Parkinson's disease (PD) is a progressive neurodegenerative disorder that primarily affects the central nervous system. Symptoms of early Parkinson's disease include Tremors, Rigidity, Bradykinesia, and Postural instability. Although typically diagnosed in individuals over 60 years old, 5 to 10 percent of cases occur in those under 50. Early detection is critical for effective treatment, and machine learning algorithms can be utilized to process user input data alongside previously collected data to assess whether an individual is affected. The selection of an optimal classification algorithm for local datasets can be challenging. This study evaluated the effectiveness of several algorithms, including Logistic Regression, Support Vector Machine, and XGBoost, yielding accuracies of 79%, 87%, and 89%, respectively. The LightGBM algorithm was selected for this study as it may provide superior accuracy.