Temporally Detailed Hypergraph Neural ODEs for Type 2 Diabetes Progression Modeling

2025-10-20

AI Summary

Modeling the continuous-time dynamics of type 2 diabetes (T2D) and its cardiovascular complications from irregularly sampled electronic health records (EHRs) remains challenging due to heterogeneous disease progression patterns and complex, nonlinear interdependencies among clinical biomarkers. Method: We propose a novel framework integrating temporal hypergraphs with neural ordinary differential equations (Neural ODEs). Specifically, we construct a clinical-pathway-driven temporal hypergraph and design a learnable hypergraph Laplacian operator to jointly capture nonlinear, multi-pathway dependencies among disease markers. Neural ODEs enable fine-grained, continuous-time modeling of patient-specific heterogeneity—including varying progression speeds and trajectories. Contribution/Results: Evaluated on two real-world EHR datasets, our method significantly outperforms state-of-the-art baselines in both complication risk prediction accuracy and temporal dynamic inference consistency. It establishes a new paradigm for personalized, continuous-time disease progression modeling grounded in structured clinical knowledge and differentiable dynamics.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs 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

Disease progression modeling aims to characterize and predict how a patient's disease complications worsen over time based on longitudinal electronic health records (EHRs). Accurate modeling of disease progression, such as type 2 diabetes, can enhance patient sub-phenotyping and inform effective and timely interventions. However, the problem is challenging due to the need to learn continuous-time dynamics of progression patterns based on irregular-time event samples and patient heterogeneity (eg different progression rates and pathways). Existing mechanistic and data-driven methods either lack adaptability to learn from real-world data or fail to capture complex continuous-time dynamics on progression trajectories. To address these limitations, we propose Temporally Detailed Hypergraph Neural Ordinary Differential Equation (TD-HNODE), which represents disease progression on clinically recognized trajectories as a temporally detailed hypergraph and learns the continuous-time progression dynamics via a neural ODE framework. TD-HNODE contains a learnable TD-Hypergraph Laplacian that captures the interdependency of disease complication markers within both intra- and inter-progression trajectories. Experiments on two real-world clinical datasets demonstrate that TD-HNODE outperforms multiple baselines in modeling the progression of type 2 diabetes and related cardiovascular diseases.

Problem

• Model continuous-time disease progression from irregular EHR data
• Capture patient heterogeneity in diabetes progression pathways
• Learn complex interdependencies across disease complication trajectories

Innovation

• Hypergraph Neural ODE framework for continuous-time dynamics
• Learnable TD-Hypergraph Laplacian captures interdependency markers
• Models progression on clinically recognized trajectories via hypergraph