Technology Research for Independent Living, Leixlip, Ireland.
Gerontology. 2012;58(5):472-80. doi: 10.1159/000337259. Epub 2012 May 10.
Falls are the most common cause of injury and hospitalization and one of the principal causes of death and disability in older adults worldwide. This study aimed to determine if a method based on body-worn sensor data can prospectively predict falls in community-dwelling older adults, and to compare its falls prediction performance to two standard methods on the same data set.
Data were acquired using body-worn sensors, mounted on the left and right shanks, from 226 community-dwelling older adults (mean age 71.5 ± 6.7 years, 164 female) to quantify gait and lower limb movement while performing the 'Timed Up and Go' (TUG) test in a geriatric research clinic. Participants were contacted by telephone 2 years following their initial assessment to determine if they had fallen. These outcome data were used to create statistical models to predict falls.
Results obtained through cross-validation yielded a mean classification accuracy of 79.69% (mean 95% CI: 77.09-82.34) in prospectively identifying participants that fell during the follow-up period. Results were significantly (p < 0.0001) more accurate than those obtained for falls risk estimation using two standard measures of falls risk (manually timed TUG and the Berg balance score, which yielded mean classification accuracies of 59.43% (95% CI: 58.07-60.84) and 64.30% (95% CI: 62.56-66.09), respectively).
Results suggest that the quantification of movement during the TUG test using body-worn sensors could lead to a robust method for assessing future falls risk.
跌倒在全球范围内是导致伤害和住院的最常见原因之一，也是老年人死亡和残疾的主要原因之一。本研究旨在确定基于穿戴式传感器数据的方法是否可以前瞻性地预测社区居住的老年人跌倒，并将其跌倒预测性能与同一数据集上的两种标准方法进行比较。
从 226 名社区居住的老年人（平均年龄 71.5±6.7 岁，164 名女性）身上采集穿戴式传感器数据，这些传感器分别安装在左右小腿上，以量化他们在老年研究诊所进行“计时起立行走”（TUG）测试时的步态和下肢运动。在初始评估后 2 年，通过电话联系参与者以确定他们是否跌倒。这些结果数据用于创建统计模型来预测跌倒。
通过交叉验证获得的结果表明，在前瞻性识别随访期间跌倒的参与者方面，平均分类准确率为 79.69%（平均 95%CI：77.09-82.34）。结果显著（p<0.0001）优于使用两种标准跌倒风险评估方法（手动计时 TUG 和伯格平衡评分）获得的结果，这两种方法的平均分类准确率分别为 59.43%（95%CI：58.07-60.84）和 64.30%（95%CI：62.56-66.09）。
结果表明，使用穿戴式传感器对 TUG 测试中的运动进行量化可能会导致一种评估未来跌倒风险的可靠方法。
