Uncertainty Quantification in Alzheimer's Disease Progression Modeling

TL;DR

This paper evaluates various uncertainty quantification methods like MC Dropout, Variational Inference, MCMC, and Ensemble Learning for Alzheimer's disease progression prediction, highlighting their calibration and accuracy under noisy data.

Contribution

It compares multiple uncertainty estimation techniques in Alzheimer's progression modeling, demonstrating their effectiveness and calibration capabilities.

Findings

MC Dropout and MCMC produce well-calibrated predictions

Ensemble Learning also performs effectively

Methods handle noisy training data well

Abstract

With the increasing number of patients diagnosed with Alzheimer's Disease, prognosis models have the potential to aid in early disease detection. However, current approaches raise dependability concerns as they do not account for uncertainty. In this work, we compare the performance of Monte Carlo Dropout, Variational Inference, Markov Chain Monte Carlo, and Ensemble Learning trained on 512 patients to predict 4-year cognitive score trajectories with confidence bounds. We show that MC Dropout and MCMC are able to produce well-calibrated, and accurate predictions under noisy training data.