Structure-Aware Temporal Modeling for Chronic Disease Progression Prediction

2025-08-20

AI Summary

To address the challenges of highly nonlinear symptom progression and insufficient modeling of multimodal temporal dependencies in Parkinson’s disease (PD) progression prediction, this paper proposes a unified framework integrating structural awareness with dynamic temporal modeling. We innovatively construct a symptom semantic graph to capture latent cross-dimensional symptom correlations and design a structure-aware gating mechanism that jointly fuses structural features extracted by graph neural networks (GNNs) with long-range temporal dynamics captured by Transformers. The model comprises three modules: symptom graph construction, structure-temporal joint encoding, and stage-aware prediction. Extensive experiments on a real-world longitudinal PD cohort demonstrate significant improvements over state-of-the-art baselines: +3.2% in AUC, −12.7% in RMSE, and +4.8% in IPW-F1. Our method accurately identifies critical progression stages and exhibits strong generalizability and scalability to varying graph structures.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Structured Learning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

This study addresses the challenges of symptom evolution complexity and insufficient temporal dependency modeling in Parkinson's disease progression prediction. It proposes a unified prediction framework that integrates structural perception and temporal modeling. The method leverages graph neural networks to model the structural relationships among multimodal clinical symptoms and introduces graph-based representations to capture semantic dependencies between symptoms. It also incorporates a Transformer architecture to model dynamic temporal features during disease progression. To fuse structural and temporal information, a structure-aware gating mechanism is designed to dynamically adjust the fusion weights between structural encodings and temporal features, enhancing the model's ability to identify key progression stages. To improve classification accuracy and stability, the framework includes a multi-component modeling pipeline, consisting of a graph construction module, a temporal encoding module, and a prediction output layer. The model is evaluated on real-world longitudinal Parkinson's disease data. The experiments involve comparisons with mainstream models, sensitivity analysis of hyperparameters, and graph connection density control. Results show that the proposed method outperforms existing approaches in AUC, RMSE, and IPW-F1 metrics. It effectively distinguishes progression stages and improves the model's ability to capture personalized symptom trajectories. The overall framework demonstrates strong generalization and structural scalability, providing reliable support for intelligent modeling of chronic progressive diseases such as Parkinson's disease.

Problem

• Predicting Parkinson's disease progression using multimodal clinical data
• Modeling structural relationships among symptoms with graph networks
• Capturing dynamic temporal features during chronic disease stages

Innovation

• Graph neural networks model symptom relationships
• Transformer architecture captures temporal disease dynamics
• Structure-aware gating mechanism fuses multimodal information