Hellmers Sandra, Krey Elias, Gashi Arber, Koschate Jessica, Schmidt Laura, Stuckenschneider Tim, Hein Andreas, Zieschang Tania
Assistance Systems and Medical Device Technology, Department for Health Services Research, Carl von Ossietzky University, Oldenburg, Germany.
Geriatric Medicine, Department for Health Services Research, Carl von Ossietzky University, Oldenburg, Germany.
Front Digit Health. 2023 Jul 26;5:1223845. doi: 10.3389/fdgth.2023.1223845. eCollection 2023.
Falls are one of the most common causes of emergency hospital visits in older people. Early recognition of an increased fall risk, which can be indicated by the occurrence of near-falls, is important to initiate interventions.
In a study with 87 subjects we simulated near-fall events on a perturbation treadmill and recorded them with inertial measurement units (IMU) at seven different positions. We investigated different machine learning models for the near-fall detection including support vector machines, AdaBoost, convolutional neural networks, and bidirectional long short-term memory networks. Additionally, we analyzed the influence of the sensor position on the classification results.
The best results showed a DeepConvLSTM with an F1 score of 0.954 (precision 0.969, recall 0.942) at the sensor position "left wrist."
Since these results were obtained in the laboratory, the next step is to evaluate the suitability of the classifiers in the field.
跌倒为老年人急诊就诊的最常见原因之一。早期识别跌倒风险增加（可通过险些跌倒的发生来表明）对于启动干预措施很重要。
在一项针对87名受试者的研究中，我们在扰动跑步机上模拟险些跌倒事件，并使用惯性测量单元（IMU）在七个不同位置进行记录。我们研究了用于险些跌倒检测的不同机器学习模型，包括支持向量机、AdaBoost、卷积神经网络和双向长短期记忆网络。此外，我们分析了传感器位置对分类结果的影响。
最佳结果显示，在传感器位置“左手腕”处，深度卷积长短期记忆网络的F1分数为0.954（精确率0.969，召回率0.942）。
由于这些结果是在实验室中获得的，下一步是评估分类器在实际环境中的适用性。
