GAN-Enhanced Multimodal Framework for Explainable Alzheimer’s Disease Detection and Progression Prediction

DOI

10.2991/978-94-6239-693-7_28How to use a DOI?

Keywords

Alzheimer’s disease; multimodal deep learning; generative adversarial networks; medical image analysis; explainable artificial intelligence; progression prediction

Abstract

Alzheimer’s disease refers to a progressive the neuro degenerative condition that causes an irreversible deterioration in memory, reasoning, and cognitive functions, presents great problems to patients, families, and the health care system. The effective clinical management of the disease requires accurate diagnosis of the disease at an early phase and effective monitoring of the disease progression. In many cases, traditional methods of diagnosis rely on the use of either neuroimaging or clinical measurements, which might not be sufficient to reflect the heterogeneous and complicated nature of the disease. The current project offers a multimodal model of learning to identify cases of Alzheimer disease and predict its progression through a combination of structural data with magnetic resonance images and clinical and cognitive data-points. A combination of several sources of information will help to represent the tendencies of the disease more comprehensively. As a solution, a generative model is utilized to increase the diversity of data to overcome the problem of the lack of training data and the lack of classes that are typically present in medical datasets. Cognitive stage is classified by extracting meaningful features of imaging data and clinical attributes using deep learning methods and fusing them. Moreover, longitudinal analysis is also added to assist in the prediction of disease progression with time. An interpretability mechanism is provided to give a visual understanding of the brain areas that affect model predictions to enhance clinical usability. The suggested framework is intended to promote the correct diagnosis, progression analysis, and provide clear decision support, which is why it can be regarded as appropriate to help clinicians in the assessment of the Alzheimer disease.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Pochimireddy Divyarupa
AU  - Chengamma Chitteti
AU  - M. Dharani
AU  - Vavilthota Uday
AU  - Bathula Manoj
AU  - P. Naga Maheswara Reddy
PY  - 2026
DA  - 2026/06/16
TI  - GAN-Enhanced Multimodal Framework for Explainable Alzheimer’s Disease Detection and Progression Prediction
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 265
EP  - 275
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_28
DO  - 10.2991/978-94-6239-693-7_28
ID  - Divyarupa2026
ER  -