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{175634,
        author = {Pathakota Megha Sri Syam and Bapatla Sashank and Gorakala Dharma Teja and Syed Buran and Gullapalli Naga Satya Sai Aditya and Dr. D. Anusha},
        title = {Parkinson's Disease Detection using Deep Learning Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {3854-3859},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175634},
        abstract = {Parkinson’s Disease (PD) is a progressive neurological disorder that affects movement and motor control, making early diagnosis both important and challenging. Traditional diagnostic methods are often time-consuming, subjective, and not always accurate, especially in the early stages. To address this, we explored a deep learning approach that uses hand-drawn spiral images to help detect PD in a faster and more reliable way. Our study compares three different models-CNN, MobileNetV2, and ResNet50, each chosen for their unique strengths in feature extraction and classification. The dataset used was collected from Kaggle and includes drawings by both individuals with Parkinson’s and healthy controls. After preprocessing and augmenting the data, we trained the models using binary classification with standard evaluation metrics like accuracy, precision, recall, and F1-score. The results showed that deep learning models, especially MobileNetV2 and ResNet50, can effectively distinguish between healthy and PD-affected individuals based on simple hand-drawn inputs. This approach has the potential to become a non-invasive, accessible screening tool to support early diagnosis and ongoing monitoring of Parkinson’s Disease. Future work will focus on improving accuracy further and deploying the system in real-time applications, such as mobile or web platforms.},
        keywords = {Deep Learning, Convolutional Neural Network, MobileNetV2, ResNet50, Spiral image Dataset, Flask framework, MySQL.},
        month = {April},
        }