Objective measurement of limb bradykinesia using a marker-less tracking algorithm with 2D-video in PD patients

Jung Hwan Shin; Jed Noel Ong; Ryul Kim; Sang-Min Park; Jihyun Choi; Han-Joon Kim; Beomseok Jeon

doi:10.1016/j.parkreldis.2020.09.007

Objective measurement of limb bradykinesia using a marker-less tracking algorithm with 2D-video in PD patients

Parkinsonism Relat Disord. 2020 Dec:81:129-135. doi: 10.1016/j.parkreldis.2020.09.007. Epub 2020 Sep 8.

Authors

Jung Hwan Shin¹, Jed Noel Ong¹, Ryul Kim², Sang-Min Park³, Jihyun Choi⁴, Han-Joon Kim¹, Beomseok Jeon⁵

Affiliations

¹ Department of Neurology, Seoul National University Hospital, Seoul National University, Seoul, South Korea.
² Department of Neurology, Inha University Hospital, Incheon, South Korea.
³ Department of Neurology, Kyungpook National University Chilgok Hospital, Daegu, South Korea.
⁴ Department of Neurology, Seoul National University Bundang Hospital, Seongnam, South Korea.
⁵ Department of Neurology, Seoul National University Hospital, Seoul National University, Seoul, South Korea. Electronic address: brain@snu.ac.kr.

PMID: 33120074
DOI: 10.1016/j.parkreldis.2020.09.007

Abstract

Background: Quantitative measurement of parkinsonian motor symptoms is crucial in clinical practice and in research. However, the widely used Unified PD Rating Scale (UPDRS) part III is based on a semi-quantitative evaluation with high inter- and intra-rater variability. Sensor-based measurements have been widely studied but are limited for their accessibility.

Methods: We analyzed 2D-RGB videos recording finger tapping and leg agility tests in 29 PD patients with a marker-less deep-learning based tracking algorithm. The tracking performance was validated with an accelerometer. Four parameters (mean amplitude, mean interpeak interval, amplitude variability and interpeak interval variability) were calculated from the position tracking.

Results: The performance of the video-tracking was in good agreement with the accelerometer-based tracking (Intra-class correlation coefficient > 0.9 for the peak amplitude, and >0.6 for the interpeak interval). The video-tracking successfully captured variable aspects of limb bradykinesia that have a distinct correlation with the general parkinsonian motor symptoms and gait. In the finger-tapping task, the mean amplitude (R = -0.6, p = 2.4 × 10^-6), amplitude variability (R = 0.36, p = 0.0092), mean interpeak interval (R = 0.34, p = 0.014), and interpeak interval variability (R = 0.66, p = 1.4 × 10^-7) was significantly correlated with the UPDRS scores. In leg agility test, the mean amplitude (R = -0.58, p = 1.7 × 10^-5), mean interpeak interval (R = 0.37, p = 0.0088) and interpeak interval variability (R = 0.7, p = 6.2 × 10^-8) were significantly correlated with the UPDRS scores, but not with amplitude variability (R = 0.17, p = 0.26). Limb rigidity was significantly correlated with the interpeak interval (R = 0.40, p = 0.0036) and its variability (R = 0.59, p = 4.2 × 10^-6) in the leg agility test.

Conclusion: The video-based tracking could objectively measure limb bradykinesia in PD patients.

Keywords: Deep-learning; Finger tapping test; Leg agility test; Parkinson disease; Video tracking.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Accelerometry
Aged
Diagnostic Techniques, Neurological* / standards
Female
Humans
Hypokinesia / diagnosis*
Hypokinesia / etiology
Hypokinesia / physiopathology
Male
Middle Aged
Parkinson Disease / complications
Parkinson Disease / diagnosis*
Parkinson Disease / physiopathology
Reproducibility of Results
Severity of Illness Index
Video Recording