Accuracy of Smartphone Video for Contactless Measurement of Hand Tremor Frequency.

Parkinson's, essential tremor, functional tremor, computer vision, artificial intelligence, optical flow

Journal

Movement disorders clinical practice
ISSN: 2330-1619
Titre abrégé: Mov Disord Clin Pract
Pays: United States
ID NLM: 101630279

Informations de publication

Date de publication:
Jan 2021
Historique:
received: 24 05 2020
revised: 14 09 2020
accepted: 20 10 2020
entrez: 2 12 2021
pubmed: 3 12 2021
medline: 3 12 2021
Statut: epublish

Résumé

Computer vision can measure movement from video without the time and access limitations of hospital accelerometry/electromyography or the requirement to hold or strap a smartphone accelerometer. To compare computer vision measurement of hand tremor frequency from smartphone video with a gold standard measure accelerometer. A total of 37 smartphone videos of hands, at rest and in posture, were recorded from 15 participants with tremor diagnoses (9 Parkinson's disease, 5 essential tremor, 1 functional tremor). Video pixel movement was 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. Bland-Altman analysis of dominant tremor frequency from smartphone video compared with accelerometer showed excellent agreement: 95% limits of agreement -0.38 Hz to +0.35 Hz. In 36 of 37 videos (97%), there was <0.5 Hz difference between computer vision and accelerometer measurement. There was no significant correlation between the level of agreement and tremor amplitude. The study suggests a potential new, contactless point-and-press measure of tremor frequency within standard clinical settings, research studies, or telemedicine.

Sections du résumé

BACKGROUND BACKGROUND
Computer vision can measure movement from video without the time and access limitations of hospital accelerometry/electromyography or the requirement to hold or strap a smartphone accelerometer.
OBJECTIVE OBJECTIVE
To compare computer vision measurement of hand tremor frequency from smartphone video with a gold standard measure accelerometer.
METHODS METHODS
A total of 37 smartphone videos of hands, at rest and in posture, were recorded from 15 participants with tremor diagnoses (9 Parkinson's disease, 5 essential tremor, 1 functional tremor). Video pixel movement was 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 RESULTS
Bland-Altman analysis of dominant tremor frequency from smartphone video compared with accelerometer showed excellent agreement: 95% limits of agreement -0.38 Hz to +0.35 Hz. In 36 of 37 videos (97%), there was <0.5 Hz difference between computer vision and accelerometer measurement. There was no significant correlation between the level of agreement and tremor amplitude.
CONCLUSION CONCLUSIONS
The study suggests a potential new, contactless point-and-press measure of tremor frequency within standard clinical settings, research studies, or telemedicine.

Identifiants

pubmed: 34853806
doi: 10.1002/mdc3.13119
pii: MDC313119
pmc: PMC8607978
doi:

Types de publication

Journal Article

Langues

eng

Pagination

69-75

Informations de copyright

© 2020 International Parkinson and Movement Disorder Society.

Déclaration de conflit d'intérêts

No specific funding was received for this work. The authors declare that there are no conflicts of interest relevant to this work.

Références

Lancet. 1986 Feb 8;1(8476):307-10
pubmed: 2868172
Parkinsonism Relat Disord. 2011 May;17(4):288-90
pubmed: 21300563
Biomed Tech (Berl). 2013 Sep 7;58 Suppl 1:
pubmed: 24042621
Mov Disord. 2015 Oct;30(12):1591-601
pubmed: 26474316
Mov Disord. 2018 Jan;33(1):75-87
pubmed: 29193359
J Neurosci Methods. 2011 May 15;198(1):110-3
pubmed: 21396403
Tremor Other Hyperkinet Mov (N Y). 2014 Aug 14;4:259
pubmed: 25157323
J Neurol Sci. 2019 Jun 15;401:27-28
pubmed: 31005760
Clin Neurophysiol Pract. 2019 Jun 28;4:134-142
pubmed: 31886436
Arch Neurol. 2006 Aug;63(8):1100-4
pubmed: 16908735
J Neurol Neurosurg Psychiatry. 2010 Nov;81(11):1223-8
pubmed: 20547625
Tremor Other Hyperkinet Mov (N Y). 2012;2:
pubmed: 23439931
Tremor Other Hyperkinet Mov (N Y). 2016 May 17;6:375
pubmed: 27257514
Mov Disord. 2020 May;35(5):711-715
pubmed: 32250460
J Neurol Sci. 2020 Sep 15;416:117003
pubmed: 32645513

Auteurs

Stefan Williams (S)

Leeds Institute of Health Science, University of Leeds Leeds UK.
Department of Neurology Leeds Teaching Hospitals National Health Service (NHS) Trust Leeds UK.

Hui Fang (H)

Department of Computer Science Loughborough University Loughborough UK.

Samuel D Relton (SD)

Leeds Institute of Health Science, University of Leeds Leeds UK.

David C Wong (DC)

Division of Informatics, Imaging and Data Science University of Manchester Manchester UK.

Taimour Alam (T)

Department of Neurology Leeds Teaching Hospitals National Health Service (NHS) Trust Leeds UK.

Jane E Alty (JE)

Department of Neurology Leeds Teaching Hospitals National Health Service (NHS) Trust Leeds UK.
Wicking Dementia Research and Education Centre University of Tasmania Hobart Tasmania Australia.

Classifications MeSH