Predicting Alzheimer's disease progression using rs-fMRI and a history-aware graph neural network

2026-04-07

AI Summary

This study addresses the prediction of cognitive decline progression in Alzheimer’s disease patients—specifically, whether individuals will advance to a more impaired clinical stage (e.g., from cognitively normal [CN] to mild cognitive impairment [MCI]) at their next follow-up visit. To this end, we propose a novel temporal modeling framework that integrates complete irregular clinical histories with resting-state functional MRI (rs-fMRI)–derived functional connectivity maps by fusing graph neural networks (GNNs) and recurrent neural networks (RNNs). Our approach incorporates time-distance feature encoding to effectively handle missing data and non-uniform sampling intervals. The method achieves 82.9% accuracy in overall stage-transition prediction and 68.8% accuracy on the particularly challenging CN→MCI early-conversion task, significantly outperforming existing approaches and demonstrating the potential of rs-fMRI for early detection of Alzheimer’s disease progression.

Abstract

Alzheimer's disease (AD) is a neurodegenerative disorder that affects more than seven million people in the United States alone. AD currently has no cure, but there are ways to potentially slow its progression if caught early enough. In this study, we propose a graph neural network (GNN)-based model for predicting whether a subject will transition to a more severe stage of cognitive impairment at their next clinical visit. We consider three stages of cognitive impairment in order of severity: cognitively normal (CN), mild cognitive impairment (MCI), and AD. We use functional connectivity graphs derived from resting-state functional magnetic resonance imaging (rs-fMRI) scans of 303 subjects, each with a different number of visits. Our GNN-based model incorporates a recurrent neural network (RNN) block, enabling it to process data from the subject's entire visit history. It can also work with irregular time gaps between visits by incorporating visit distance information into our input features. Our model demonstrates robust predictive performance, even with missing visits in the subjects' visit histories. It achieves an accuracy of 82.9%, with an especially impressive accuracy of 68.8% on CN to MCI conversions - a task that poses a substantial challenge in the field. Our results highlight the effectiveness of rs-fMRI in predicting the onset of MCI or AD and, in conjunction with other modalities, could offer a viable method for enabling timely interventions to slow the progression of cognitive impairment.

Problem

• Alzheimer's disease
• disease progression prediction
• cognitive impairment
• rs-fMRI
• clinical transition

Innovation

• graph neural network
• resting-state fMRI
• Alzheimer's disease progression
• recurrent neural network
• longitudinal prediction