A Functional Gradient Boost Approach for Identifying Parkinson's Disease
Abstract
Parkinson's disease is a neurodegenerative disorder characterised by the manifestation of involuntary and uncontrolled motor symptoms, such as tremors, rigidity, and impaired balance and coordination. Parkinson's disease is characterised by the degeneration of neurons in the substantia nigra, a region located within the brain. The gradient boost method will be employed in the field of machine learning to identify individuals afflicted with Parkinson's disease. This study employs a collection of features derived from the Parkinson's progression markers initiative (PPMI) in order to gain insights into the initiation and progression of brain diseases, as well as to explore potential interventions for mitigating their effects. The method was applied to a cohort of patients selected from the Parkinson's progression markers initiative (PPMI) dataset for evaluation. The utilisation of a machine learning algorithm facilitates the categorization of individuals afflicted with Parkinson's disease into distinct clusters.