Prediction of Parkinson’s Disease Using Machine Learning

Abstract

Parkinson's Disease is a neurological condition triggered by nerve cell disruption in our body. There is a chemical called Dopamine which is used for controlling movements of the body and various functions. The lack of production of dopamine or in other words the cell count which produces dopamine reduced by 80% leads to Parkinson's Disease. This disease has a lot of symptoms like vocal symptoms, tremors, gait difficulties, and mental issues. We can use any of these symptoms to predict Parkinson's Disease. Machine learning is now being introduced as being one of the specific areas in every other domain for fast results and less cost. Even in the medical domain machine learning is being used for various purposes. We can use ML here to predict whether a patient is suffering from Parkinson's or not. In this paper, we use voice features of various patients who are either diagnosed with PD or not diagnosed with PD. We train our data with different Machine Learning algorithms like Logistic Regression, KNN, Random Forest. Feature selection is also used to get better accuracy. Accuracy is important in the medical field, so it is imminent we use the algorithm which gives the best accuracy. Using Machine Learning is going to reduce the cost of prediction of PD and also save various resources.