The main objective of the research is to diagnose Parkinson’s disease (PD) accurately and quickly. Computer-aided analysis is utilized to identify PD using patient data such as voice, magnetic resonance imaging, speech, and handwriting. Extended clinical diagnostic techniques have recently been designed to increase PD detection accuracy. Even so, there have been numerous issues with the current approaches for diagnosing Parkinson’s disease like selection of unsuitable characteristics, computing complexity, and difficulty in training. This study’s main goal is to investigate the Decision Tree algorithm’s application to a dataset containing tremor features. Tremor is one of the most significant indicators of Parkinson’s disease. Tremor features including frequency, amplitude, and other significant characteristics such as age, gender, and family hierarchy of every individual are considered in determining if a patient has PD or not. These characteristics contribute to achieving greater classification accuracy and enhancing the effectiveness of the proposed model. Python is employed for simulation, and the proposed model works adequately in the detection of PD with an accuracy of approximately 94%.