使用关节节点图的深度学习和机器学习方法检测年轻和老年成年人的姿势控制。

Detection of Postural Control in Young and Elderly Adults Using Deep and Machine Learning Methods with Joint-Node Plots.

机构信息

Department of Occupation Therapy, I-Shou University, No. 8, Yida Rd., Jiaosu Village, Yanchao District, Kaohsiung 82445, Taiwan.

Department of Medical Imaging and Radiological Science, I-Shou University, No. 8, Yida Rd., Jiaosu Village, Yanchao District, Kaohsiung 82445, Taiwan.

出版信息

Sensors (Basel). 2021 May 5;21(9):3212. doi: 10.3390/s21093212.

DOI:10.3390/s21093212

PMID:34063144

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8124823/

Abstract

Postural control decreases with aging. Thus, an efficient and accurate method of detecting postural control is needed. We enrolled 35 elderly adults (aged 82.06 ± 8.74 years) and 20 healthy young adults (aged 21.60 ± 0.60 years) who performed standing tasks for 40 s, performed six times. The coordinates of 15 joint nodes were captured using a Kinect device (30 Hz). We plotted joint positions into a single 2D figure (named a joint-node plot, JNP) once per second for up to 40 s. A total of 15 methods combining deep and machine learning for postural control classification were investigated. The accuracy, sensitivity, specificity, positive predicted value (PPV), negative predicted value (NPV), and kappa values of the selected methods were assessed. The highest PPV, NPV, accuracy, sensitivity, specificity, and kappa values were higher than 0.9 in validation testing. The presented method using JNPs demonstrated strong performance in detecting the postural control ability of young and elderly adults.

摘要

姿势控制随着年龄的增长而下降。因此，需要一种高效、准确的姿势控制检测方法。我们招募了 35 名老年人（年龄 82.06 ± 8.74 岁）和 20 名健康的年轻人（年龄 21.60 ± 0.60 岁），他们进行了 40 秒的站立任务，共进行了 6 次。使用 Kinect 设备（30 Hz）捕获了 15 个关节节点的坐标。我们每秒绘制一次关节位置，最多绘制 40 秒，形成一个二维图（称为关节节点图，JNP）。总共研究了 15 种结合深度学习和机器学习的姿势控制分类方法。评估了所选方法的准确性、敏感性、特异性、阳性预测值（PPV）、阴性预测值（NPV）和kappa 值。在验证测试中，所选方法的最高 PPV、NPV、准确性、敏感性、特异性和 kappa 值均高于 0.9。使用 JNPs 的提出的方法在检测年轻和老年人的姿势控制能力方面表现出了强大的性能。