A Multimodal Deep Learning Framework for Early Detection of Alzheimer’s Disease

Alzheimer’s Disease (AD) is a progressive neurodegenerative disorder that severely impacts cognitive function and quality of life. Early diagnosis, particularly in the Mild Cognitive Impairment (MCI) stage, is essential for effective intervention and disease management. In recent years, Artificial Intelligence (AI) has emerged as a powerful tool in analyzing complex biomedical data for early detection of AD. This study proposes a multimodal deep learning framework that combines ۳D Convolutional Neural Networks (۳D-CNN) for MRI image analysis with Long Short-Term Memory (LSTM) networks for processing sequential cognitive data. The model integrates spatial and temporal features to classify subjects as cognitively normal, MCI, or AD. Experiments conducted on the ADNI dataset demonstrate that the proposed model achieves high classification accuracy (۹۲.۶%) and area under the ROC curve (AUC = ۰.۹۷۲), outperforming traditional machine learning and single-modality deep learning approaches. The key innovation of this study lies in leveraging temporal sequences of extracted features instead of static images. This approach enables the model to capture hidden patterns in the progression of the disease more effectively, resulting in significantly improved performance in early Alzheimer’s detection compared to conventional image-based methods.

Keywords:

alzheimer’s disease , mild cognitive impairment , artificial intelligence , deep learning , multimodal learning , MRI analysis , cognitive assessment