Parkinson’s Disease Diagnosis: Integrating Decision Trees and Random Forest

This research work attempts to create a powerful machine-learning model that can identify the prefrontal cortex of individuals with Parkinson’s Disease by analyzing their voice recordings. The disorder of Parkinson’s, a progressive neurodegenerative condition that is characterized by the presence of tremors, muscular rigidity, and coordination issues, is early detection and requires no invasiveness. Leveraging the advanced computational techniques, this research pioneered a two-phase approach that incorporated Decision Tres and random Forest to have more specific diagnoses. The amalgamation of these methods not only addresses the diagnostic issues, but also facilitates the formulation of individualized treatment strategies. Ultimately, these strategies have a preeminent impact on the aspect of liveliness of patients with Parkinson’s disease.