Identifying Parkinson’s Disease in it’s Primitive Phase using Vocal Characteristics

Parkinson's Disease (PD) is a condition within the nervous System that limits mobility and is typified by tremors, stiffness, imbalance issues, and vocal abnormalities. Effective management and therapy of this disease (PD) depend on early identification and discovery of the disease. Research into the topic of "voice features for Parkinson's (PD) detection" looks into viability of using voice recordings for Parkinson's disease screening or treatment. PD patients may have certain patterns in their vocal characteristics, such as variations in pitch, loudness, and speech rhythm. Examining these aspects of speech could reveal important information on the occurrence and development of Parkinson's disease. Voice analysis's potential as a Parkinson's disease diagnosis tool has been examined in a number of studies. These investigations frequently use machine. Machine learning (ML) techniques are widely applied in these studies to evaluate voice recordings and extract pertinent information. This work investigates the use of voice features in machine learning (ML) algorithms for PD identification. In this study, we examine how well XG-Boost performs in comparison with five distinct algorithms. We discovered after conducting a thorough research and experimentation that XG- Boost is consistently more accurate than the other models.