International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 186 - Number 75 |
Year of Publication: 2025 |
Authors: Sujan Aryal |
![]() |
Sujan Aryal . Early-Stage Alzheimer’s Disease Prediction using MRI -based Data: A Multimodal Deep Learning Approach. International Journal of Computer Applications. 186, 75 ( Mar 2025), 26-31. DOI=10.5120/ijca2025924640
Alzheimer's Disease (AD) is a progressive neurological condition characterized by cognitive deterioration and memory impairment. Prompt identification is essential for timely intervention, facilitating more efficient management and treatment approaches. Conventional diagnostic approaches depend on cognitive evaluations and clinical assessments, which frequently do not identify Alzheimer's disease in its initial stages. Deep learning has emerged as an effective method for automating the diagnosis of Alzheimer's disease via brain MRI data. This study introduces a deep learning framework aimed at detecting early-stage Alzheimer’s by utilizing MRI data to improve accuracy and facilitate prompt intervention. The dataset comprises 6,400 MRI scans categorized into four different groups: Mild Demented, Moderate Demented, Non-Demented, and Very Mild Demented. Carefully comparing most of the models such as VGG16, VGG19, ResNet, MobileNetV2, InceptionV3, DenseNet169, and EfficientNetB0 and fine-tuning and mitigating overfitting custom models, the final model achieved a weighted F1 score of 0.99%, indicating potential for substantial enhancement as an optimal predictor or classifier of MRI scans and the results also suggest that its effectiveness in promoting early diagnosis for patients with Alzheimer's disease.