Supratak Akara, Datta Gourab, Gafson Arie R, Nicholas Richard, Guo Yike, Matthews Paul M
Data Science Institute, Imperial College London London, United Kingdom.
Division of Brain Sciences, Department of Medicine, Imperial College London, London, United Kingdom.
Front Neurol. 2018 Jul 13;9:561. doi: 10.3389/fneur.2018.00561. eCollection 2018.
The timed 25-foot walk (T25FW) is widely used as a clinic performance measure, but has yet to be directly validated against gait speed in the home environment. To develop an accurate method for remote assessment of walking speed and to test how predictive the clinic T25FW is for real-life walking. An AX3-Axivity tri-axial accelerometer was positioned on 32 MS patients (Expanded Disability Status Scale [EDSS] 0-6) in the clinic, who subsequently wore it at home for up to 7 days. Gait speed was calculated from these data using both a model developed with healthy volunteers and models generated from a machine learning algorithm. The healthy volunteer model predicted gait speed poorly for more disabled people with MS. However, the accuracy of individually personalized models was high regardless of disability (-value = 0.98, -value = 1.85 × 10). With the latter, we confirmed that the clinic T25FW is strongly predictive of the maximum sustained gait speed in the home environment (-value = 0.89, -value = 4.34 × 10). Remote gait monitoring with individually personalized models is accurate for patients with MS. Using these models, we have directly validated the clinical meaningfulness (i.e., predictiveness) of the clinic T25FW for the first time.
25英尺定时步行测试（T25FW）被广泛用作临床性能指标，但尚未在家庭环境中针对步态速度进行直接验证。目的是开发一种准确的远程评估步行速度的方法，并测试临床T25FW对现实生活中步行的预测能力。在诊所中，将AX3-Axivity三轴加速度计放置在32名多发性硬化症患者（扩展残疾状态量表[EDSS]为0-6）身上，随后他们在家中佩戴该加速度计长达7天。使用与健康志愿者一起开发的模型以及由机器学习算法生成的模型，根据这些数据计算步态速度。健康志愿者模型对残疾程度较高的多发性硬化症患者的步态速度预测效果不佳。然而，无论残疾程度如何，个性化模型的准确性都很高（R值 = 0.98，P值 = 1.85 × 10）。使用后者，我们证实临床T25FW对家庭环境中的最大持续步态速度具有很强的预测性（R值 = 0.89，P值 = 4.34 × 10）。使用个性化模型进行远程步态监测对多发性硬化症患者是准确的。通过使用这些模型，我们首次直接验证了临床T25FW的临床意义（即预测性）。
