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{166837,
        author = {Ms. Shivani Rai and Mr.Rajneesh Pachouri and Mr. Anurag Jain},
        title = {Advancements in Parkinson’s disease Detection Using Automated Analysis of Spiral Drawings},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {2},
        pages = {2228-2234},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=166837},
        abstract = {Parkinson's disease (PD) is a huge global health concern that is spreading to many different countries and is getting worse every day. Consequently, it is crucial to identify it early on, which has proven to be a difficult assignment for researchers because the disease's symptoms usually manifest in middle or late middle age. In this work, neural network models that can identify Parkinson's disease (PD) in its early stages are developed. Parkinson's disease (PD) is a common neurological illness that causes limb rigidity, tremor, and increasingly slow movement. It also causes gait abnormalities, such as stooped posture, shuffling steps, festination, freezing of gait, and falling. Prompt identification of Parkinson's disease (PD) allows for the prompt start of treatment, which lowers morbidity. The ageing population, which has a high prevalence of Parkinson's disease (PD), also frequently demonstrates growing gait slowness due to other conditions, such as joint osteoarthritis or sarcopenia. This makes it difficult to correctly diagnose PD, especially in the early stages of the disease. Therefore, it is essential to create a trustworthy and impartial technique to distinguish the gait features of Parkinson's disease from those of healthy senior people. In order to create the model, this project uses a variety of machine learning techniques, including adaptive boosting, RNN, convolutional deep neural networks, support vector machines, decision trees, convolutional neural networks, and linear regression. Its focus is on the Spiral Test difficulty symptoms in individuals affected by Parkinson's disease. A variety of criteria, including accuracy, receiver operating characteristic curve (ROC), sensitivity, precision, and specificity, are used to assess the performance of these classifiers. In order to forecast Parkinson's disease, the most crucial traits among all the features are finally found using the feature selection technique. },
        keywords = {Parkinson's disease, PD stage, IMU, neural network, gait.},
        month = {July},
        }