eMedia Research Lab/STADIUS, Department of Electrical Engineering (ESAT), KU Leuven, Andreas Vesaliusstraat 13, 3000 Leuven, Belgium; Intelligent Mobile Platform Research Group, Department of Mechanical Engineering, KU Leuven, Andreas Vesaliusstraat 13, 3000 Leuven, Belgium.
Research Group for Neurorehabilitation (eNRGy), Department of Rehabilitation Sciences, KU Leuven, Tervuursevest 101, 3001 Heverlee, Belgium.
Gait Posture. 2020 Jul;80:130-136. doi: 10.1016/j.gaitpost.2020.05.026. Epub 2020 May 23.
Manual annotation of initial contact (IC) and end contact (EC) is a time consuming process. There are currently no robust techniques available to automate this process for Parkinson's disease (PD) patients with freezing of gait (FOG).
To determine the validity of a data-driven approach for automated gait event detection.
15 freezers were asked to complete several straight-line and 360 degree turning trials in a 3D gait laboratory during the off-period of their medication cycle. Trials that contained a freezing episode were indicated as freezing trials (FOG) and trials without a freezing episode were termed as functional gait (FG). Furthermore, the highly varied gait data between onset and termination of a FOG episode was excluded. A Temporal Convolutional Neural network (TCN) was trained end-to-end with lower extremity kinematics. A Bland-Altman analysis was performed to evaluate the agreement between the results of the proposed model and the manual annotations.
For FOG-trials, F1 scores of 0.995 and 0.992 were obtained for IC and EC, respectively. For FG-trials, F1 scores of 0.997 and 0.999 were obtained for IC and EC, respectively. The Bland-Altman plots indicated excellent timing agreement, with on average 39% and 47% of the model predictions occurring within 10 ms from the manual annotations for FOG-trials and FG-trials, respectively.
These results indicate that our data-driven approach for detecting gait events in PD patients with FOG is sufficiently accurate and reliable for clinical applications.
手动标注初始接触 (IC) 和结束接触 (EC) 是一个耗时的过程。目前尚无针对冻结步态 (FOG) 的帕金森病 (PD) 患者进行自动标注的稳健技术。
确定一种数据驱动方法自动检测步态事件的有效性。
15 名冻结者在药物周期的停药期内被要求在 3D 步态实验室中完成几次直线和 360 度转弯试验。包含冻结事件的试验被标记为冻结试验 (FOG)，没有冻结事件的试验被称为功能步态 (FG)。此外，还排除了 FOG 事件起始和结束时高度变化的步态数据。一个时间卷积神经网络 (TCN) 与下肢运动学进行端到端训练。进行 Bland-Altman 分析以评估所提出模型的结果与手动标注之间的一致性。
对于 FOG 试验，IC 和 EC 的 F1 分数分别为 0.995 和 0.992。对于 FG 试验，IC 和 EC 的 F1 分数分别为 0.997 和 0.999。Bland-Altman 图表明了极好的时间一致性，平均有 39%和 47%的模型预测与 FOG 试验和 FG 试验的手动标注相差 10ms 以内。
这些结果表明，我们用于检测 FOG 的 PD 患者步态事件的基于数据的方法具有足够的准确性和可靠性，可用于临床应用。
