Department of Information Engineering, I-Shou University, Kaohsiung 840, Taiwan.
Department of Computer and Communication, National Pingtung University, Pingtung 912, Taiwan.
Int J Environ Res Public Health. 2021 Sep 4;18(17):9363. doi: 10.3390/ijerph18179363.
Attention-deficit/hyperactivity disorder (ADHD) is the most common neuropsychiatric disorder in children. Several scales are available to evaluate ADHD therapeutic effects, including the Swanson, Nolan, and Pelham (SNAP) questionnaire, the Vanderbilt ADHD Diagnostic Rating Scale, and the visual analog scale. However, these scales are subjective. In the present study, we proposed an objective and automatic approach for evaluating the therapeutic effects of medication in patients with (ADHD). The approach involved using movement quantification of patients' skeletons detected automatically with OpenPose in outpatient videos. Eleven skeleton parameter series were calculated from the detected skeleton sequence, and the corresponding 33 features were extracted using autocorrelation and variance analysis. This study enrolled 25 patients with ADHD. The outpatient videos were recorded before and after medication treatment. Statistical analysis indicated that four features corresponding to the first autocorrelation coefficients of the original series of four skeleton parameters and 11 features each corresponding to the first autocorrelation coefficients of the differenced series and the averaged variances of the original series of 11 skeleton parameters significantly decreased after the use of methylphenidate, an ADHD medication. The results revealed that the proposed approach can support physicians as an objective and automatic tool for evaluating the therapeutic effects of medication on patients with ADHD.
注意缺陷多动障碍（ADHD）是儿童中最常见的神经精神疾病。有几种量表可用于评估 ADHD 的治疗效果，包括 Swanson、Nolan 和 Pelham（SNAP）问卷、范德比尔特 ADHD 诊断量表和视觉模拟量表。然而，这些量表都是主观的。在本研究中，我们提出了一种客观和自动的方法来评估药物治疗 ADHD 患者的疗效。该方法涉及使用 OpenPose 自动检测患者骨骼的运动量化，从检测到的骨骼序列中计算出 11 个骨骼参数系列，并使用自相关和方差分析提取相应的 33 个特征。这项研究共纳入了 25 名 ADHD 患者。门诊视频记录了药物治疗前后的情况。统计分析表明，在使用 ADHD 药物哌醋甲酯后，四个骨骼参数原始序列的第一个自相关系数对应的四个特征，以及 11 个骨骼参数原始序列的差分序列和平均值方差的第一个自相关系数对应的 11 个特征显著降低。结果表明，所提出的方法可以为医生提供一种客观、自动的工具，用于评估 ADHD 患者药物治疗的疗效。
