Attention-Driven Multimodal Convolutional Networks for Early Alzheimer's Disease Identification

View at publisher Summarise with VIRAT
Authors: Shruti P, Rekha R, Isra Taroob I, Ragul Rishwanth P, Dhanush B R, Jayavasanth D
Cited by: 0
References: 25

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This study investigates the impact of attention mechanisms and multi-modal fusion on diagnostic model performance. Clinical and imaging data were evaluated using baseline models and enhanced with additive and self-attention techniques. The clinical model achieved 92 % accuracy, which improved to 96.62 % with additive attention. Similarly, the image model reached 96.54 % accuracy with self-attention. When both modalities were combined, the model attained the highest performance with 97.23 % accuracy and an F1 score of 0.95. These results demonstrate that integrating attention mechanisms and multi-modal fusion significantly enhances predictive accuracy, precision, and robustness, highlighting their potential for improving clinical decision support systems.

Fields of Study & Subjects

Dementia and Cognitive Impairment Research Artificial Intelligence in Healthcare Multimodal Machine Learning Applications

Publication details

Journal / source
International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS)
Pages
1–6
Publication date
8 January 2026
Language
EN