal Parkinson’s disease (PD) prediction remains challenging. Method: We propose two novel deep learning–mixed effects hybrid models—Generalized Neural Mixed Model (GNMM) and Neural Mixed Effects (NME)—that relax the restrictive linearity assumption of conventional Linear Mixed Models (LMMs) on disease progression trajectories. Leveraging speech-based biomarkers as input, both models perform end-to-end learning of nonlinear Unified Parkinson’s Disease Rating Scale (UPDRS) dynamics per individual. Results: Evaluated on the Oxford PD Remote Digital Monitoring dataset, our models achieve high-accuracy prediction of total UPDRS scores. Compared to LMMs, they significantly improve predictive performance while preserving the interpretability and statistical rigor of mixed-effects frameworks alongside the representational power of deep learning. These advances provide a robust, personalized, and interpretable tool for remote PD monitoring and clinical trial enrichment.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Predicting Parkinson's Disease (PD) progression is crucial, and voice biomarkers offer a non-invasive method for tracking symptom severity (UPDRS scores) through telemonitoring. Analyzing this longitudinal data is challenging due to within-subject correlations and complex, nonlinear patient-specific progression patterns. This study benchmarks LMMs against two advanced hybrid approaches: the Generalized Neural Network Mixed Model (GNMM) (Mandel 2021), which embeds a neural network within a GLMM structure, and the Neural Mixed Effects (NME) model (Wortwein 2023), allowing nonlinear subject-specific parameters throughout the network. Using the Oxford Parkinson's telemonitoring voice dataset, we evaluate these models' performance in predicting Total UPDRS to offer practical guidance for PD research and clinical applications.

Problem

• Compare models for predicting Parkinson's Disease progression
• Evaluate longitudinal voice biomarkers for UPDRS score tracking
• Address nonlinear patient-specific patterns in PD progression

Innovation

• Hybrid LMMs and neural networks for PD progression
• Neural networks embedded in GLMM structure
• Nonlinear subject-specific parameters in NME model