Dataset Information

Application of Machine Vision in Classifying Gait Frailty Among Older Adults.

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.

SUBMITTER: Liu Y

PROVIDER: S-EPMC8637841 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Application of Machine Vision in Classifying Gait Frailty Among Older Adults.

Liu Yixin Y He Xiaohai X Wang Renjie R Teng Qizhi Q Hu Rui R Qing Linbo L Wang Zhengyong Z He Xuan X Yin Biao B Mou Yi Y Du Yanping Y Li Xinyi X Wang Hui H Liu Xiaolei X Zhou Lixing L Deng Linghui L Xu Ziqi Z Xiao Chun C Ge Meiling M Sun Xuelian X Jiang Junshan J Chen Jiaoyang J Lin Xinyi X Xia Ling L Gong Haoran H Yu Haopeng H Dong Birong B

Frontiers in aging neuroscience 20211116

<b>Background:</b> 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. <b>Methods:</b> 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 se ...[more]

PMID: 34867286

Similar Datasets

Project description:ObjectiveTo examine whether the association between dopamine-related genotype and gait speed differs according to frailty status or race.DesignCross-sectional population-based study (Cardiovascular Health Study).SettingMulticenter study, four U.S. sites.ParticipantsVolunteer community-dwelling adults aged 65 years and older, without evidence of Parkinson's disease (N = 3,744; 71 years; 82% White; 39% male).MeasurementsGait speed (usual pace; m/s), physical frailty (Fried definition), and genetic polymorphism of catechol-O-methyltransferase (COMT; rs4680), an enzyme regulating tonic brain dopamine levels, were assessed. Interaction of COMT by frailty and by race predicting gait speed were tested, and, if significant, analyses were stratified. Multivariable regression models of COMT predicting gait speed were adjusted for demographics and locomotor risk factors. Sensitivity analyses were repeated, stratified by clinical cutoffs of gait speed (0.6 and 1.0 m/s) instead of frailty status.ResultsThe interaction of COMT by frailty and COMT by race were P = .02 and P = .01, respectively. Compared with Met/Met (higher dopaminergic signaling), the Val/Val group (lower dopaminergic signaling) walked marginally more slowly in the full cohort (0.87 vs 0.89 m/s; P = .2). Gait speed differences were significant for frail (n = 220; 0.55 vs 0.63 m/s; P = .03), but not for prefrail (n = 1,691; 0.81 vs 0.81 m/s; P = .9) or nonfrail (n = 1,833; 0.98 vs 0.97 m/s; P = .7); results were similar in fully adjusted models. Among frail, associations were similar for Whites and Blacks, with statistical significance for Whites only. Associations stratified by clinical cutoffs of gait speed were not significant.ConclusionThe association of dopamine-related genotype with gait speed is stronger among adults with frailty compared with those without frailty. The potential effects of dopaminergic signaling on preserving physical function in biracial cohorts of frail adults should be further examined.

Project description:BackgroundThere is increasing evidence that pre-frailty manifests as early as middle age. Understanding the factors contributing to an early trajectory from good health to pre-frailty in middle aged and older adults is needed to inform timely preventive primary care interventions to mitigate early decline and future frailty.MethodsA cohort of 656 independent community dwelling adults, aged 40-75 years, living in South Australia, undertook a comprehensive health assessment as part of the Inspiring Health cross-sectional observational study. Secondary analysis was completed using machine learning models to identify factors common amongst participants identified as not frail or pre-frail using the Clinical Frailty Scale (CFS) and Fried Frailty Phenotype (FFP). A correlation-based feature selection was used to identify factors associated with pre-frailty classification. Four machine learning models were used to derive the prediction models for classification of not frail and pre-frail. The class discrimination capability of the machine learning algorithms was evaluated using area under the receiver operating characteristic curve (AUC), sensitivity, specificity, precision, F1-score and accuracy.ResultsTwo stages of feature selection were performed. The first stage included 78 physiologic, anthropometric, environmental, social and lifestyle variables. A follow-up analysis with a narrower set of 63 variables was then conducted with physiologic factors associated with the FFP associated features removed, to uncover indirect indicators connected with pre-frailty. In addition to the expected physiologic measures, a range of anthropometric, environmental, social and lifestyle variables were found to be associated with pre-frailty outcomes for the cohort. With FFP variables removed, machine learning (ML) models found higher BMI and lower muscle mass, poorer grip strength and balance, higher levels of distress, poor quality sleep, shortness of breath and incontinence were associated with being classified as pre-frail. The machine learning models achieved an AUC score up to 0.817 and 0.722 for FFP and CFS respectively for predicting pre-frailty. With feature selection, the performance of ML models improved by up to + 7.4% for FFP and up to + 7.9% for CFS.ConclusionsThe results of this study indicate that machine learning methods are well suited for predicting pre-frailty and indicate a range of factors that may be useful to include in targeted health assessments to identify pre-frailty in middle aged and older adults.

Project description:Background and Objectives: The world's population is rapidly aging, and it is estimated that, by 2050, every sixth person on earth will be older than 65 years. Around 30% of older adults entering cardiac rehabilitation (CR) meet the criteria of frailty. Frailty identification has not been included in the routine evaluation of CR patients yet, and there is a lack of evidence on what training regimen for improving physical performance in frail people is optimal. Therefore, the aim of our study was to determine the prevalence of frailty and to evaluate the effect of two different complementary training programs on the gait speed of older vulnerable and frail patients with acute coronary syndrome and mid-range-to-preserved left ventricular ejection fraction (≥40%) during short-term CR. Materials and Methods: This randomized controlled trial was conducted from January 2020 to September 2021. CR participants (n = 97) with a mean age of 73.1 ± 5.3 years were randomly allocated into three groups: control (CG, n = 32), intervention-1 (IG-1, n = 32) and intervention-2 (IG-2, n = 33). The patients of all three groups attended a usual inpatient CR program, and two intervention groups additionally received different resistance and balance training programs 3 days a week: the IG-1 underwent complementary training with traditional means of physical therapy, while the IG-2 underwent complementary training with mechanical devices. The mean CR duration was 18.9 ± 1.7 days. Frailty was assessed with the Edmonton Frail Scale, and the 5 m walk test was used to evaluate gait speed. Results: Frailty was determined in 37.1% of participants, and 42.3% met the criteria of being vulnerable. After CR, the gait speed of frail and vulnerable patients significantly improved in all three groups (p < 0.05). In the IG-2, slow gait speed was reversed to normal in the overwhelming majority of patients (p < 0.05), while the CG had the greatest proportion of patients who remained to be slow after CR (p < 0.05). Conclusions: A considerable part of patients entering CR are frail or vulnerable; therefore, it is of crucial importance to assess frailty status in all older people. All three CR programs improved gait speed in frail and vulnerable older patients with ischemic heart disease. Complementary resistance and balance training with mechanical devices more effectively reversed slow gait speed to normal during short-term CR.

Dataset Information

Application of Machine Vision in Classifying Gait Frailty Among Older Adults.

Publications

Application of Machine Vision in Classifying Gait Frailty Among Older Adults.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets