The purposes of the study were (1) to compare postural sway between participants with Parkinson’s disease (PD) and healthy controls and (2) to develop and validate an automated classification of PD postural control patterns using a machine learning approach. A total of 9 participants in the early stage of PD and 12 healthy controls were recruited. Participants were instructed to stand on a force plate and maintain stillness for 2 minutes with eyes open and eyes closed. The center of pressure data were collected at 50 Hz. Linear displacements, standard deviations, total distances, sway areas, and multiscale entropy of center of pressure were calculated and compared using mixed-model analysis of variance. Five supervised machine learning algorithms (ie, logistic regression, K-nearest neighbors, Naïve Bayes, decision trees, and random forest) were used to classify PD postural control patterns. Participants with PD exhibited greater center of pressure sway and variability compared with controls. The K-nearest neighbor method exhibited the best prediction performance with an accuracy rate of up to 0.86. In conclusion, participants with PD exhibited impaired postural stability and their postural sway features could be identified by machine learning algorithms.

该研究的目的是 (1) 比较帕金森病 (PD) 参与者和健康对照者之间的姿势摇摆，以及 (2) 使用机器学习方法开发和验证 PD 姿势控制模式的自动分类。总共招募了 9 名 PD 早期参与者和 12 名健康对照者。参与者被要求站在测力板上，睁眼和闭眼保持静止 2 分钟。压力数据的中心以 50 Hz 的频率收集。使用混合模型方差分析计算并比较线性位移、标准差、总距离、摇摆面积和压力中心的多尺度熵。使用五种监督机器学习算法（即逻辑回归、K 最近邻、朴素贝叶斯、决策树和随机森林）对 PD 姿势控制模式进行分类。与对照组相比，PD 参与者表现出更大的压力中心波动和变异性。K近邻法表现出最好的预测性能，准确率高达0.86。总之，患有 PD 的参与者表现出姿势稳定性受损，他们的姿势摇摆特征可以通过机器学习算法来识别。