Early Prediction of Parkinson Disease Using Machine Learning and Deep Learning Approaches

EasyChair Preprint 4889

Abstract

Parkinson disease(PD), the second most common neurological disorder that causes significant disability, reduces the quality of life and has no cure. Nerve cells in this part of the brain are responsible for producing a chemical called dopamine. Dopamine acts as a message between the parts of the brain and nervous system that help control and co-ordinate body movements. As dopamine generally neurons in the parts begin to experience difficulty in speaking, writing, walking or completing other simple task .Approximately, 90% affected people with Parkinson have speech disorders. The average age of onset is about 70 years, and the incidence rises significantly with advancing age. However, a small percent of people with PD have “early-onset” disease that begins before the age of 50.More than 10 million people worldwide are living with PD. No cure for PD exists today, but research is ongoing and medications or surgery can often provide substantial improvement with motor symptoms. Parkinson disease is one of the most serious diseases. Hence diagnosing it at an earlier stage could help prevent or reduce the effects. The machine learning classification algorithms are used to predict if a person has Parkinson disease or not, comparing different machine learning algorithm such as logistic regression, decision tree, k-nearest neighbour as well as some “Ensemble” learning techniques where we attempt to improve the accuracy by combining several models .The machine learning model can be implemented to significantly improve diagnosis method of Parkinson disease .In this study it indicates that the ensemble techniques Xgboost classification (Extreme gradient boosting) algorithm achieved the high test accuracy rate (95%) compared to other classification algorithm .The performance of the methods has been assessed with a reliable dataset from UCI Machine learning repository.

Keyphrases: Decision Tree, Parkinson’s dataset, Parkinson’s disease, Support Vector Machine, UCI machine learning, Xgboost(Extreme gradient boosting), classification algorithm, logistic regression, machine learning

@booklet{EasyChair:4889,
  author    = {Harshvardhan Tiwari and Shiji K Shridhar and Preeti V Patil and K R Sinchana and G Aishwarya},
  title     = {Early Prediction of Parkinson Disease Using Machine Learning and Deep Learning Approaches},
  howpublished = {EasyChair Preprint 4889},
  year      = {EasyChair, 2021}}