PROJECT TITLE :

A Method for Automatic and Objective Scoring of Bradykinesia Using Orientation Sensors and Classification Algorithms

ABSTRACT:

Correct assessment of bradykinesia may be a key component within the diagnosis and monitoring of Parkinson's disease. Its analysis is based on a careful assessment of symptoms and it's quantified using rating scales, where the Movement Disorders Society-Sponsored Revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) is the gold normal. Regardless of their importance, the bradykinesia-related items show low agreement between completely different evaluators. In this study, we style an applicable tool that has an objective quantification of bradykinesia which evaluates all characteristics described within the MDS-UPDRS. Twenty-5 patients with Parkinson's disease performed three of the five bradykinesia-connected items of the MDS-UPDRS. Their movements were assessed by four evaluators and were recorded with a 9 degrees-of-freedom sensor. Sensor fusion was utilized to obtain a 3-D representation of movements. Based mostly on the resulting signals, a set of options related to the characteristics described in the MDS-UPDRS was outlined. Feature selection methods were employed to work out the most necessary options to quantify bradykinesia. The options selected were used to train support vector machine classifiers to get an automatic score of the movements of each patient. The simplest results were obtained when seven options were included within the classifiers. The classification errors for finger tapping, diadochokinesis and toe tapping were 15–sixteen.five%, 9.3–nine.8%, and eighteen.2–20.a pair of% smaller than the typical interrater scoring error, respectively. The introduction of objective scoring within the assessment of bradykinesia might eliminate inconsistencies at intervals evaluators and interrater assessment disagreements and might improve the monitoring of movement disorders.