Learning Patient-Specific Spatial Biomarker Dynamics via Operator Learning for Alzheimer's Disease Progression

2025-07-21

AI Summary

Alzheimer’s disease (AD) progression prediction faces challenges including strong inter-individual dynamic heterogeneity, difficulty in fusing longitudinal multimodal data, and limited model interpretability. To address these, we propose a neural operator–based personalized disease modeling framework: (i) leveraging Laplacian eigenfunctions as geometric bases to explicitly encode structural brain geometry priors; (ii) introducing patient-specific disease operators that bypass reliance on pre-specified differential equations; and (iii) establishing a digital twin architecture integrating longitudinal neuroimaging, biomarkers, and clinical data for spatiotemporal dynamical modeling. Our method achieves >90% prediction accuracy across key AD biomarkers—including amyloid-β (Aβ), phosphorylated tau (p-tau), and regional atrophy rates—significantly outperforming state-of-the-art approaches. It enables robust individualized trajectory forecasting and facilitates in silico therapeutic intervention trials.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Alzheimer's disease (AD) is a complex, multifactorial neurodegenerative disorder with substantial heterogeneity in progression and treatment response. Despite recent therapeutic advances, predictive models capable of accurately forecasting individualized disease trajectories remain limited. Here, we present a machine learning-based operator learning framework for personalized modeling of AD progression, integrating longitudinal multimodal imaging, biomarker, and clinical data. Unlike conventional models with prespecified dynamics, our approach directly learns patient-specific disease operators governing the spatiotemporal evolution of amyloid, tau, and neurodegeneration biomarkers. Using Laplacian eigenfunction bases, we construct geometry-aware neural operators capable of capturing complex brain dynamics. Embedded within a digital twin paradigm, the framework enables individualized predictions, simulation of therapeutic interventions, and in silico clinical trials. Applied to AD clinical data, our method achieves high prediction accuracy exceeding 90% across multiple biomarkers, substantially outperforming existing approaches. This work offers a scalable, interpretable platform for precision modeling and personalized therapeutic optimization in neurodegenerative diseases.

Problem

• Predict individualized Alzheimer's disease progression trajectories
• Model patient-specific spatial biomarker dynamics
• Enable personalized therapeutic intervention simulations

Innovation

• Learns patient-specific disease operators dynamically
• Uses Laplacian eigenfunction bases for brain dynamics
• Enables digital twin paradigm for personalized predictions