An integrated predictive model for Alzheimer’s disease progression from cognitively normal subjects using generated MRI and interpretable AI

Abstract Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that begins with subtle cognitive changes and advances to severe impairment. Early diagnosis is crucial for effective intervention and management. In this study, we propose an integrated framework that leverages ensemble t...

Full description

Saved in:
Bibliographic Details
Main Authors: Atefe Aghaei, Mohsen Ebrahimi Moghaddam
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-13478-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333050561789952
author Atefe Aghaei
Mohsen Ebrahimi Moghaddam
author_facet Atefe Aghaei
Mohsen Ebrahimi Moghaddam
author_sort Atefe Aghaei
collection DOAJ
description Abstract Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that begins with subtle cognitive changes and advances to severe impairment. Early diagnosis is crucial for effective intervention and management. In this study, we propose an integrated framework that leverages ensemble transfer learning, generative modeling, and automatic ROI extraction techniques to predict the progression of Alzheimer’s disease from cognitively normal (CN) subjects. Using the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, we employ a three-stage process: (1) estimating the probability of transitioning from CN to mild cognitive impairment (MCI) using ensemble transfer learning, (2) generating future MRI images using Transformer-based Generative Adversarial Network (ViT-GANs) to simulate disease progression after two years, and (3) predicting AD using a 3D convolutional neural network (CNN) with calibrated probabilities using isotonic regression and interpreting critical regions of interest (ROIs) with Gradient-weighted Class Activation Mapping (Grad-CAM). However, the proposed method has generality and may work when sufficient data for simulating brain changes after three years or more is available; in the training phase, regarding available data, brain changes after 2 years have been considered. Our approach addresses the challenge of limited longitudinal data by creating high-quality synthetic images and improving model transparency by identifying key brain regions involved in disease progression. The proposed method demonstrates high accuracy and F1-score, 0.85 and 0.86, respectively, in CN to AD prediction up to 10 years, offering a potential tool for early diagnosis and personalized intervention strategies in Alzheimer’s disease.
format Article
id doaj-art-ced44aa7255b484488589161964fa637
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ced44aa7255b484488589161964fa6372025-08-20T03:46:00ZengNature PortfolioScientific Reports2045-23222025-08-0115112310.1038/s41598-025-13478-2An integrated predictive model for Alzheimer’s disease progression from cognitively normal subjects using generated MRI and interpretable AIAtefe Aghaei0Mohsen Ebrahimi Moghaddam1Faculty of Computer Science and Engineering, Shahid Beheshti UniversityFaculty of Computer Science and Engineering, Shahid Beheshti UniversityAbstract Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that begins with subtle cognitive changes and advances to severe impairment. Early diagnosis is crucial for effective intervention and management. In this study, we propose an integrated framework that leverages ensemble transfer learning, generative modeling, and automatic ROI extraction techniques to predict the progression of Alzheimer’s disease from cognitively normal (CN) subjects. Using the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, we employ a three-stage process: (1) estimating the probability of transitioning from CN to mild cognitive impairment (MCI) using ensemble transfer learning, (2) generating future MRI images using Transformer-based Generative Adversarial Network (ViT-GANs) to simulate disease progression after two years, and (3) predicting AD using a 3D convolutional neural network (CNN) with calibrated probabilities using isotonic regression and interpreting critical regions of interest (ROIs) with Gradient-weighted Class Activation Mapping (Grad-CAM). However, the proposed method has generality and may work when sufficient data for simulating brain changes after three years or more is available; in the training phase, regarding available data, brain changes after 2 years have been considered. Our approach addresses the challenge of limited longitudinal data by creating high-quality synthetic images and improving model transparency by identifying key brain regions involved in disease progression. The proposed method demonstrates high accuracy and F1-score, 0.85 and 0.86, respectively, in CN to AD prediction up to 10 years, offering a potential tool for early diagnosis and personalized intervention strategies in Alzheimer’s disease.https://doi.org/10.1038/s41598-025-13478-2Alzheimer’s progression predictionMRIVit-GANAutomatic ROI extractionProbabilityEnsemble transfer learning
spellingShingle Atefe Aghaei
Mohsen Ebrahimi Moghaddam
An integrated predictive model for Alzheimer’s disease progression from cognitively normal subjects using generated MRI and interpretable AI
Scientific Reports
Alzheimer’s progression prediction
MRI
Vit-GAN
Automatic ROI extraction
Probability
Ensemble transfer learning
title An integrated predictive model for Alzheimer’s disease progression from cognitively normal subjects using generated MRI and interpretable AI
title_full An integrated predictive model for Alzheimer’s disease progression from cognitively normal subjects using generated MRI and interpretable AI
title_fullStr An integrated predictive model for Alzheimer’s disease progression from cognitively normal subjects using generated MRI and interpretable AI
title_full_unstemmed An integrated predictive model for Alzheimer’s disease progression from cognitively normal subjects using generated MRI and interpretable AI
title_short An integrated predictive model for Alzheimer’s disease progression from cognitively normal subjects using generated MRI and interpretable AI
title_sort integrated predictive model for alzheimer s disease progression from cognitively normal subjects using generated mri and interpretable ai
topic Alzheimer’s progression prediction
MRI
Vit-GAN
Automatic ROI extraction
Probability
Ensemble transfer learning
url https://doi.org/10.1038/s41598-025-13478-2
work_keys_str_mv AT atefeaghaei anintegratedpredictivemodelforalzheimersdiseaseprogressionfromcognitivelynormalsubjectsusinggeneratedmriandinterpretableai
AT mohsenebrahimimoghaddam anintegratedpredictivemodelforalzheimersdiseaseprogressionfromcognitivelynormalsubjectsusinggeneratedmriandinterpretableai
AT atefeaghaei integratedpredictivemodelforalzheimersdiseaseprogressionfromcognitivelynormalsubjectsusinggeneratedmriandinterpretableai
AT mohsenebrahimimoghaddam integratedpredictivemodelforalzheimersdiseaseprogressionfromcognitivelynormalsubjectsusinggeneratedmriandinterpretableai