Analysis and Visualization of 3D Motion Data for UPDRS Rating of Patients with Parkinson's Disease.

Neltje Piro,Ronald Blechschmidt-Trapp,Lennart Piro,Jan Kassubek

doi:10.3390/s16060930

Abstract

Remote monitoring of Parkinson’s Disease (PD) patients with inertia sensors is a relevant method for a better assessment of symptoms. We present a new approach for symptom quantification based on motion data: the automatic Unified Parkinson Disease Rating Scale (UPDRS) classification in combination with an animated 3D avatar giving the neurologist the impression of having the patient live in front of him. In this study we compared the UPDRS ratings of the pronation-supination task derived from: (a) an examination based on video recordings as a clinical reference; (b) an automatically classified UPDRS; and (c) a UPDRS rating from the assessment of the animated 3D avatar. Data were recorded using Magnetic, Angular Rate, Gravity (MARG) sensors with 15 subjects performing a pronation-supination movement of the hand. After preprocessing, the data were classified with a J48 classifier and animated as a 3D avatar. Video recording of the movements, as well as the 3D avatar, were examined by movement disorder specialists and rated by UPDRS. The mean agreement between the ratings based on video and (b) the automatically classified UPDRS is 0.48 and with (c) the 3D avatar it is 0.47. The 3D avatar is similarly suitable for assessing the UPDRS as video recordings for the examined task and will be further developed by the research team.

Highlights

Parkinson’s disease (PD) is an age-related, neurodegenerative disorder whose underlying pathological processes can be traced as a topographically ascending degeneration scheme spreading from the lower brainstem toward mesencephalic structures and the basal ganglia, reaching the neocortex, as evident from neuropathological studies [1]
The deployed version of libGDX did not support the generation of shadows
The individual neurologists rated consistently so that there were no significant differences between the ratings based on video and consistently so that there were no significant differences between the ratings based on video and avatar, considering each rater

Summary

Introduction

Parkinson’s disease (PD) is an age-related, neurodegenerative disorder whose underlying pathological processes can be traced as a topographically ascending degeneration scheme spreading from the lower brainstem toward mesencephalic structures and the basal ganglia, reaching the neocortex, as evident from neuropathological studies [1]. The severity of PD-related symptoms are typically quantified using the Unified Parkinson Disease Rating Scale (UPDRS) revised by the Movement Disorder Society (MDS). Part III of the UPDRS considers the examination of motor symptoms. The full assessment of the patient’s health status with the UPDRS is time-consuming, is dependent on the rater’s experience [4], and considers only a snapshot of time. The assessment of motor function over time is necessary for an individual adjustment of medication and appropriate quality of treatment.

Objectives

Methods

Results

Discussion

Conclusion