International Journal of Scientific Research and Engineering Development

An intelligent framework for identifying dyslexia using brain MRI data and cutting-edge machine learning techniques is presented in this paper. The suggested system analyzes extracted brain features and finds patterns linked to dyslexia using the TabNet model. It seeks to support early diagnosis and enhance clinical decision-making procedures in practical healthcare. The suggested system analyzes brain MRI data for dyslexia detection using an interpretable machine learning technique based on TabNet. The model finds important neural features that contribute to predictions by utilizing attention mechanisms. Behavioral data integration also improves personalization by facilitating precise classification and offering insightful information that promotes early diagnosis, successful intervention, and better learning outcomes for individuals.The system delivers accurate dyslexia detection results from MRI data showing high accuracy and F1-score performance according to the experimental findings. The TabNet model outperforms traditional methods because it delivers trustworthy predictions that can be understood by users to enhance diagnostic processes and clinical decision-making in actual medical environments.By combining interpretability and accuracy, the suggested system improves dyslexia detection and enables a deeper comprehension of the brain-based characteristics influencing predictions. It encourages early diagnosis and lessens reliance on subjective techniques. This method advances the use of explainable artificial intelligence in healthcare.

Prema.V, Spurgeon Williams.G, Suhirtha.CK, Vasudevan.S,"Interpretable Dyslexia Detection from Brain MRI Using Tab-Net Based Machine Learning" International Journal of Scientific Research and Engineering Development, V9(2): Page(1123-1129) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.