Home / Current Issue / Paper 1717501
Early Detection of Alzheimer’s Disease Using Machine Learning
Subject area: Science,Engineering and Technology · Area of research: Engineering
DOI: https://doi.org/10.64388/IREV9I11-1717501
Abstract
Early detection of Alzheimer’s disease (AD) is critical for timely intervention and slowing disease progression. Manual analysis of MRI scans is labor-intensive and subject to inter-clinician variability. This paper presents an end-to-end deep learning system for automated classification of Alzheimer’s stages using brain MRI images. A Convolutional Neural Network (CNN) is trained to classify images into four categories: Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented, achieving a test accuracy of 99.84% on 1,276 held-out samples from the Kaggle Alzheimer MRI Dataset (6,376 images total). The system is deployed via a Streamlit web interface for real-time prediction, enhanced with Grad-CAM visualization to highlight discriminative brain regions. Batch processing and timestamped prediction history tracking are also supported. Experimental results demonstrate sub-second inference latency, confirming the system’s potential as a clinical decision-support tool.
Keywords
Alzheimer’s Disease, CNN, Deep Learning, Grad-CAM, MRI, Streamlit
How to cite this paper
@article{1717501,
author = {Om Patkar, Vedant Khorjekar, Rhitikesh Gaikwad, Prof. Salabha Jacob},
title = {Early Detection of Alzheimer’s Disease Using Machine Learning},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {1486-1489},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1717501.pdf},
abstract = {Early detection of Alzheimer’s disease (AD) is critical for timely intervention and slowing disease progression. Manual analysis of MRI scans is labor-intensive and subject to inter-clinician variability. This paper presents an end-to-end deep learning system for automated classification of Alzheimer’s stages using brain MRI images. A Convolutional Neural Network (CNN) is trained to classify images into four categories: Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented, achieving a test accuracy of 99.84% on 1,276 held-out samples from the Kaggle Alzheimer MRI Dataset (6,376 images total). The system is deployed via a Streamlit web interface for real-time prediction, enhanced with Grad-CAM visualization to highlight discriminative brain regions. Batch processing and timestamped prediction history tracking are also supported. Experimental results demonstrate sub-second inference latency, confirming the system’s potential as a clinical decision-support tool.},
keywords = {Alzheimer’s Disease, CNN, Deep Learning, Grad-CAM, MRI, Streamlit},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1717501}
}