Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{194913,
        author = {Santhru P and Bharath N and Gunasekar S},
        title = {Medical Diagnosis Assistant using Fine Tuning Model},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {5776-5782},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194913},
        abstract = {In the fast growing clinical world , the rapid and accurate interpretation of Chest X-Rays is critical for diagnosing respiratory and cardiovascular pathologies; However the integration of Artificial Intelligence (AI) in the medical industry and also with the medical imaging often leads to limiting the clinical explainability, accuracy, diagnostic delays and cognitive fatigue among radiologist. This research help to overcome the limitations in the clinical world by providing explainable AI, GradCam and with the help of multi model like DenseNet(169), EfficientNet-B5 and VitBase and also our HybridModel these platform help to achieve high precision diagnosis. The core problem solution relies on integration on Explainable AI(XAI) through GradCam attention mapping with RAG that provides evidence based medical reasoning which gives us accurate results. The technical implementation is done using Fast API backend with 44 Specialised modules and a react based frontend dashboard managing 33 endpoints for seamless clinical workflow integration. The hybrid model which we created will give you committee of experts in regards of the results instead of single architecture diagnostic tool which will help in determining the results with more accuracy.},
        keywords = {Artificial Intelligence, GradCam, Explainable AI(XAI), Retrieval Augmented Generation (RAG), Vision Transformer (Vit), DenseNet(169), EfficientNet-B5.},
        month = {March},
        }