A Stage-Aware Mixture of Experts Framework for Neurodegenerative Disease Progression Modelling

2025-08-09

AI Summary

Modeling neurodegenerative diseases faces two key challenges: (1) sparse and irregular longitudinal neuroimaging data, and (2) dynamically evolving pathological mechanisms across disease stages. To address these, we propose the Stage-Aware Mixture of Experts (SME) model. SME employs a time-dependent expert weighting mechanism to jointly capture distinct pathological propagation dynamics—graph diffusion–dominant in early stages versus unknown biophysical processes in later stages. It integrates iterative dual optimization for estimating individual temporal positions, non-uniform graph neural diffusion (IGND), and a local neural response module, enabling flexible and interpretable spatiotemporal modeling of brain network evolution. Experiments demonstrate that SME significantly improves fitting accuracy under data sparsity, robustly reconstructs population-level disease progression trajectories, and uncovers stage-specific mechanistic transitions consistent with clinical cognition. Our work establishes a novel paradigm for modeling disease heterogeneity through stage-aware, mechanistically grounded neural dynamics.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• 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
• Web Mining and Content Analysis: Models for Web evolution
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

The long-term progression of neurodegenerative diseases is commonly conceptualized as a spatiotemporal diffusion process that consists of a graph diffusion process across the structural brain connectome and a localized reaction process within brain regions. However, modeling this progression remains challenging due to 1) the scarcity of longitudinal data obtained through irregular and infrequent subject visits and 2) the complex interplay of pathological mechanisms across brain regions and disease stages, where traditional models assume fixed mechanisms throughout disease progression. To address these limitations, we propose a novel stage-aware Mixture of Experts (MoE) framework that explicitly models how different contributing mechanisms dominate at different disease stages through time-dependent expert weighting.Data-wise, we utilize an iterative dual optimization method to properly estimate the temporal position of individual observations, constructing a co hort-level progression trajectory from irregular snapshots. Model-wise, we enhance the spatial component with an inhomogeneous graph neural diffusion model (IGND) that allows diffusivity to vary based on node states and time, providing more flexible representations of brain networks. We also introduce a localized neural reaction module to capture complex dynamics beyond standard processes.The resulting IGND-MoE model dynamically integrates these components across temporal states, offering a principled way to understand how stage-specific pathological mechanisms contribute to progression. The stage-wise weights yield novel clinical insights that align with literature, suggesting that graph-related processes are more influential at early stages, while other unknown physical processes become dominant later on.

Problem

• Modeling neurodegenerative disease progression with scarce longitudinal data
• Capturing complex pathological mechanisms across brain regions and stages
• Integrating time-dependent mechanisms via stage-aware expert weighting

Innovation

• Stage-aware Mixture of Experts for dynamic weighting
• Iterative dual optimization for temporal alignment
• Inhomogeneous graph neural diffusion for flexible modeling