Lien Wei-Chih, Ching Congo Tak-Shing, Lai Zheng-Wei, Wang Hui-Min David, Lin Jhih-Siang, Huang Yen-Chang, Lin Feng-Huei, Wang Wen-Fong
Department of Physical Medicine and Rehabilitation, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan.
Department of Physical Medicine and Rehabilitation, College of Medicine, National Cheng Kung University, Tainan, Taiwan.
Front Bioeng Biotechnol. 2022 May 13;10:887269. doi: 10.3389/fbioe.2022.887269. eCollection 2022.
This study aimed to use the k-nearest neighbor (kNN) algorithm, which combines gait stability and symmetry derived from a normalized cross-correlation () analysis of acceleration signals from the bilateral ankles of older adults, to assess fall risk. Fifteen non-fallers and 12 recurrent fallers without clinically significant musculoskeletal and neurological diseases participated in the study. Sex, body mass index, previous falls, and the results of the 10 m walking test (10 MWT) were recorded. The acceleration of the five gait cycles from the midsection of each 10 MWT was used to calculate the unilateral coefficients for gait stability and bilateral coefficients for gait symmetry, and then kNN was applied for classifying non-fallers and recurrent fallers. The duration of the 10 MWT was longer among recurrent fallers than it was among non-fallers ( < 0.05). Since the gait signals were acquired from tri-axial accelerometry, the kNN F1 scores with the x-axis components were 92% for non-fallers and 89% for recurrent fallers, and the root sum of squares (RSS) of the signals was 95% for non-fallers and 94% for recurrent fallers. The kNN classification on gait stability and symmetry revealed good accuracy in terms of distinguishing non-fallers and recurrent fallers. Specifically, it was concluded that the RSS-based coefficients can serve as effective gait features to assess the risk of falls.
本研究旨在使用k近邻（kNN）算法评估跌倒风险，该算法结合了通过对老年人双侧脚踝加速度信号进行归一化互相关（）分析得出的步态稳定性和对称性。15名未跌倒者和12名无临床显著肌肉骨骼和神经系统疾病的复发性跌倒者参与了该研究。记录了性别、体重指数、既往跌倒情况以及10米步行测试（10MWT）的结果。利用每次10MWT中段的五个步态周期的加速度来计算步态稳定性的单侧系数和步态对称性的双侧系数，然后应用kNN对未跌倒者和复发性跌倒者进行分类。复发性跌倒者的10MWT持续时间比未跌倒者长（<0.05）。由于步态信号是通过三轴加速度计采集的，kNN在x轴分量上的F1分数，未跌倒者为92%，复发性跌倒者为89%，信号的均方根（RSS），未跌倒者为95%，复发性跌倒者为94%。kNN对步态稳定性和对称性的分类在区分未跌倒者和复发性跌倒者方面显示出良好的准确性。具体而言，得出的结论是，基于RSS的系数可作为评估跌倒风险的有效步态特征。
