Application of Machine Vision in Classifying Gait Frailty Among Older Adults

Machine vision-based gait scan method for identifying cognitive impairment in older adults

Objective

Early identification of cognitive impairment in older adults could reduce the burden of age-related disabilities. Gait parameters are associated with and predictive of cognitive decline. Although a variety of sensors and machine learning analysis methods have been used in cognitive studies, a deep optimized machine vision-based method for analyzing gait to identify cognitive decline is needed.

Methods

This study used a walking footage dataset of 158 adults named West China Hospital Elderly Gait, which was labelled by performance on the Short Portable Mental Status Questionnaire. We proposed a novel recognition network, Deep Optimized GaitPart (DO-GaitPart), based on silhouette and skeleton gait images. Three improvements were applied: short-term temporal template generator (STTG) in the template generation stage to decrease computational cost and minimize loss of temporal information; depth-wise spatial feature extractor (DSFE) to extract both global and local fine-grained spatial features from gait images; and multi-scale temporal aggregation (MTA), a temporal modeling method based on attention mechanism, to improve the distinguishability of gait patterns.

Results

An ablation test showed that each component of DO-GaitPart was essential. DO-GaitPart excels in backpack walking scene on CASIA-B dataset, outperforming comparison methods, which were GaitSet, GaitPart, MT3D, 3D Local, TransGait, CSTL, GLN, GaitGL and SMPLGait on Gait3D dataset. The proposed machine vision gait feature identification method achieved a receiver operating characteristic/area under the curve (ROCAUC) of 0.876 (0.852-0.900) on the cognitive state classification task.

Conclusion

The proposed method performed well identifying cognitive decline from the gait video datasets, making it a prospective prototype tool in cognitive assessment.

Exploring the potential of the sit-to-stand test for self-assessment of physical condition in advanced knee osteoarthritis patients using computer vision

Introduction

Knee osteoarthritis (KOA) is a prevalent condition often associated with a decline in patients' physical function. Objective self-assessment of physical conditions poses challenges for many advanced KOA patients. To address this, we explored the potential of a computer vision method to facilitate home-based physical function self-assessments.

Methods

We developed and validated a simple at-home artificial intelligence approach to recognize joint stiffness levels and physical function in individuals with advanced KOA. One hundred and four knee osteoarthritis (KOA) patients were enrolled, and we employed the WOMAC score to evaluate their physical function and joint stiffness. Subsequently, patients independently recorded videos of five sit-to-stand tests in a home setting. Leveraging the AlphaPose and VideoPose algorithms, we extracted time-series data from these videos, capturing three-dimensional spatiotemporal information reflecting changes in key joint angles over time. To deepen our study, we conducted a quantitative analysis using the discrete wavelet transform (DWT), resulting in two wavelet coefficients: the approximation coefficients (cA) and the detail coefficients (cD).

Results

Our analysis specifically focused on four crucial joint angles: "the right hip," "right knee," "left hip," and "left knee." Qualitative analysis revealed distinctions in the time-series data related to functional limitations and stiffness among patients with varying levels of KOA. In quantitative analysis, we observed variations in the cA among advanced KOA patients with different levels of physical function and joint stiffness. Furthermore, there were no significant differences in the cD between advanced KOA patients, demonstrating different levels of physical function and joint stiffness. It suggests that the primary difference in overall movement patterns lies in the varying degrees of joint stiffness and physical function among advanced KOA patients.

Discussion

Our method, designed to be low-cost and user-friendly, effectively captures spatiotemporal information distinctions among advanced KOA patients with varying stiffness levels and functional limitations utilizing smartphones. This study provides compelling evidence for the potential of our approach in enabling self-assessment of physical condition in individuals with advanced knee osteoarthritis.

Use of Artificial Intelligence in the Identification and Management of Frailty: A Scoping Review Protocol

INTRODUCTION

Rapid population ageing and associated health issues such as frailty are a growing public health concern. While early identification and management of frailty may limit adverse health outcomes, the complex presentations of frailty pose challenges for clinicians. Artificial intelligence (AI) has emerged as a potential solution to support the early identification and management of frailty. In order to provide a comprehensive overview of current evidence regarding the development and use of AI technologies including machine learning and deep learning for the identification and management of frailty, this protocol outlines a scoping review aiming to identify and present available information in this area. Specifically, this protocol describes a review that will focus on the clinical tools and frameworks used to assess frailty, the outcomes that have been evaluated and the involvement of knowledge users in the development, implementation and evaluation of AI methods and tools for frailty care in clinical settings.

METHODS AND ANALYSIS

This scoping review protocol details a systematic search of eight major academic databases, including Medline, Embase, PsycInfo, Cumulative Index to Nursing and Allied Health Literature (CINAHL), Ageline, Web of Science, Scopus and Institute of Electrical and Electronics Engineers (IEEE) Xplore using the framework developed by Arksey and O'Malley and enhanced by Levac et al and the Joanna Briggs Institute. The search strategy has been designed in consultation with a librarian. Two independent reviewers will screen titles and abstracts, followed by full texts, for eligibility and then chart the data using a piloted data charting form. Results will be collated and presented through a narrative summary, tables and figures.

ETHICS AND DISSEMINATION

Since this study is based on publicly available information, ethics approval is not required. Findings will be communicated with healthcare providers, caregivers, patients and research and health programme funders through peer-reviewed publications, presentations and an infographic.

REGISTRATION DETAILS

OSF Registries (https://doi.org/10.17605/OSF.IO/T54G8).

Machine learning approaches for frailty detection, prediction and classification in elderly people: A systematic review

BACKGROUND

Frailty in older people is a syndrome related to aging that is becoming increasingly common and problematic as the average age of the world population increases. Detecting frailty in its early stages or, even better, predicting its appearance can greatly benefit health in later years of life and save the healthcare system from high costs. Machine Learning models fit the need to develop a tool for supporting medical decision-making in detecting or predicting frailty.

METHODS

In this review, we followed the PRISMA methodology to conduct a systematic search of the most relevant Machine Learning models that have been developed so far in the context of frailty. We selected 41 publications and compared them according to their purpose, the type of dataset used, the target variables, and the results they obtained, highlighting their shortcomings and strengths.

RESULTS

The variety of frailty definitions allows many problems to fall into this field, and it is often challenging to compare results due to the differences in target variables. The data types can be divided into gait data, usually collected with sensors, and medical records, often in the context of aging studies. The most common algorithms are well-known models available from every Machine Learning library. Only one study developed a new framework for frailty classification, and only two considered Explainability.

CONCLUSIONS

This review highlights some gaps in the field of Machine Learning applied to the assessment and prediction of frailty, such as the need for a universal quantitative definition. It emphasizes the need for close collaboration between medical professionals and data scientists to unlock the potential of data collected in hospital and clinical settings. As a suggestion for future work, the area of Explainability, which is crucial for models in medicine and health care, was considered in very few studies.

Predictive Accuracy of Digital Biomarker Technologies for Detection of Mild Cognitive Impairment and Pre-Frailty Amongst Older Adults: A Systematic Review and Meta-Analysis

Digital biomarker technologies coupled with predictive models are increasingly applied for early detection of age-related potentially reversible conditions including mild cognitive impairment (MCI) and pre-frailty (PF). We aimed to determine the predictive accuracy of digital biomarker technologies to detect MCI and PF with systematic review and meta-analysis. A computer-assisted search on major academic research databases including IEEE-Xplore was conducted. Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines were adopted reporting in this study. Summary receiver operating characteristic curve based on random-effect bivariate model was used to evaluate overall sensitivity and specificity for detection of the respective age-related conditions. A total of 43 studies were selected for final systematic review and meta-analysis. 26 studies reported on detection of MCI with sensitivity and specificity of 0.48-1.00 and 0.55-1.00, respectively. On the other hand, there were 17 studies that reported on the detection of PF with reported sensitivity of 0.53-1.00 and specificity of 0.61-1.00. Meta-analysis further revealed pooled sensitivities of 0.84 (95% CI: 0.79-0.88) and 0.82 (95% CI: 0.74-0.88) for in-home detection of MCI and PF, respectively, while pooled specificities were 0.85 (95% CI: 0.80-0.89) and 0.82 (95% CI: 0.75-0.88), respectively. Besides MCI, and PF, in this work during systematic review, we also found one study which reported a sensitivity of 0.93 and a specificity of 0.57 for detection of cognitive frailty (CF). The meta-analytic result, for the first time, quantifies the predictive efficacy of digital biomarker technologies for detection of MCI and PF. Additionally, we found the number of studies for detection of CF to be notably lower, indicating possible research gaps to explore predictive models on digital biomarker technology for detection of CF.