Machine Learning Methods for Predicting Parkinson's Disease Progression

The article presents the developed machine learning model for the diagnosis and prognosis of a neurological disorder - Parkinson's disease. The choice of the algorithm used to create the model is justified. By employing machine learning methods, particularly Support Vector Machines and k-Nearest Neighbors algorithms, high accuracy and reliability were achieved in predicting disease class labels. The analysis of relationships between clinical, genetic, and biomarker features demonstrated that these characteristics significantly influence the development of Parkinson's disease.