Bayesian meta-learning for modeling Alzheimer's disease progression
2026-06-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionMachine Learning
AI summaryⓘ
The authors developed a new method to predict how Alzheimer's disease will progress in individuals using MRI data and their past health records. Unlike traditional methods that either treat each person separately or ignore individual differences, their approach learns from multiple people but adjusts predictions for each person’s history. This method can make predictions for new patients without needing to be retrained and is better at estimating long-term disease outcomes without being overly confident. Tests on real patient data showed it performs well compared to other models, especially for long-term predictions.
Alzheimer's diseasedisease progressionMRI volumemeta-learningBayesian meta-learnersingle-task neural networksstatistical regressionpredictive modelinglong-term prediction
Authors
Clara Hoffmann, Nadja Klein
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.