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

TL;DR

This paper introduces a novel operator learning framework that models personalized Alzheimer's disease progression by capturing complex brain dynamics from multimodal data, enabling accurate predictions and therapeutic simulations.

Contribution

It develops a patient-specific operator learning approach using neural operators and geometry-aware bases for personalized AD modeling, surpassing existing methods.

Findings

Achieves over 90% prediction accuracy across biomarkers.

Outperforms existing models in forecasting disease trajectories.

Enables simulation of therapeutic interventions and clinical trials.

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.