The method examines classifying audio signal feature sets to identify Parkinson's disease (PD), which is referred to as a condition that affects the brain and spinal cord, rendering patients incapable of speaking, walking, or controlling their tremors. In this procedure, machine learning techniques are used, and the classifiers make use of the sound component dataset obtained from parametric a technique called algorithms & models utilized the UCI collection source. Thanks to XGBoost, which had an overall accuracy rate of 96 percent and an MCC of 89 percent, the system provided a considerably improved forecast of the state of the palladium patient. Parkinson's disease people disease commonly experience monotonous, low-volume noise. Parkinson's disease, a neurodevelopmental disorder, impacts many millions of people worldwide. It's important to highlight that 60% of individuals aged 50 and older are afflicted by Parkinson's disease (PD). Those with PD often encounter difficulties in both daily functioning and communication,creating a formidable task so that they attend routine medical check-ups and monitoring. The early detection Providing care for Parkinson's patients are vital for allowing individuals to sustain their regular lifestyles. The increasing global elderly population underscores the urgent necessity for swift, accurate, and remote Parkinson's disease detection. Recent progress in machine learning holds significant potential for enhancing the early identification and evaluation of Parkinson's disease. Our algorithms performed amazingly, with training success detecting from circular pictures of 95.34percent, validate efficiency of 93.00 percent, training success for Parkinson's disease detecting from wave pictures of 93.34 percent, and training efficiency for Parkinson's disease detecting from wave pictures of 86.00 percent, respectively.