Bayesian meta-learning for modeling Alzheimer's disease progression

2026-06-01

AI Summary

This work addresses the challenges of data sparsity and heterogeneity in predicting individual progression of Alzheimer’s disease. It proposes the first Bayesian meta-learning framework tailored to this task, integrating MRI scans with longitudinal clinical data to train a neural network that models conditional distributions over disease trajectories. The model dynamically generates personalized posterior distributions of disease severity scores without requiring retraining for new individuals, enabling robust long-term forecasting while mitigating overconfidence. Its computational complexity scales linearly with the number of historical observations. Evaluated on real-world ADNI data, the approach significantly outperforms both single-task models and deterministic meta-learners, demonstrating particularly strong performance in long-term progression prediction.

Abstract

Predicting whether an individual with Alzheimer's disease will experience mild or severe disease progression is essential for personalized treatment. Typically, practitioners seek to predict the distribution of a discrete disease score, conditional on an individual's current MRI volume and their historical disease trajectory. Classical statistical regression models and single-task neural networks are not well-suited for this purpose because fitting separate models is infeasible (since each individual typically has few observations), while ignoring individual-level correlation leads to poor generalization. Meta-learning, in contrast, provides a natural avenue to dynamically predict distributions without retraining and model nonlinear relationships between the outcome and covariates. Motivated by this, we propose a Bayesian meta-learner that is trained on multiple individuals but tailors the predictive disease score distribution to each individual's historical data. Our model predicts on unseen individuals without retraining, scales linearly with the number of historical observations, and is guaranteed to be less overconfident when predicting long-term disease scores compared to its deterministic counterpart. On real-world data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, our model achieves performance competitive with both single-task models and deterministic meta-learners, while substantially improving performance when predicting long-term disease progression.

Problem

• Alzheimer's disease
• disease progression prediction
• personalized treatment
• Bayesian meta-learning
• predictive modeling

Innovation

• Bayesian meta-learning
• Alzheimer's disease progression
• personalized prediction
• uncertainty quantification
• few-shot time-series modeling