Frontiers in Aging Neuroscience (Nov 2021)
Application of Machine Vision in Classifying Gait Frailty Among Older Adults
- Yixin Liu,
- Yixin Liu,
- Yixin Liu,
- Xiaohai He,
- Renjie Wang,
- Qizhi Teng,
- Rui Hu,
- Linbo Qing,
- Zhengyong Wang,
- Xuan He,
- Biao Yin,
- Yi Mou,
- Yanping Du,
- Xinyi Li,
- Hui Wang,
- Hui Wang,
- Hui Wang,
- Xiaolei Liu,
- Xiaolei Liu,
- Xiaolei Liu,
- Lixing Zhou,
- Lixing Zhou,
- Lixing Zhou,
- Linghui Deng,
- Linghui Deng,
- Linghui Deng,
- Ziqi Xu,
- Chun Xiao,
- Meiling Ge,
- Meiling Ge,
- Meiling Ge,
- Xuelian Sun,
- Xuelian Sun,
- Xuelian Sun,
- Junshan Jiang,
- Jiaoyang Chen,
- Xinyi Lin,
- Ling Xia,
- Haoran Gong,
- Haopeng Yu,
- Haopeng Yu,
- Birong Dong,
- Birong Dong,
- Birong Dong
Affiliations
- Yixin Liu
- National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Yixin Liu
- Geriatric Health Care and Medical Research Center, Sichuan University, Chengdu, China
- Yixin Liu
- Department of Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Xiaohai He
- College of Electronics and Information Engineering, Sichuan University, Chengdu, China
- Renjie Wang
- Department of Rehabilitation Medicine, West China Hospital, Sichuan University, Chengdu, China
- Qizhi Teng
- College of Electronics and Information Engineering, Sichuan University, Chengdu, China
- Rui Hu
- College of Electronics and Information Engineering, Sichuan University, Chengdu, China
- Linbo Qing
- College of Electronics and Information Engineering, Sichuan University, Chengdu, China
- Zhengyong Wang
- College of Electronics and Information Engineering, Sichuan University, Chengdu, China
- Xuan He
- College of Electronics and Information Engineering, Sichuan University, Chengdu, China
- Biao Yin
- College of Electronics and Information Engineering, Sichuan University, Chengdu, China
- Yi Mou
- Geroscience and Chronic Disease Department, The 8th Municipal Hospital for the People, Chengdu, China
- Yanping Du
- Department of Rehabilitation Medicine, West China Hospital, Sichuan University, Chengdu, China
- Xinyi Li
- Medical Examination Center, Aviation Industry Corporation of China 363 Hospital, Chengdu, China
- Hui Wang
- National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Hui Wang
- Geriatric Health Care and Medical Research Center, Sichuan University, Chengdu, China
- Hui Wang
- Department of Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Xiaolei Liu
- National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Xiaolei Liu
- Geriatric Health Care and Medical Research Center, Sichuan University, Chengdu, China
- Xiaolei Liu
- Department of Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Lixing Zhou
- National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Lixing Zhou
- Geriatric Health Care and Medical Research Center, Sichuan University, Chengdu, China
- Lixing Zhou
- Department of Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Linghui Deng
- National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Linghui Deng
- Geriatric Health Care and Medical Research Center, Sichuan University, Chengdu, China
- Linghui Deng
- Department of Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Ziqi Xu
- West China School of Basic Medical Sciences and Forensic Medicine, Sichuan University, Chengdu, China
- Chun Xiao
- National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Meiling Ge
- National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Meiling Ge
- Geriatric Health Care and Medical Research Center, Sichuan University, Chengdu, China
- Meiling Ge
- Department of Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Xuelian Sun
- National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Xuelian Sun
- Geriatric Health Care and Medical Research Center, Sichuan University, Chengdu, China
- Xuelian Sun
- Department of Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Junshan Jiang
- Medical College, Jiangsu University, Zhenjiang, China
- Jiaoyang Chen
- 0Public Health Department, Chengdu Medical College, Chengdu, China
- Xinyi Lin
- 0Public Health Department, Chengdu Medical College, Chengdu, China
- Ling Xia
- 0Public Health Department, Chengdu Medical College, Chengdu, China
- Haoran Gong
- 1West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, China
- Haopeng Yu
- 1West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, China
- Haopeng Yu
- 2Med-X Center for Informatics, Sichuan University, Chengdu, China
- Birong Dong
- National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- Birong Dong
- Geriatric Health Care and Medical Research Center, Sichuan University, Chengdu, China
- Birong Dong
- Department of Geriatrics, West China Hospital, Sichuan University, Chengdu, China
- DOI
- https://doi.org/10.3389/fnagi.2021.757823
- Journal volume & issue
-
Vol. 13
Abstract
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.
Keywords
