Dataset for Accuracy of an accelerometer-based smartphone application for balance assessment to predict falls in older adults

The purpose of this study was to examine the accuracy of an ACC-based smartphone application for predicting falls in community-dwelling older persons and to determine whether ACC-based smartphone balance assessment approach was more successful at predicting falls in older adults. At baseline, eighty older persons completed a balance evaluation using an accelerometer-based smartphone application that includes the Modified Clinical Test of Sensory Interaction in Balance (MCTSIB), a single-leg stance (SL) test, and a limit of stability (LOS) test. Additionally, the fall rate was documented throughout a six-month follow-up period. Accuracy was determined using the area under the receiver operating characteristic curve (AUC).

本研究旨在验证基于加速度计（accelerometer, ACC）的智能手机应用程序预测社区居住老年人跌倒风险的准确性，并探讨该基于加速度计的智能手机平衡评估方法在老年人跌倒预测中的有效性是否更优。基线阶段，80名老年人通过基于加速度计的智能手机应用程序完成了平衡评估，该评估涵盖平衡感觉交互作用改良临床测试（Modified Clinical Test of Sensory Interaction in Balance, MCTSIB）、单腿站立（single-leg stance, SL）测试及稳定极限（limit of stability, LOS）测试。此外，研究记录了受试者在6个月随访期内的跌倒发生情况。最终采用受试者工作特征曲线下面积（area under the receiver operating characteristic curve, AUC）评估模型的预测准确性。