Department of Neurology, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Kita 15, Nishi 7, Kita-ku, Sapporo 060-8638, Japan; Hokuyukai Neurological Hospital, 4-30, 2jo, 2cho-me, Nijuyonken, Nishi-ku, Sapporo 063-0802, Japan.
Department of Neurology, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Kita 15, Nishi 7, Kita-ku, Sapporo 060-8638, Japan.
J Neurol Sci. 2024 Sep 15;464:123158. doi: 10.1016/j.jns.2024.123158. Epub 2024 Jul 30.
Although pose estimation algorithms have been used to analyze videos of patients with Parkinson's disease (PD) to assess symptoms, their feasibility for differentiating PD from other neurological disorders that cause gait disturbances has not been evaluated yet. We aimed to determine whether it was possible to differentiate between PD and spinocerebellar degeneration (SCD) by analyzing video recordings of patient gait using a pose estimation algorithm.
We videotaped 82 patients with PD and 61 patients with SCD performing the timed up-and-go test. A pose estimation algorithm was used to extract the coordinates of 25 key points of the participants from these videos. A transformer-based deep neural network (DNN) model was trained to predict PD or SCD using the extracted coordinate data. We employed a leave-one-participant-out cross-validation method to evaluate the predictive performance of the trained model using accuracy, sensitivity, and specificity. As there were significant differences in age, weight, and body mass index between the PD and SCD groups, propensity score matching was used to perform the same experiment in a population that did not differ in these clinical characteristics.
The accuracy, sensitivity, and specificity of the trained model were 0.86, 0.94, and 0.75 for all participants and 0.83, 0.88, and 0.78 for the participants extracted by propensity score matching.
The differentiation of PD and SCD using key point coordinates extracted from gait videos and the DNN model was feasible and could be used as a collaborative tool in clinical practice and telemedicine.
尽管姿势估计算法已被用于分析帕金森病（PD）患者的视频以评估症状，但尚未评估其区分导致步态障碍的 PD 与其他神经障碍的能力。我们旨在通过分析使用姿势估计算法对患者步态进行视频记录，确定是否可以区分 PD 和脊髓小脑变性（SCD）。
我们对 82 名 PD 患者和 61 名 SCD 患者进行了计时起立行走测试的录像。使用姿势估计算法从这些视频中提取参与者 25 个关键点的坐标。使用基于转换器的深度神经网络（DNN）模型，利用提取的坐标数据预测 PD 或 SCD。我们采用了一种留一参与者交叉验证方法，使用准确性、敏感性和特异性来评估训练模型的预测性能。由于 PD 和 SCD 组在年龄、体重和体重指数方面存在显著差异，因此使用倾向评分匹配在这些临床特征无差异的人群中进行了相同的实验。
对于所有参与者，训练模型的准确性、敏感性和特异性分别为 0.86、0.94 和 0.75，对于通过倾向评分匹配提取的参与者，准确性、敏感性和特异性分别为 0.83、0.88 和 0.78。
使用步态视频和 DNN 模型提取的关键点坐标对 PD 和 SCD 进行区分是可行的，可以作为临床实践和远程医疗中的协同工具。
