Early Detection of Parkinson's Disease Using Machine Learning

In this research paper, we tackle the challenge of accurately diagnosing Parkinson's disease (PD) using machine learning (ML) techniques, with a specific focus on addressing imbalanced datasets. We employ Adaptive Synthetic Sampling (ADASYN) to intelligently balance class representation, ensuring that minority groups, which are crucial for precise PD detection, are included. Additionally, we utilize min-max scaling to rescale features and incorporate various ML models, such as XGBoost, to leverage their unique strengths. Our findings underscore the effectiveness of this integrated approach in accurately identifying Parkinson's disease. Evaluation metrics, including accuracy, precision, recall, and F1 score, demonstrate the robust performance of our model. Visualization tools like the Confusion Matrix and Receiver Operating Characteristic (ROC) curve provide detailed insights into the capabilities of our model and areas for improvement. Significantly, our model achieves exceptional accuracy (97.44%) and precision (100%) in detecting Parkinson's disease, surpassing alternative algorithms.