Abstract : Large medical datasets are available in various data repositories and are used to identify diseases. Parkinson's disease is regarded as one of the most lethal and progressive nervous system diseases affecting movement. It is the second most common cause of disability in the brain and it Reduces life expectancy and has no cure. Nearly 90% of affected people with this disease have speech disorders. In real-world applications, data is generated using a variety of Machine Learning techniques. Machine learning algorithms assist in the generation of useful content from it. Machine learning algorithms are used to detect diseases in their early stages in order to extend the lives of the elderly. When considering the term 'Parkinson's,' the main concept is speech features. In this paper, we are reviewing various Machine Learning techniques such as KNN, SVM, Naïve Bayes, Deep learning techniques and Logistic Regression to predict Parkinson's disease based on user input, and the input for algorithms is the dataset. Based on these characteristics, we anticipate that the algorithms will be more accurate. The model is used in conjunction with the frontend to predict whether or not the patient has Parkinson's disease. Prediction is critical in the early stages of patient recovery. This can be accomplished with the assistance of Machine Learning

Keyword : Convolutional Neural Network (CNN), Deep Belief Networks (DBN), Deep Neural Networks (DNN), K-nearest Neighbors Algorithm (KNN), Machine Learning, Parkinson’s, Speech disorders, Support Vector Machine Classifier (SVM).