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{190756,
        author = {AISHWARYA B R and VIDYASHREE Y C and Nishanth S},
        title = {Quantitative Spiral Pattern Analysis for Parkinson’s Disease Diagnosis Using ML Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {4954-4959},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190756},
        abstract = {Parkinson’s Disease (PD) is a progressive neurodegenerative disorder that primarily affects motor function, often remaining undiagnosed in its early stages due to subtle and gradual symptom onset. Early detection is critical for timely clinical intervention and effective disease management. This paper presents an automated machine learning–based approach for early Parkinson’s Disease detection using spiral drawing analysis, a clinically established assessment for evaluating fine motor control. Spiral drawings collected from both healthy individuals and Parkinson’s patients are subjected to comprehensive preprocessing steps, including resizing, grayscale conversion, noise reduction, normalization, and data augmentation to enhance robustness and reduce variability. A compact and regularized Convolutional Neural Network (CNN) is designed to learn discriminative patterns associated with Parkinsonian motor impairments, such as tremor-induced oscillations, irregular stroke dynamics, and structural deviations in spiral geometry. Experimental evaluation demonstrates that the proposed model effectively differentiates between normal and Parkinson-affected spiral drawings, achieving reliable classification performance and strong generalization across augmented datasets. The proposed framework offers a non-invasive, cost-effective, and easily deployable screening solution that can support clinicians in early Parkinson’s Disease identification and has strong potential for integration into telemedicine and remote health monitoring systems.},
        keywords = {Parkinson’s Disease Detection; Spiral Drawing Analysis; Machine Learning; Convolutional Neural Networks; Motor Impairment Assessment; Medical Image Analysis; Early Diagnosis},
        month = {January},
        }