Paper Contents
Abstract
Parkinson's disease (PD) is a neurodegenerative movement disorder in which symptoms develop gradually, starting with a mild tremor in one hand and a feeling of body stiffness and worsening over time. It affects more than 6 million people worldwide. Currently, there is no conclusive result for this disease from non-specialist doctors, especially in the early stage of the disease, where the identification of symptoms in its early stages is very difficult. The proposed predictive analytics framework is a combination of K-means clustering and a decision tree that is used to extract information from patients. Using machine learning techniques, the problem can be solving minimum error rate. Voice data files obtained from the UCI Machine learning repository, if provided as input for voice data analysis. Our proposed system also provides accurate results by integrating spiral drawings of normal and Parkinson's patients. A random forest classification algorithm is used from these drawings which converts these drawings into pixels for classification and the extracted values are compared with a trained database to extract different features and the results are produced with maximum accuracy. also OpenCV (Open Source Computer Vision Library) a library of programming functions focused primarily on real-time computer vision was built to provide an infrastructure for computer vision applications and accelerate the use of real-time machine perception. Our output will thus show early detection of the disease and may be able to prolong the life of the sick patient with proper treatment and medication leading to a peaceful life. Artificial intelligence (AI) has played a promising role in PD diagnosis. However, it introduces bias due to insufficient sample size, poor validation, clinical evaluation, and lack of big data configuration.
Copyright
Copyright © 2024 Anil Lamkhade. This is an open access article distributed under the Creative Commons Attribution License.
