Early Detection of Parkinsons Using Machine Learning

Biomarkers derived from human voice can offer in-sight into neurological disorders, such as Parkinson's disease (PD), because of their underlying cognitive and neuromuscular function. Historically, PD has been difficult to quantity and doctors have tended to focus on some symptoms while ignoring others, relying primarily on subjective rating scales. With advancements in technology and the prevalence of audio collecting devices in daily lives, reliable models that can translate this audio data into a diagnostic tool for healthcare professionals would potentially provide diagnoses that are cheaper and more accurate. This project provides evidence to validate this concept here using a voice dataset collected from people with and without PD. This paper explores the effectiveness of using extreme gradient boosting algorithms, such as XG boost algorithm, to accurately diagnose individuals with the disease Researchers have found that this term is a basic term for a PD More recently, Learning Machines (MLs) have helped solve computer vision problems, process natural languages, recognize Parkinson's speech using machine learning tools and provide a better understanding of the PD database in the current decade. Parkinson's voice database is available at UCI machine storage in the center of learning equipment and intelligent programs. The major outcome of this project is to bring out the result with the most accuracy using XG boost Algorithm. The database contains the similar links show high variability in the Parkinson's disease database. The most importantly the comparison has been made to explicit the outcome result and to prove that the XG boost algorithm provides more accuracy comparing with other algorithms.