An Automatic Detection Method for Bradykinesia in Parkinson's Disease Based on Inertial Sensor

Parkinson's disease (PD) and Parkinson's syndrome (PS) are common neurodegenerative diseases that occur in the elderly. Bradykinesia is a typical motor symptom of PD and PS.This paper is mainly based on the inertial sensor to collect the upper limb movement signals of Parkinson's disease, extract the corresponding characteristics, and use the neural network multi-layer perceptron (MLP) model to automatically detect the bradykinesia of Parkinson's disease. The experimental results show that the classification accuracy of neural network multi-layer perceptron algorithm for Parkinson's disease and normal subjects is over 90%, and the classification accuracy for normal subjects, Parkinson's disease and Parkinson's syndrome is 85%.This study shows the feasibility of using wearable devices to quantitatively evaluate the motor symptoms of patients with Parkinson's disease and Parkinson's syndrome, and the extracted quantitative indicators and detection methods have certain reference value for future related studies.