Application of Machine Vision in Classifying Gait Frailty Among Older Adults

Frontiers in Aging Neuroscience

Xinyi Lin¹  Jiaoyang Chen¹  Ling Xia¹  Haoran Gong²  Haopeng Yu³  Xuan He⁴  Rui Hu⁴  Zhengyong Wang⁴  Qizhi Teng⁴  Linbo Qing⁴  Biao Yin⁴  Xiaohai He⁴  Xuelian Sun⁵  Meiling Ge⁵  Linghui Deng⁵  Lixing Zhou⁵  Hui Wang⁵  Birong Dong⁵  Xiaolei Liu⁵  Yixin Liu⁵  Renjie Wang⁶  Yanping Du⁶  Yi Mou⁸  Junshan Jiang⁹  Xinyi Li^1,10  Chun Xiao^1,11  Ziqi Xu^1,12 

[1] 0Public Health Department, Chengdu Medical College, Chengdu, China;1West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, China;2Med-X Center for Informatics, Sichuan University, Chengdu, China;College of Electronics and Information Engineering, Sichuan University, Chengdu, China;Department of Geriatrics, West China Hospital, Sichuan University, Chengdu, China;Department of Rehabilitation Medicine, West China Hospital, Sichuan University, Chengdu, China;Geriatric Health Care and Medical Research Center, Sichuan University, Chengdu, China;Geroscience and Chronic Disease Department, The 8th Municipal Hospital for the People, Chengdu, China;Medical College, Jiangsu University, Zhenjiang, China;Medical Examination Center, Aviation Industry Corporation of China 363 Hospital, Chengdu, China;National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, China;West China School of Basic Medical Sciences and Forensic Medicine, Sichuan University, Chengdu, China;

关键词: frailty;    gait;    machine vision;    biomarkers;    preventative health care;    feature extraction;   

DOI  :  10.3389/fnagi.2021.757823

来源: DOAJ

【 摘 要 】

Background: Frail older adults have an increased risk of adverse health outcomes and premature death. They also exhibit altered gait characteristics in comparison with healthy individuals.Methods: In this study, we created a Fried’s frailty phenotype (FFP) labelled casual walking video set of older adults based on the West China Health and Aging Trend study. A series of hyperparameters in machine vision models were evaluated for body key point extraction (AlphaPose), silhouette segmentation (Pose2Seg, DPose2Seg, and Mask R-CNN), gait feature extraction (Gaitset, LGaitset, and DGaitset), and feature classification (AlexNet and VGG16), and were highly optimised during analysis of gait sequences of the current dataset.Results: The area under the curve (AUC) of the receiver operating characteristic (ROC) at the physical frailty state identification task for AlexNet was 0.851 (0.827–0.8747) and 0.901 (0.878–0.920) in macro and micro, respectively, and was 0.855 (0.834–0.877) and 0.905 (0.886–0.925) for VGG16 in macro and micro, respectively. Furthermore, this study presents the machine vision method equipped with better predictive performance globally than age and grip strength, as well as than 4-m-walking-time in healthy and pre-frailty classifying.Conclusion: The gait analysis method in this article is unreported and provides promising original tool for frailty and pre-frailty screening with the characteristics of convenience, objectivity, rapidity, and non-contact. These methods can be extended to any gait-related disease identification processes, as well as in-home health monitoring.

【 授权许可】

Unknown