Hamzat, Babatunde, Pokhrel, Sangita ORCID: https://orcid.org/0009-0008-2092-7029 and Ganesan, Swathi ORCID: https://orcid.org/0000-0002-6278-2090 (2025) Early prediction of Alzheimer’s disease using machine learning algorithm: A convolutional neural network approach. Brain & Heart.

Preview

Text manuscript_bh05833.pdf - Published Version Available under License Creative Commons Attribution. Download (4MB) | Preview

Abstract

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that severely impacts memory and cognitive functions. Early diagnosis remains crucial for timely intervention and care. This research aims to explore the use of artificial intelligence, specifically deep learning, for the early prediction and Classification of AD using structural magnetic resonance imaging (MRI) images. A dataset comprising approximately 44,000 brain MRI images with four diagnostic classes (mild, moderate, severe, and very severe dementia) was used to train and evaluate multiple convolutional neural network (CNN) architectures. Three deep learning models were developed and tested: A custom CNN built from scratch, a spatial-channel convolutional attention network (SCCAN), and a pre-trained Visual Geometry Group VGG16 model using transfer learning. The methodology included extensive preprocessing, data augmentation, normalization, and a train–validation–test split to ensure robust performance. Evaluation metrics such as accuracy, precision, recall, F1-score, and confusion matrices were used to assess classification efficacy. Among the models tested, the Visual Geometry Group VGG16 model achieved the highest classification accuracy, closely followed by the SCCAN, while the custom CNN demonstrated competitive performance with fewer layers. Grad-CAM visualizations were integrated to provide insight into model decision-making, enhancing interpretability. The results confirm the
effectiveness of deep learning in classifying early AD stages with high accuracy and support its integration into clinical diagnostic tools. However, the study also identifies limitations, including dataset diversity, class imbalance, and generalizability across diverse populations. Future research should consider using larger, multi-center datasets (including positron emission tomography and electroencephalography modalities). This project demonstrates that deep learning can offer reliable, scalable, and interpretable solutions for the early detection of AD, potentially transforming the diagnostic pathway and enabling earlier therapeutic interventions.

Item Type:	Article
Status:	Published
DOI:	10.36922/BH025310043
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76.9.H85 Human-Computer Interaction; Virtual Reality; Mixed Reality; Augmented Reality ; Extended Reality T Technology > T Technology (General)
School/Department:	London Campus
URI:	https://ray.yorksj.ac.uk/id/eprint/13284

University Staff: Request a correction | RaY Editors: Update this record