An artificial intelligence-based decision support system for early and accurate diagnosis of Parkinson's Disease

People with Parkinson's Disease (PD) might struggle with sadness, restlessness, or difficulty speaking, chewing, or swallowing. A diagnosis can be challenging because there is no specific PD test. It is diagnosed by doctors using a neurological exam and a medical history. This study proposes several Machine Learning (ML) algorithms to predict PD. These ML algorithms include K-Nearest Neighbor (KNN), Random Forest (RF), Support Vector Machine (SVM), and eXtreme Gradient Boosting algorithms (XGBoost), and their ensemble methods using publicly available PD dataset with 195 instances. The ML algorithms are used to predict and classify PD using homogeneous XGBoost ensemble techniques with reduced amount of entropy. Synthetic Minority Oversampling Technique (SMOTE) is utilized to handle imbalanced data, and 10-fold cross-validation is employed for evaluation. The results show that the homogeneous XGBoost-Random Forest outperforms other ML methods with 98% accuracy and Matthew's correlation coefficient value 0.93.