当前位置: X-MOL 学术J. Appl. Biomech. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Accuracy and Reliability of Onset Detection Algorithms in Gait Initiation for Healthy Controls and Participants With Parkinson's Disease.
Journal of Applied Biomechanics ( IF 1.4 ) Pub Date : 2019-10-18 , DOI: 10.1123/jab.2018-0431
Aisha Chen 1 , Sandhya Selvaraj 1 , Vennila Krishnan 1 , Shadnaz Asgari 1
Affiliation  

Accurate and reliable detection of the onset of gait initiation is essential for the correct assessment of gait. Thus, this study was aimed at evaluation of the reliability and accuracy of 3 different center of pressure-based gait onset detection algorithms: A displacement baseline-based algorithm (method 1), a velocity baseline-based algorithm (method 2), and a velocity extrema-based algorithm (method 3). The center of pressure signal was obtained during 10 gait initiation trials from 16 healthy participants and 3 participants with Parkinson's disease. Intrasession and absolute reliability of each algorithm was assessed using the intraclass correlation coefficient and the coefficient of variation of center of pressure displacement during the postural phase of gait initiation. The accuracy was evaluated using the time error of the detected onset by each algorithm relative to that of visual inspection. The authors' results revealed that although all 3 algorithms had high to very high intrasession reliabilities in both healthy subjects and subjects with Parkinson's disease, methods 2 and 3 showed significantly better absolute reliability than method 1 in healthy controls (P = .001). Furthermore, method 2 outperformed the other 2 algorithms in both healthy subjects and subjects with Parkinson's disease with an overall accuracy of 0.80. Based on these results, the authors recommend using method 2 for accurate and reliable gait onset detection.

中文翻译:

开始检测算法在健康对照和帕金森病参与者步态启动中的准确性和可靠性。

准确可靠地检测步态开始的开始对于正确评估步态至关重要。因此,本研究旨在评估 3 种不同的基于压力的步态起始检测算法的可靠性和准确性:基于位移基线的算法(方法 1)、基于速度基线的算法(方法 2)和基于速度极值的算法(方法 3)。压力信号中心是在 16 名健康参与者和 3 名帕金森病参与者的 10 次步态启动试验中获得的。使用组内相关系数和步态起始姿势阶段压力位移中心的变异系数评估每个算法的会话内和绝对可靠性。使用每种算法检测到的发病时间相对于视觉检查的时间误差来评估准确性。作者的结果表明,尽管所有 3 种算法在健康受试者和帕金森病受试者中都具有高到非常高的会话期间可靠性,但方法 2 和 3 在健康对照组中显示出明显优于方法 1 的绝对可靠性 (P = .001)。此外,方法 2 在健康受试者和帕金森病受试者中均优于其他 2 种算法,总体准确度为 0.80。基于这些结果,作者建议使用方法 2 进行准确可靠的步态起始检测。结果显示,尽管所有 3 种算法在健康受试者和帕金森病受试者中都具有高到非常高的会话期间可靠性,但方法 2 和 3 在健康对照组中显示出明显优于方法 1 的绝对可靠性 (P = .001)。此外,方法 2 在健康受试者和帕金森病受试者中均优于其他 2 种算法,总体准确度为 0.80。基于这些结果,作者建议使用方法 2 进行准确可靠的步态起始检测。结果显示,尽管所有 3 种算法在健康受试者和帕金森病受试者中都具有高到非常高的会话期间可靠性,但方法 2 和 3 在健康对照组中显示出明显优于方法 1 的绝对可靠性 (P = .001)。此外,方法 2 在健康受试者和帕金森病受试者中均优于其他 2 种算法,总体准确度为 0.80。基于这些结果,作者建议使用方法 2 进行准确可靠的步态起始检测。s 疾病的总体准确度为 0.80。基于这些结果,作者建议使用方法 2 进行准确可靠的步态起始检测。s 疾病的总体准确度为 0.80。基于这些结果,作者建议使用方法 2 进行准确可靠的步态起始检测。
更新日期:2019-11-01
down
wechat
bug