Parkinson’s Disease Detection Using Machine Learning Algorithms

In order to come up with an efficient method for the discovery of Parkinson’s Disease (PD), various research papers were taken into consideration that are dependent on Parkinson’s Detection using various Machine Learning algorithm (MLA). Patients with Parkinson’s disease (PWP) have movement issues as well as communication impairments, making physical visits for medication and monitoring challenges. Early identification of Parkinson’s disease allows people to live a normal life. The global aging population has brought about an increased focus on the importance of early, remote, and accurate detection of Parkinson’s disease (PD). This paper utilized the various techniques of MLA and it was also observed that the suggested model is more effective and provides higher precision. Here, the research has been carried out on the biological voice data of 31 individuals among which 23 suffered from PD. The potential outcomes of the paper is based on the detection accuracy using six different classifiers of ML. The accuracy output includes Support Vector Machine (SVM) 85%, Decision Tree 85%, Logistic Regression 85%, Random Forest 85%, Gradient Boost 87% and XG Boost 85%. From the above findings we propmote the incorporation of machine learning methodologies into clinical decision-making processes to enhance the accuracy and systematization of Parkinson’s disease diagnosis.