Supervised classification of bradykinesia for Parkinson's disease diagnosis from smartphone videos

David C. Wong; Samuel D. Relton; Hui Fang; Rami Qhawaji; Christopher D. Graham; Jane Alty; Stefan Williams

doi:10.1109/CBMS.2019.00017

Supervised classification of bradykinesia for Parkinson's disease diagnosis from smartphone videos

David C. Wong, Samuel D. Relton, Hui Fang, Rami Qhawaji, Christopher D. Graham, Jane Alty, Stefan Williams

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

Slowness of movement, known as bradykinesia, is an important early symptom of Parkinson's disease. This symptom is currently assessed subjectively by clinical experts. However, expert assessment has been shown to be subject to inter-rater variability. We propose a low-cost, contactless system using smarthphone videos to automatically determine the presence of bradykinesia. Using 70 videos recorded in a pilot study, we predicted the presence of bradykinesia with an estimated test accuracy of 0.79 and the presence of Parkinson's disease with estimated test accuracy 0.63. Even on a small set of pilot data this accuracy is comparable to that recorded by blinded human experts.

Original language	English
Title of host publication	Proceedings - 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems, CBMS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	32-37
Number of pages	6
Volume	2019-June
ISBN (Electronic)	9781728122861
DOIs	https://doi.org/10.1109/CBMS.2019.00017
Publication status	Published - 01 Jun 2019
Event	32nd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2019 - Cordoba, Spain Duration: 05 Jun 2019 → 07 Jun 2019

Conference

Conference	32nd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2019
Country/Territory	Spain
City	Cordoba
Period	05/06/2019 → 07/06/2019

Keywords

Bradykinesia
Classification
Computer Vision
Diagnosis
Parkinson's
Support Vector Machine
Video

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging
Computer Science Applications

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/CBMS.2019.00017

Cite this

Wong, D. C., Relton, S. D., Fang, H., Qhawaji, R., Graham, C. D., Alty, J., & Williams, S. (2019). Supervised classification of bradykinesia for Parkinson's disease diagnosis from smartphone videos. In Proceedings - 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems, CBMS 2019 (Vol. 2019-June, pp. 32-37). [8787472] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CBMS.2019.00017

@inproceedings{d2f6565ab91a47fb915e8af721e79c84,

title = "Supervised classification of bradykinesia for Parkinson's disease diagnosis from smartphone videos",

abstract = "Slowness of movement, known as bradykinesia, is an important early symptom of Parkinson's disease. This symptom is currently assessed subjectively by clinical experts. However, expert assessment has been shown to be subject to inter-rater variability. We propose a low-cost, contactless system using smarthphone videos to automatically determine the presence of bradykinesia. Using 70 videos recorded in a pilot study, we predicted the presence of bradykinesia with an estimated test accuracy of 0.79 and the presence of Parkinson's disease with estimated test accuracy 0.63. Even on a small set of pilot data this accuracy is comparable to that recorded by blinded human experts.",

keywords = "Bradykinesia, Classification, Computer Vision, Diagnosis, Parkinson's, Support Vector Machine, Video",

author = "Wong, {David C.} and Relton, {Samuel D.} and Hui Fang and Rami Qhawaji and Graham, {Christopher D.} and Jane Alty and Stefan Williams",

year = "2019",

month = jun,

day = "1",

doi = "10.1109/CBMS.2019.00017",

language = "English",

volume = "2019-June",

pages = "32--37",

booktitle = "Proceedings - 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems, CBMS 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "32nd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2019 ; Conference date: 05-06-2019 Through 07-06-2019",

}

Wong, DC, Relton, SD, Fang, H, Qhawaji, R, Graham, CD, Alty, J & Williams, S 2019, Supervised classification of bradykinesia for Parkinson's disease diagnosis from smartphone videos. in Proceedings - 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems, CBMS 2019. vol. 2019-June, 8787472, Institute of Electrical and Electronics Engineers Inc., pp. 32-37, 32nd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2019, Cordoba, Spain, 05/06/2019. https://doi.org/10.1109/CBMS.2019.00017

Supervised classification of bradykinesia for Parkinson's disease diagnosis from smartphone videos. / Wong, David C.; Relton, Samuel D.; Fang, Hui et al.

Proceedings - 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems, CBMS 2019. Vol. 2019-June Institute of Electrical and Electronics Engineers Inc., 2019. p. 32-37 8787472.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Supervised classification of bradykinesia for Parkinson's disease diagnosis from smartphone videos

AU - Wong, David C.

AU - Relton, Samuel D.

AU - Fang, Hui

AU - Qhawaji, Rami

AU - Graham, Christopher D.

AU - Alty, Jane

AU - Williams, Stefan

PY - 2019/6/1

Y1 - 2019/6/1

N2 - Slowness of movement, known as bradykinesia, is an important early symptom of Parkinson's disease. This symptom is currently assessed subjectively by clinical experts. However, expert assessment has been shown to be subject to inter-rater variability. We propose a low-cost, contactless system using smarthphone videos to automatically determine the presence of bradykinesia. Using 70 videos recorded in a pilot study, we predicted the presence of bradykinesia with an estimated test accuracy of 0.79 and the presence of Parkinson's disease with estimated test accuracy 0.63. Even on a small set of pilot data this accuracy is comparable to that recorded by blinded human experts.

AB - Slowness of movement, known as bradykinesia, is an important early symptom of Parkinson's disease. This symptom is currently assessed subjectively by clinical experts. However, expert assessment has been shown to be subject to inter-rater variability. We propose a low-cost, contactless system using smarthphone videos to automatically determine the presence of bradykinesia. Using 70 videos recorded in a pilot study, we predicted the presence of bradykinesia with an estimated test accuracy of 0.79 and the presence of Parkinson's disease with estimated test accuracy 0.63. Even on a small set of pilot data this accuracy is comparable to that recorded by blinded human experts.

KW - Bradykinesia

KW - Classification

KW - Computer Vision

KW - Diagnosis

KW - Parkinson's

KW - Support Vector Machine

KW - Video

UR - http://www.scopus.com/inward/record.url?scp=85071049575&partnerID=8YFLogxK

U2 - 10.1109/CBMS.2019.00017

DO - 10.1109/CBMS.2019.00017

M3 - Conference contribution

AN - SCOPUS:85071049575

VL - 2019-June

SP - 32

EP - 37

BT - Proceedings - 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems, CBMS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 32nd IEEE International Symposium on Computer-Based Medical Systems, CBMS 2019

Y2 - 5 June 2019 through 7 June 2019

ER -

Wong DC, Relton SD, Fang H, Qhawaji R, Graham CD, Alty J et al. Supervised classification of bradykinesia for Parkinson's disease diagnosis from smartphone videos. In Proceedings - 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems, CBMS 2019. Vol. 2019-June. Institute of Electrical and Electronics Engineers Inc. 2019. p. 32-37. 8787472 doi: 10.1109/CBMS.2019.00017

Supervised classification of bradykinesia for Parkinson's disease diagnosis from smartphone videos

Abstract

Conference

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this