EUVIMEDEUVIMED entdecken
Crossref

A Novel Multistage Attention‐Enhanced Mixture of Experts Model for Alzheimer's Disease Diagnosis

Muhammad John Abbas, Muhammad Attique Khan, Veena Dillshad, Ahmed Ibrahim Alzahrani, Nasser Alalwan, Ali Alamer, Yunyoung Nam, Amir Hussain

Expert Systems · 2026-03 · 43 (3)

DOI: 10.1111/exsy.70223 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Expert Systems, online erschienen am 10.02.2026. Verfasst von Muhammad John Abbas und 7 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 83 Literaturangaben. Gefördert von: Ministry of Science and ICT, South Korea, King Saud University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Alzheimer's Disease (AD) is a progressive neurodegenerative disease diagnosed through cognitive impairment, and an early diagnosis is essential to improve treatment and care options. Current diagnostic approaches of AD, such as neuroimaging, cognitive assessments and biomarker research, are lengthy, vague and not sufficient to assess the early stages of AD. To address these problems, we introduced a novel deep learning model, ‘NeuroMixFormer’, which is based on a mixture‐of‐experts architecture for AD classification from MRI. The proposed multistage architecture employs a dynamic routing mechanism and four expert blocks per stage, each integrating dense connectivity with a spatial and channel attention module for feature extraction. To improve early feature learning, auxiliary classifiers are incorporated at intermediate stages of training. Evaluations on three datasets (ADNI, Mendeley and Kaggle Augmented Alzheimer's MRI) demonstrated the proposed model's superior performance over existing deep learning architectures and state‐of‐the‐art methods, achieving up to 99.48% accuracy on the Kaggle dataset, 90.28% on the Mendeley dataset and 99.86% on the ADNI dataset, respectively. Ablation studies confirmed the importance of dual‐attention mechanisms, and expert routing analysis showed clear specialisation patterns across AD stages, improving both classification accuracy and interpretability. These results underscore the effectiveness and generalisability of NeuroMixFormer in automated dementia detection, highlighting its potential to support early and precise AD diagnosis. However, the high computational cost and inference time associated with this high accuracy limit the practicality of the proposed approach in clinical settings.

Förderung

  • Ministry of Science and ICT, South Korea
  • King Saud University

Zitieren

APA

Abbas, M. J., Khan, M. A., Dillshad, V., Alzahrani, A. I., Alalwan, N., Alamer, A., Nam, Y., & Hussain, A. (2026). A Novel Multistage Attention‐Enhanced Mixture of Experts Model for Alzheimer's Disease Diagnosis. Expert Systems, 43(3). https://doi.org/10.1111/exsy.70223

Vancouver

Abbas MJ, Khan MA, Dillshad V, Alzahrani AI, Alalwan N, Alamer A, et al. A Novel Multistage Attention‐Enhanced Mixture of Experts Model for Alzheimer's Disease Diagnosis. Expert Systems. 2026;43(3). doi:10.1111/exsy.70223

BibTeX
@article{Abbas2026,
  author = {Abbas, Muhammad John and Khan, Muhammad Attique and Dillshad, Veena and Alzahrani, Ahmed Ibrahim and Alalwan, Nasser and Alamer, Ali and Nam, Yunyoung and Hussain, Amir},
  title = {A Novel Multistage Attention‐Enhanced Mixture of Experts Model for Alzheimer's Disease Diagnosis},
  journal = {Expert Systems},
  year = {2026},
  volume = {43},
  number = {3},
  doi = {10.1111/exsy.70223}
}
Kostenlos starten →