Paper Key : IRJ************432
Author: Vaishnavi
Date Published: 05 May 2023
Abstract
Parkinson's disease (PD) is usually identified using clinical observations and data from clinical studies, including the identification of many motor symptoms. Contrary to popular belief, traditional diagnostic approaches may be subject to prejudice because they depend on the interpretation of movements that can be feeble to see with human eyes and hence difficult to characterize, potentially leading to misinterpretation. Meanwhile, Parkinson's disease's first non-motor symptoms may be mild and caused by a range of other disorders. As a consequence, these symptoms are commonly overlooked, making early Parkinson's disease identification challenging. To overcome these challenges and improve PD diagnosis and assessment procedures, a machine learning algorithm for PD categorization has been applied to the vocal dataset consisting of 24 features. The report findings will shed light on the detection and classification of Parkinson's disease using the application of machine learning techniques and will aid in the creation of a highly accurate model as well as an effective tool for the disease's early detection and management.
DOI LINK : 10.56726/IRJMETS37926 https://www.doi.org/10.56726/IRJMETS37926