Revolutionizing Alzheimer’s Diagnosis: A Hybrid Deep Learning Approach for Enhanced MRI Analysis. In Proceedings of the Americas Conference on Information Systems

This study addresses the urgent need for more accurate and accessible diagnostic tools for Alzheimer’s Disease (AD), a neurodegenerative disorder marked by progressive cognitive decline. Current diagnostic methods are often invasive, costly, and reliant on manual interpretation of neuroimaging data. To overcome these challenges, the research introduces a hybrid deep learning framework that integrates EfficientNetB0 with Convolutional Neural Networks (CNN) to analyze MRI scans automatically.Drawing on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset of over 200 MRI scans and clinical records, the model demonstrated superior performance compared to existing approaches. It effectively detected hallmark AD features such as amyloid beta plaques and neurofibrillary tangles, achieving higher accuracy and diagnostic efficiency.The findings highlight the transformative potential of AI-driven methods in medical imaging, particularly for clinical environments with limited resources. Beyond advancing early detection, the work opens avenues for multimodal data integration and improved model interpretability in future studies.Keywords: Alzheimer’s Disease, Deep Learning, MRI, EfficientNetB0, Convolutional Neural Networks