Center for the Study of Movement, Cognition and Mobility, Neurological Institute, Tel Aviv Sourasky Medical Center, Tel Aviv 6492416, Israel.
Sagol School of Neuroscience, Tel Aviv University, Tel Aviv 6997801, Israel.
Sensors (Basel). 2022 Sep 19;22(18):7094. doi: 10.3390/s22187094.
Remote assessment of the gait of older adults (OAs) during daily living using wrist-worn sensors has the potential to augment clinical care and mobility research. However, hand movements can degrade gait detection from wrist-sensor recordings. To address this challenge, we developed an anomaly detection algorithm and compared its performance to four previously published gait detection algorithms. Multiday accelerometer recordings from a wrist-worn and lower-back sensor (i.e., the “gold-standard” reference) were obtained in 30 OAs, 60% with Parkinson’s disease (PD). The area under the receiver operator curve (AUC) and the area under the precision−recall curve (AUPRC) were used to evaluate the performance of the algorithms. The anomaly detection algorithm obtained AUCs of 0.80 and 0.74 for OAs and PD, respectively, but AUPRCs of 0.23 and 0.31 for OAs and PD, respectively. The best performing detection algorithm, a deep convolutional neural network (DCNN), exhibited high AUCs (i.e., 0.94 for OAs and 0.89 for PD) but lower AUPRCs (i.e., 0.66 for OAs and 0.60 for PD), indicating trade-offs between precision and recall. When choosing a classification threshold of 0.9 (i.e., opting for high precision) for the DCNN algorithm, strong correlations (r > 0.8) were observed between daily living walking time estimates based on the lower-back (reference) sensor and the wrist sensor. Further, gait quality measures were significantly different in OAs and PD compared to healthy adults. These results demonstrate that daily living gait can be quantified using a wrist-worn sensor.
使用腕戴式传感器对老年人（OAs）在日常生活中的步态进行远程评估，有可能增强临床护理和移动性研究。然而，手部运动会降低腕部传感器记录的步态检测精度。为了解决这一挑战，我们开发了一种异常检测算法，并将其性能与之前发表的四种步态检测算法进行了比较。在 30 名 OAs 中（60%患有帕金森病（PD）），使用腕戴式和下背部传感器（即“金标准”参考）获得了多天的加速度计记录。使用接收器操作曲线下面积（AUC）和精度-召回曲线下面积（AUPRC）评估算法的性能。异常检测算法分别获得了 0.80 和 0.74 的 AUC，分别为 OAs 和 PD，但分别为 0.23 和 0.31 的 AUPRC，OAs 和 PD。表现最佳的检测算法，即深度卷积神经网络（DCNN），表现出较高的 AUC（即，OAs 为 0.94，PD 为 0.89），但较低的 AUPRC（即，OAs 为 0.66，PD 为 0.60），表明精度和召回率之间存在权衡。当为 DCNN 算法选择分类阈值为 0.9（即选择高精度）时，基于下背部（参考）传感器和腕部传感器的日常生活行走时间估计之间观察到很强的相关性（r>0.8）。此外，与健康成年人相比，OAs 和 PD 的步态质量测量值有显著差异。这些结果表明，日常生活中的步态可以使用腕戴式传感器进行量化。
