Publication

Abstract : Parkinson's Disease (PD) is a chronic neurologic deteriorating condition produced by mislaying of dopamine-producing cells within the cerebrum. These dopamine-producing cells are liable for the mastery, adaptive, and grace of movements. When these cells are astrayed, then enough dopamine is not processed which leads to Parkinson's motor symptoms. The proposed method follows data collection, feature selection, train a model, and model prediction. This paper explores, Machine Learning (ML)-based diagnosis of PD using various classifiers and their prediction accuracy is diagnosed with the defined attributes. From the experimental results it was observed that the Gradient Boost algorithm gives the best test accuracy of 91.53%.