Predicting Alzheimer’s Disease Progression from Mild Cognitive Impairment via Automated Brain Age Modeling

Abstract

The early detection of individuals with Mild Cognitive Impairment (MCI) who are at high risk of developing Alzheimer’s Disease (AD) is important for proper clinical intervention and disease management. Studies show that there is a strong link between brain age, which is estimated from brain scan data, and actual chronological age. This difference is called the Brain Age Gap (BAG), and it acts as a useful biological marker for identifying people at risk of brain degeneration. This study aims to create an automated dual-network framework that predicts MCI subjects’ likelihood of converting to AD based on their structural magnetic resonance imaging (MRI) brain scans. The two networks will consist of (i) a three-dimensional convolutional neural network (CNN) model that predicts an estimated brain age based on the inputted MRI scan of a subject, and (ii) a risk prediction network that predicts probability of MCI-to-AD conversion by incorporating estimated brain age, BAG, and deep feature representations. The framework will be trained in sequential order using a longitudinal neuroimaging dataset. Results from the experiment indicate higher classification performance can be attained with the proposed dual-network architecture over current state-of-the-art single-stage classification methods or models without brain age. Furthermore, these results strongly support the use of brain age-based predictive features for early prediction of AD risk. The proposed method offers a fully automated and clinically interpretable solution for supporting early diagnosis and personalized intervention planning in Alzheimer’s disease.