Full text not available from this repository.

Abstract

Background: Computer vision can measure movement from video without the time and accesslimitations of hospital accelerometry/electromyography or the requirement to hold or strap a smartphoneaccelerometer.Objective: To compare computer vision measurement of hand tremor frequency from smartphone video with agold standard measure accelerometer.Methods: A total of 37 smartphone videos of hands, at rest and in posture, were recorded from 15 participantswith tremor diagnoses (9 Parkinson’s disease, 5 essential tremor, 1 functional tremor). Video pixel movementwas measured using the computing technique of optical flow, with contemporaneous accelerometer recording.Fast Fourier transform and Bland-Altman analysis were applied. Tremor amplitude was scored by 2 clinicians.Results: Bland-Altman analysis of dominant tremor frequency from smartphone video compared withaccelerometer showed excellent agreement: 95% limits of agreement −0.38 Hz to +0.35 Hz. In 36 of 37 videos(97%), there was Conclusion: The study suggests a potential new, contactless point-and-press measure of tremor frequencywithin standard clinical settings, research studies, or telemedicine.

Item Type:	Article
Authors/Creators:	Williams, S and Fang, H and Relton, SD and Wong, DC and Alam, T and Alty, JE
Keywords:	parkinson's, computer visions, smartphone, tremor, dystonia, essential tremor, functional tremor
Journal or Publication Title:	Movement Disorders Clinical Practice
Publisher:	John Wiley & Sons, Inc.
ISSN:	2330-1619
DOI / ID Number:	10.1002/mdc3.13119
Copyright Information:	© 2020 International Parkinson and Movement Disorder Society
Related URLs:	Google Scholar: Alty, JE
Item Statistics:	View statistics for this item

Actions (login required)

Item Control Page