Identifying Parkinson's Patients by a Functional Gradient Boosting Approach

Abstract

Over 10 million people worldwide suffer with Parkinson's disease (PD). The ecumenical medical community continues to rely on physical examination, scales, signs, and symptoms, but there is no evaluation for this obscenely common disease. As technology advances, machine learning and healthcare are becoming more and more entwined. One of the machine learning methods known as functional gradient boosting (FGB) has shown promise as a diagnostic tool for PD patients, helping and speeding up their recovery. FGB helps practitioners create tailored therapeutics that improve treatment results and patient's quality of life. Additionally, it helps healthcare providers track the development of diseases, foresee symptoms, and describe treatments. As research on functional gradient boosting advances, it is positioned to significantly transform Parkinsonism rehabilitation and improve patient outcomes.