Parkinson’s Neurodegenerative Disease Prediction with Robust Methods Of Machine Learning

Parkinson's disease is a degenerative brain disease that causes tremors, often in the elderly. There is a growing impact on bodily movements as a result of this terrified tool disease. It could also start as a barely visible tremor in only one hand, then escalate to uncontrollable shaking of the arms, making it difficult to hold a glass in the hand. Though tremors are a hallmark of the disease, it can also cause slow movements or rigidity. We used the PD patients speech recording dataset informational index from the UCI tool learning repository for this study. The performance of the diagnosis version is measured using machine learning classifiers and universal performance criteria such as sensitivity, accuracy, and specificity rate. This research work focuses on a prediction model for determining whether or not persons have the condition. The primary goal of this research is to assess the accuracy of various machine learning (ML) classifiers, including Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree Classification (DTC), and K-Nearest-Neighbor (KNN), Random Forest Classification (RFC), and Gaussian Naive Bayes (GNB). These algorithms use PCA to extract functions for the dimensionality discount motive. The primary purpose of the research is to conduct a comparison analysis of oneof-a-kind approaches that have been applied to this dataset, as well as the Accuracy Analysis, in order to offer you with the brilliant elegance rule. The goal is also to go through the records so that healthy and Parkinson's patients can be properly classified.