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

arXiv cs.CV / 4/9/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper presents a graph neural network model that predicts whether individuals with Alzheimer's-related cognitive impairment will transition to a more severe stage at their next clinical visit (CN, MCI, or AD).
It builds functional connectivity graphs from resting-state fMRI (rs-fMRI) and trains on 303 subjects, leveraging each subject’s full visit history rather than treating visits as isolated samples.
The approach uses an RNN component and adds visit-distance information to handle irregular time gaps between visits, enabling learning over non-uniform clinical follow-up schedules.
The model is reported to be robust to missing visits and achieves 82.9% accuracy overall, with 68.8% accuracy on the particularly challenging CN→MCI conversion task.
The authors argue that rs-fMRI-based prediction—potentially combined with other modalities—could support earlier identification of progression and enable timely interventions.

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.