Abstract            Volume:10  Issue-6  Year-2022         Original Research Articles

Online ISSN : 2347 - 3215 Issues : 12 per year Publisher : Excellent Publishers Email : editorijcret@gmail.com

Alzheimer's disease (AD) is a neurodegenerative condition that needs early and correct diagnosis for successful intervention. The goal of this work is to automate the diagnosis of Alzheimer's from MRI scans using a deep learning model that is a combination of LSTM-GRU and to encrypt patient data with AES encryption. Current techniques like SVM, CNN, and Random Forests have limitations when dealing with sequential data, overfitting, and weak generalization. The suggested framework combines both spatial and temporal information from MRI scans, overcoming these limitations by employing LSTM for temporal analysis and GRU for computational efficiency, while AES encryption provides data security. The procedure involves data collection, pre-processing with Z-score normalization, safe storage, classification using the hybrid model, and performance evaluation. The model achieved an accuracy of 99.20%, precision of 99.30%, recall of 99.10%, and F1-score of 99.20%, which is indicative of its viability for use in real-life clinical practice. Future improvement opportunities include the application of transfer learning and real-time data processing.

Download this article as