Data-driven spatiotemporal modeling reveals personalized trajectories of cortical atrophy in Alzheimer's disease

TL;DR

This study introduces a personalized graph-based dynamical model that predicts individual cortical atrophy trajectories in Alzheimer's disease, outperforming existing benchmarks and revealing distinct progression patterns.

Contribution

The paper presents a novel personalized spatiotemporal modeling approach using brain graphs to forecast Alzheimer's disease progression at the individual level.

Findings

Accurately predicts amyloid-beta, tau, neurodegeneration, and cognition biomarkers.

Identifies distinct disease progression subtypes.

Highlights regional brain vulnerabilities consistent with known patterns.

Abstract

Alzheimer's disease (AD) is characterized by the progressive spread of pathology across brain networks, yet forecasting this cascade at the individual level remains challenging. We present a personalized graph-based dynamical model that captures the spatiotemporal evolution of cortical atrophy from longitudinal MRI and PET data. The approach constructs individualized brain graphs and learns the dynamics driving regional neurodegeneration. Applied to 1,891 participants from the Alzheimer's Disease Neuroimaging Initiative, the model accurately predicts key AD biomarkers -- including amyloid-beta, tau, neurodegeneration, and cognition -- outperforming clinical and neuroimaging benchmarks. Patient-specific parameters reveal distinct progression subtypes and anticipate future cognitive decline more effectively than standard biomarkers. Sensitivity analysis highlights regional drivers of disease spread, reproducing known temporolimbic and frontal vulnerability patterns. This network-based digital twin framework offers a quantitative, personalized paradigm for AD trajectory prediction, with implications for patient stratification, clinical trial design, and targeted therapeutic development.