基于机器学习的老年患者定时起立行走测试记录中的助行器检测

Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients.

作者信息

Ziegl Andreas, Hayn Dieter, Kastner Peter, Loffler Kerstin, Weidinger Lisa, Brix Bianca, Goswami Nandu, Schreier Gunter

出版信息

Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:808-811. doi: 10.1109/EMBC44109.2020.9176574.

DOI:10.1109/EMBC44109.2020.9176574

Abstract

Frailty and falls are the main causes of morbidity and disability in elderly people. The Timed Up-and-Go (TUG) test has been proposed as an appropriate method for evaluating elderly individuals' risk of falling. To analyze the TUG's potential for falls prediction, we conducted a clinical study with participants aged ≥ 65 years, living in nursing homes. We harvested 138 TUG recordings with the information, if patients used a walking aid or not and developed a method to predict the use of walking aids using a Random Forest Classifier for ultrasonic based TUG test recordings. We achieved a high accuracy with an Area Under the Curve (AUC) of 96,9% using a 20% leave out evaluation strategy. Automated collection of structured data from TUG recordings - like the use of a walking aid - may help to improve fall risk tools in future.

摘要

衰弱和跌倒为老年人发病和残疾的主要原因。定时起立行走（TUG）测试已被提议作为评估老年人跌倒风险的一种合适方法。为分析TUG在跌倒预测方面的潜力，我们对年龄≥65岁、居住在养老院的参与者进行了一项临床研究。我们收集了138份TUG记录，并记录了患者是否使用助行器的信息，还开发了一种方法，使用基于超声波的TUG测试记录的随机森林分类器来预测助行器的使用情况。使用20%留出法评估策略，我们获得了较高的准确率，曲线下面积（AUC）为96.9%。从TUG记录中自动收集结构化数据，比如是否使用助行器，可能有助于未来改进跌倒风险评估工具。