Williams Stefan, Fang Hui, Relton Samuel D, Wong David C, Alam Taimour, Alty Jane E
Leeds Institute of Health Science, University of Leeds Leeds UK.
Department of Neurology Leeds Teaching Hospitals National Health Service (NHS) Trust Leeds UK.
Mov Disord Clin Pract. 2020 Dec 28;8(1):69-75. doi: 10.1002/mdc3.13119. eCollection 2021 Jan.
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.
计算机视觉可以从视频中测量运动，不受医院加速度计/肌电图的时间和使用限制，也无需手持或捆绑智能手机加速度计。
比较通过智能手机视频进行的计算机视觉测量的手部震颤频率与金标准测量方法加速度计的结果。
从15名患有震颤诊断的参与者（9例帕金森病、5例特发性震颤、1例功能性震颤）中记录了37个手部在休息和姿势状态下的智能手机视频。使用光流计算技术测量视频像素运动，并同步记录加速度计数据。应用快速傅里叶变换和布兰德-奥特曼分析。由2名临床医生对震颤幅度进行评分。
对智能手机视频与加速度计测量的主要震颤频率进行布兰德-奥特曼分析，结果显示一致性极佳：一致性界限为95%时，-0.38赫兹至+0.35赫兹。在37个视频中的36个（97%）中，计算机视觉测量与加速度计测量之间的差异<0.5赫兹。一致性水平与震颤幅度之间无显著相关性。
该研究表明，在标准临床环境、研究或远程医疗中，可能存在一种新的、非接触式的震颤频率点按测量方法。
