Université Paris Saclay, Université Paris Cité, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, Gif-sur-Yvette, France.
Service de Neurologie, Service de Santé des Armées, HIA Percy, Clamart, France.
J Neuroeng Rehabil. 2024 Jun 18;21(1):104. doi: 10.1186/s12984-024-01405-x.
Recently, the use of inertial measurement units (IMUs) in quantitative gait analysis has been widely developed in clinical practice. Numerous methods have been developed for the automatic detection of gait events (GEs). While many of them have achieved high levels of efficiency in healthy subjects, detecting GEs in highly degraded gait from moderate to severely impaired patients remains a challenge. In this paper, we aim to present a method for improving GE detection from IMU recordings in such cases.
We recorded 10-meter gait IMU signals from 13 healthy subjects, 29 patients with multiple sclerosis, and 21 patients with post-stroke equino varus foot. An instrumented mat was used as the gold standard. Our method detects GEs from filtered acceleration free from gravity and gyration signals. Firstly, we use autocorrelation and pattern detection techniques to identify a reference stride pattern. Next, we apply multiparametric Dynamic Time Warping to annotate this pattern from a model stride, in order to detect all GEs in the signal.
We analyzed 16,819 GEs recorded from healthy subjects and achieved an F1-score of 100%, with a median absolute error of 8 ms (IQR [3-13] ms). In multiple sclerosis and equino varus foot cohorts, we analyzed 6067 and 8951 GEs, respectively, with F1-scores of 99.4% and 96.3%, and median absolute errors of 18 ms (IQR [8-39] ms) and 26 ms (IQR [12-50] ms).
Our results are consistent with the state of the art for healthy subjects and demonstrate a good accuracy in GEs detection for pathological patients. Therefore, our proposed method provides an efficient way to detect GEs from IMU signals, even in degraded gaits. However, it should be evaluated in each cohort before being used to ensure its reliability.
最近，惯性测量单元（IMU）在定量步态分析中的应用在临床实践中得到了广泛的发展。已经开发出许多用于自动检测步态事件（GEs）的方法。虽然其中许多方法在健康受试者中都达到了高效率，但在从中度到严重受损的患者中检测高度退化的步态 GEs 仍然是一个挑战。在本文中，我们旨在提出一种改进从 IMU 记录中检测 GEs 的方法。
我们从 13 名健康受试者、29 名多发性硬化症患者和 21 名脑卒中后马蹄内翻足患者记录了 10 米步态 IMU 信号。使用仪器垫作为金标准。我们的方法从无重力和旋转信号滤波的加速度中检测 GEs。首先，我们使用自相关和模式检测技术来识别参考步幅模式。接下来，我们应用多参数动态时间规整来从模型步幅中注释此模式，以便在信号中检测到所有 GEs。
我们分析了从健康受试者记录的 16819 个 GEs，获得了 100%的 F1 分数，中位数绝对误差为 8 毫秒（IQR [3-13] 毫秒）。在多发性硬化症和马蹄内翻足队列中，我们分别分析了 6067 和 8951 个 GEs，F1 分数分别为 99.4%和 96.3%，中位数绝对误差分别为 18 毫秒（IQR [8-39] 毫秒）和 26 毫秒（IQR [12-50] 毫秒）。
我们的结果与健康受试者的最新技术水平一致，并证明了在病理患者中检测 GEs 的准确性较好。因此，我们提出的方法为从 IMU 信号中检测 GEs 提供了一种有效的方法，即使在退化的步态中也是如此。然而，在将其用于确保可靠性之前，应该在每个队列中进行评估。
