Parkinson’s Disease Detection Using Machine Learning

Parkinson’s disease (PD) is one of the most fatal and progressive nervous system illnesses affecting movement. It is a common neurological illness that causes disabilities, shortens people’s lives, and has no treatment. Almost 90% of those affected by this condition suffer speech problems. Large datasets are accessible in many data repositories for use in solving real-world problems. A significant amount of study has been done in this area in recent years with positive outcomes. In this modern era, machine learning (ML) is the answer to every problem. ML techniques are also utilized in the detection of PD, which has afflicted many individuals. A Parkinson’s voice dataset is used in this paper. The authors have utilized several machine learning methods like support vector machine (SVM), random forest (RF), logistic regression (LR), K-nearest neighbor (KNN), and XGBoost (XGB) for PD detection. The output of each algorithm is compared based on their accuracies. The KNN outperforms all the other methods by obtaining the highest accuracy of 95% in magnitude.