Discernment of Parkinson’s disease using Machine learning

Abstract

Parkinson’s disease is one of the most common neurological disorders in the world that is caused when the cells in the brain that are responsible for the creation of dopamine breakdown and as a result less dopamine is produced .The cells in the brain that create dopamine are in charge of movement regulation, adaptability, and fluency. Since researchers believe that the disease starts developing many years before the motor (movement-related) symptoms arise, they have been exploring for ways to identify non-motor symptoms that occur early in the disease and prevent it from progressing. The aim of this work is to detect the presence of Parkinson’s disease in a person using Machine Learning techniques. The suggested diagnosis technique uses feature selection and classification procedures. Feature selection includes feature importance that is nothing but a technique of representing the importance of input features by giving them scores and also recursive feature elimination that finds the most relevant features to determine the target variable. The other methods like Artificial Neural Networks and Support Vector Machines are also used in this work. With the fewest number of voice features, 93.84 percent accuracy was attained for Parkinson's diagnosis