Copyright © 2025 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{188829,
        author = {ASHWINI},
        title = {A Novel Method to Predict Knee Osteoarthritis Progression on MRI Using Machine Learning Methods.},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {3518-3521},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188829},
        abstract = {Knee osteoarthritis (OA) is a degenerative musculoskeletal disorder that significantly affects mobility and quality of life, particularly among elderly and overweight populations. Early identification and grading of OA progression are vital for planning timely interventions and preventing long-term disability. This paper proposes a deep-learning-driven approach for automatic detection and severity prediction of knee OA from MRI and X-ray imaging. A curated dataset comprising over 8,000 images categorized into five severity classes—normal, doubtful, mild, moderate, and severe—was used. Mobilenet and VGG16 architectures were evaluated for classification, combined with extensive image augmentation to enhance robustness. Experimental results demonstrate an accuracy range of 72.5%–100% across tasks, while a force-plate-based supplementary feature extraction method achieved 91% accuracy in early-stage OA detection. This study highlights the potential of machine learning for rapid, objective, and reproducible OA assessment, supporting clinicians in early diagnosis and treatment planning.},
        keywords = {},
        month = {December},
        }