Alzheimer’s Disease Prediction and Diagnosis Using Machine Learning Techniques

Abstract

Alzheimer’s Disease (AD) is a medical condition that affects the human brain. It is a progressive neurodegenerative disorder that significantly impairs memory, cognitive, and executive functions, particularly among the elderly. Early and accurate diagnosis is essential for effective disease management and slowing its progression. Despite advances in predicting this disease, there is still a need to improve prediction. In this study, we propose a lightweight, custom convolutional neural network (CNN) model for multi-class classification of Alzheimer's disease stages using magnetic resonance images. The model achieved a test accuracy of 98.28%. The F1 scores for the four classes ranged from 0.96 to 0.99, while the average precision and recall were 0.98, demonstrating robust and balanced performance across all diagnostic categories. These results outperform many existing methods while maintaining computational efficiency and complexity-free performance. The proposed model provides an effective and scalable solution for early-stage Alzheimer's disease diagnosis from MRI scans, with potential integration into medical systems that support real-world clinical decisions.