Machine Learning Application to Quantify the Tremor Level for Parkinson’s Disease Patients

摘要: Abstract Parkinson’s disease (PD) is a neurodegenerative disorder with progressive nature. It causes motor symptoms such as resting tremor, bradykinesia and others movement disorders. Because of its nature, this needs continuous monitoring symptoms. Health Monitoring Systems are widely used to monitor the progress, improving treatment minimizing drug side effects. In research, we developed two predictive models using supervised machine learning approach. These can classify Parkinson disease’s rest tremor between high or low frequencies, showing intensity symptom. This classification allows detailed medication’s effectiveness progress. our validation, applied leave-one-out cross-validation methods level PD tremor. results, reached accuracy 92.8%. Therefore, work proposes new approach classifying patients quality´s live on treatment, non-invasive health systems improved by algorithms.