Using New Camera-Based Technologies for Gait Analysis in Older Adults in Comparison to the Established GAITRite System

Improving human activity classification based on micro-doppler signatures of FMCW radar with the effect of noise

Nowadays, classifying human activities is applied in many essential fields, such as healthcare, security monitoring, and search and rescue missions. Radar sensor-based human activity classification is regarded as a superior approach in comparison to other techniques, such as visual perception-based methodologies and wearable gadgets. However, noise usually exists throughout the process of extracting raw radar signals, decreasing the quality and reliability of the extracted features. This paper presents a novel method for removing white Gaussian noise from raw radar signals using a denoising algorithm before classifying human activities using a deep convolutional neural network (DCNN). Specifically, the denoising algorithm is used as a preprocessing step to remove white Gaussian noise from the input raw radar signal. After that, a lightweight Cross-Residual Convolutional Neural Network (CRCNN) with adaptable cross-residual connections is suggested for classification. The analysis results show that the denoising algorithm with a range-bin interval of 3 and a cut-threshold value of 3 achieves the best denoising effect. When the denoising algorithm was applied to the dataset, CRCNN improved the right classification rate by up to 10% compared to the recognition results achieved with the original noise-added dataset. Additionally, a comparison of the CRCNN with the denoising algorithm solution with six cutting-edge DCNNs was conducted. The experimental results reveal that the proposed model greatly outperforms the others.

Effective evaluation of HGcnMLP method for markerless 3D pose estimation of musculoskeletal diseases patients based on smartphone monocular video

Markerless pose estimation based on computer vision provides a simpler and cheaper alternative to human motion capture, with great potential for clinical diagnosis and remote rehabilitation assessment. Currently, the markerless 3D pose estimation is mainly based on multi-view technology, while the more promising single-view technology has defects such as low accuracy and reliability, which seriously limits clinical application. This study proposes a high-resolution graph convolutional multilayer perception (HGcnMLP) human 3D pose estimation framework for smartphone monocular videos and estimates 15 healthy adults and 12 patients with musculoskeletal disorders (sarcopenia and osteoarthritis) gait spatiotemporal, knee angle, and center-of-mass (COM) velocity parameters, etc., and compared with the VICON gold standard system. The results show that most of the calculated parameters have excellent reliability (VICON, ICC (2, k): 0.853-0.982; Phone, ICC (2, k): 0.839-0.975) and validity (Pearson r: 0.808-0.978, p< 0.05). In addition, the proposed system can better evaluate human gait balance ability, and the K-means++ clustering algorithm can successfully distinguish patients into different recovery level groups. This study verifies the potential of a single smartphone video for 3D human pose estimation for rehabilitation auxiliary diagnosis and balance level recognition, and is an effective attempt at the clinical application of emerging computer vision technology. In the future, it is hoped that the corresponding smartphone program will be developed to provide a low-cost, effective, and simple new tool for remote monitoring and rehabilitation assessment of patients.

The validity of smartphone-based spatiotemporal gait measurements during walking with and without head turns: Comparison with the GAITRite® system

Smartphone accelerometry has potential to provide clinicians with specialized gait analysis not available in most clinical settings. The Gait&Balance Application (G&B App) uses smartphone accelerometry to assess spatiotemporal gait parameters under two conditions: walking looking straight ahead and walking with horizontal head turns. This study investigated the validity of G&B App gait parameters compared with the GAITRite® pressure-sensitive walkway. Healthy young and older adults (age range 21-85 years) attended a single session where a smartphone was secured over the lumbosacral junction. Data were collected concurrently with the app and GAITRite® systems as participants completed the two walking conditions. Spatiotemporal gait parameters for 54 participants were determined from both systems and agreement evaluated with partial Pearson's correlation coefficients and limits of agreement. The results demonstrated moderate to excellent validity for G&B App measures of step time (rp 0.97, 95 % CI [0.96, 0.98]), walking speed (rp 0.83 [0.78, 0.87]), and step length (rp 0.74, [0.66, 0.80]) when walking looking straight ahead, and results were comparable with head turns. The validity of walking speed and step length measures was influenced by sex and height. G&B App measures of step length variability, step time variability, step length asymmetry, and step time asymmetry had poor validity. The G&B App has potential to provide valid measures of unilateral and bilateral step time, unilateral and bilateral step length, and walking speed, under two walking conditions in healthy young and older adults. Further research should validate this tool in clinical conditions and optimise the algorithm for demographic characteristics.

Physical fitness moderates the association between brain network impairment and both motor function and cognition in progressive multiple sclerosis

BACKGROUND

Neurodegeneration leads to continuous accumulation of disability in progressive Multiple Sclerosis (MS). Exercise is considered to counteract disease progression, but little is known on the interaction between fitness, brain networks and disability in MS.

OBJECTIVE

The aim of this study to explore functional and structural brain connectivity and the interaction between fitness and disability based on motor and cognitive functional outcomes in a secondary analysis of a randomised, 3-month, waiting group controlled arm ergometry intervention in progressive MS.

METHODS

We modelled individual structural and functional brain networks based on magnetic resonance imaging (MRI). We used linear mixed effect models to compare changes in brain networks between the groups and explore the association between fitness, brain connectivity and functional outcomes in the entire cohort.

RESULTS

We recruited 34 persons with advanced progressive MS (pwMS, mean age 53 years, females 71%, mean disease duration 17 years and an average walking restriction of < 100 m without aid). Functional connectivity increased in highly connected brain regions of the exercise group (p = 0.017), but no structural changes (p = 0.817) were observed. Motor and cognitive task performance correlated positively with nodal structural connectivity but not nodal functional connectivity. We also found that the correlation between fitness and functional outcomes was stronger with lower connectivity.

CONCLUSIONS

Functional reorganisation seems to be an early indicator of exercise effects on brain networks. Fitness moderates the relationship between network disruption and both motor and cognitive outcomes, with growing importance in more disrupted brain networks. These findings underline the need and opportunities associated with exercise in advanced MS.

"PNP slows down" - linearly-reduced whole body joint velocities and altered gait patterns in polyneuropathy

Introduction

Gait disturbances are a common consequence of polyneuropathy (PNP) and a major factor in patients' reduced quality of life. Less is known about the underlying mechanisms of PNP-related altered motor behavior and its distribution across the body. We aimed to capture whole body movements in PNP during a clinically relevant mobility test, i.e., the Timed Up and Go (TUG). We hypothesize that joint velocity profiles across the entire body would enable a deeper understanding of PNP-related movement alterations. This may yield insights into motor control mechanisms responsible for altered gait in PNP.

Methods

20 PNP patients (61 ± 14 years) and a matched healthy control group (CG, 60 ± 15 years) performed TUG at (i) preferred and (ii) fast movement speed, and (iii) while counting backward (dual-task). We recorded TUG duration (s) and extracted gait-related parameters [step time (s), step length (cm), and width (cm)] during the walking sequences of TUG and calculated center of mass (COM) velocity [represents gait speed (cm/s)] and joint velocities (cm/s) (ankles, knees, hips, shoulders, elbows, wrists) with respect to body coordinates during walking; we then derived mean joint velocities and ratios between groups.

Results

Across all TUG conditions, PNP patients moved significantly slower (TUG time, gait speed) with prolonged step time and shorter steps compared to CG. Velocity profiles depend significantly on group designation, TUG condition, and joint. Correlation analysis revealed that joint velocities and gait speed are closely interrelated in individual subjects, with a 0.87 mean velocity ratio between groups.

Discussion

We confirmed a PNP-related slowed gait pattern. Interestingly, joint velocities in the rest of the body measured in body coordinates were in a linear relationship to each other and to COM velocity in space coordinates, despite PNP. Across the whole body, PNP patients reduce, on average, their joint velocities with a factor of 0.87 compared to CG and thus maintain movement patterns in terms of velocity distributions across joints similarly to healthy individuals. This down-scaling of mean absolute joint velocities may be the main source for the altered motor behavior of PNP patients during gait and is due to the poorer quality of their somatosensory information.

Clinical Trial Registration

https://drks.de/search/de, identifier DRKS00016999.

Depth-Imaging for Gait Analysis on a Treadmill in Older Adults at Risk of Falling

BACKGROUND

Accidental falls are a major health issue in older people. One significant and potentially modifiable risk factor is reduced gait stability. Clinicians do not have sophisticated kinematic options to measure this risk factor with simple and affordable systems. Depth-imaging with AI-pose estimation can be used for gait analysis in young healthy adults. However, is it applicable for measuring gait in older adults at a risk of falling?

METHODS

In this methodological comparison 59 older adults with and without a history of falls walked on a treadmill while their gait pattern was recorded with multiple inertial measurement units and with an Azure Kinect depth-camera. Spatiotemporal gait parameters of both systems were compared for convergent validity and with a Bland-Altman plot.

RESULTS

Correlation between systems for stride length (r=.992, [Formula: see text]) and stride time (r=0.914, [Formula: see text]) was high. Bland-Altman plots revealed a moderate agreement in stride length (-0.74 ± 3.68 cm; [-7.96 cm to 6.47 cm]) and stride time (-3.7±54 ms; [-109 ms to 102 ms]).

CONCLUSION

Gait parameters in older adults with and without a history of falls can be measured with inertial measurement units and Azure Kinect cameras. Affordable and small depth-cameras agree with IMUs for gait analysis in older adults with and without an increased risk of falling. However, tolerable accuracy is limited to the average over multiple steps of spatiotemporal parameters derived from the initial foot contact. Clinical Translation Statement- Gait parameters in older adults with and without a history of falls can be measured with inertial measurement units and Azure Kinect. Affordable and small depth-cameras, developed for various purposes in research and industry, agree with IMUs in clinical gait analysis in older adults with and without an increased risk of falling. However, tolerable accuracy to assess function or monitor changes in gait is limited to the average over multiple steps of spatiotemporal parameters derived from the initial foot contact.

Comparison of spatio-temporal gait parameters between the GAITRite® platinum plus classic and the GAITRite® CIRFACE among older adults: a retrospective observational study

BACKGROUND

The GAITRite® system is one of the gold standards for gait electronic analysis, especially for older adults. Previous GAITRite® systems were composed of an electronic roll-up walkway. Recently, a new GAITRite® electronic walkway, named CIRFACE, was commercialized. It is composed of a changeable association of stiff plates, unlike previous models. Are the gait parameters measured similar between these two walkways among older adults and according to the cognitive status, the history of falls, and the use of walking aids?

METHODS

In this retrospective observational study, 95 older ambulatory participants (mean, 82.6 ± 5.8 years) were included. Ten spatio-temporal gait parameters were measured simultaneously with the two GAITRite® systems in older adults while walking at comfortable self-selected pace. The GAITRite® Platinum Plus Classic (26') was superimposed on the GAITRite® CIRFACE (VI). Comparisons between the parameters of the two walkways were performed using Bravais-Pearson correlation, between-method differences (corresponding to bias), percentage errors and Intraclass Correlation Coefficients (ICC_2,1). Subgroup analyses were performed according to the cognitive status, the history of falls in the last 12 months and the use of walking aids.

RESULTS

The whole walk parameters recorded by the two walkways were extremely correlated with a Bravais-Pearson correlation coefficient ranging from 0.968 to 0.999, P < .001, indicating a very high correlation. According to the ICC_2,1 calculated for absolute agreement, all gait parameters had excellent reliability (ranging from 0.938 to 0.999). Mean bias for 9 parameters out of 10 were ranged from - 0.27 to 0.54, with clinically acceptable percentage errors (1.2-10.1%). Step length showed a substantially higher bias (1.4 ± 1.2 cm), nevertheless the percentage errors remained clinically acceptable (5%).

CONCLUSION

When walking at comfortable self-selected pace, the standard spatio-temporal walk parameters provided by both the GAITRite® PPC and the GAITRite® CIRFACE seem similar and very highly correlated in older adults with various cognitive or motor status. The data of studies using these systems can be compared and mixed with a very low risk of bias in a meta-analytic process. Also, the geriatric care units can choose the most ergonomic system according to their infrastructure without affecting their gait data.

TRIAL REGISTRATION

NCT04557592 (21/09/2020).

Study for the validation of the FeetMe® integrated sensor insole system compared to GAITRite® system to assess gait characteristics in patients with multiple sclerosis

OBJECTIVE

To determine the concordance and statistical precision in gait velocity in people with multiple sclerosis (pwMS), measured with FeetMe® (insoles with pressure and motion sensors) compared with GAITRite® (classic reference system of gait analysis) in the timed 25-Feet Walk test (T25WT).

METHODS

This observational, cross-sectional, prospective, single center study was conducted between September-2018 and April-2019 in pwMS aged 18-55 years, with Expanded Disability Status Scale (EDSS) 0-6.5 and relapse free ≥30 days at baseline. Primary endpoint was gait velocity. Secondary endpoints were ambulation time, cadence, and stride length assessment, while the correlation between gait variables and the clinical parameters of MS subjects was assessed as an exploratory endpoint.

RESULTS

A total of 207 MS subjects were enrolled, of whom, 205 were considered in primary analysis. Most subjects were women (66.8%) and had relapsing-remitting MS (RRMS) (82.9%), with overall mean (standard deviation [SD]) age of 41.5 (8.0) year and EDSS 3.1 (2.0). There was a statistically significant (p<0.0001) and strong agreement (intra-class correlation coefficient (ICC) >0.830) in gait velocity, ambulation time and cadence assessment between FeetMe® and GAITRite®.

CONCLUSIONS

Agreement between devices was strong (ICC≥0.800). FeetMe® is the first validated wearable medical device that allows gait monitoring in MS subjects, being potentially able to assess disease activity, progression, and treatment response.

Methods for Spatiotemporal Analysis of Human Gait Based on Data from Depth Sensors

Gait analysis may serve various purposes related to health care, such as the estimation of elderly people's risk of falling. This paper is devoted to gait analysis based on data from depth sensors which are suitable for use both at healthcare facilities and in monitoring systems dedicated to household environments. This paper is focused on the comparison of three methods for spatiotemporal gait analysis based on data from depth sensors, involving the analysis of the movement trajectories of the knees, feet, and centre of mass. The accuracy of the results obtained using those methods was assessed for different depth sensors' viewing angles and different types of subject clothing. Data were collected using a Kinect v2 device. Five people took part in the experiments. Data from a Zebris FDM platform were used as a reference. The obtained results indicate that the viewing angle and the subject's clothing affect the uncertainty of the estimates of spatiotemporal gait parameters, and that the method based on the trajectories of the feet yields the most information, while the method based on the trajectory of the centre of mass is the most robust.

Concurrent Validity of GAITRite and the 10-m Walk Test to Measure Gait Speed in Adults with Chronic Ankle Instability

Since there are many different assessments related to gait speed, it is important to determine the concurrent validity of each measure so that they can be used interchangeably. Our study aimed to investigate the concurrent validity of gait speed measured by the 10 m walk test (10 MWT) and the gold standard gait analysis system, the GAITRite system, for people with chronic ankle instability (CAI). For 16 people with CAI, 4 evaluations of the 10 MWT and 4 evaluations of the GAITRite system were performed (a comfortable gait speed for 2 evaluations; a maximal gait speed for 2 evaluations). We used intraclass correlations [ICC (2,1), absolute agreement] and Bland−Altman plots to analyze the relationship between the gait speed of the two measures. The absolute agreement between the 10 MWT and the GAITRite system is at the comfortable gait speed [ICC = 0.66; p < 0.001)], and the maximal gait speed [ICC = 0.68; p < 0.001)] showed fair to good agreement. Both gait speeds had a proportional bias; the limit of agreement (LOA) was large (0.50 at the comfortable gait speed and 0.60 at the maximal gait speed). Regression-based Bland−Altman plots were created for the comfortable gait speed (R2 = 0.54, p < 0.001) and the maximal gait speed (R2 = 0.78, p < 0.001). The regression-based LOA ranged from 0.45 to 0.66 m/s for the comfortable gait speed and 1.09 to 1.37 m/s for the maximal gait speed. Our study suggests that it is undesirable to mix the 10 MWT and the GAITRite system gait speed measurements in people with CAI. Each measure should not be recorded by the same evaluation tool and referenced to normative data.

Towards a Low-Cost Solution for Gait Analysis Using Millimeter Wave Sensor and Machine Learning

Human Activity Recognition (HAR) that includes gait analysis may be useful for various rehabilitation and telemonitoring applications. Current gait analysis methods, such as wearables or cameras, have privacy and operational constraints, especially when used with older adults. Millimeter-Wave (MMW) radar is a promising solution for gait applications because of its low-cost, better privacy, and resilience to ambient light and climate conditions. This paper presents a novel human gait analysis method that combines the micro-Doppler spectrogram and skeletal pose estimation using MMW radar for HAR. In our approach, we used the Texas Instruments IWR6843ISK-ODS MMW radar to obtain the micro-Doppler spectrogram and point clouds for 19 human joints. We developed a multilayer Convolutional Neural Network (CNN) to recognize and classify five different gait patterns with an accuracy of 95.7 to 98.8% using MMW radar data. During training of the CNN algorithm, we used the extracted 3D coordinates of 25 joints using the Kinect V2 sensor and compared them with the point clouds data to improve the estimation. Finally, we performed a real-time simulation to observe the point cloud behavior for different activities and validated our system against the ground truth values. The proposed method demonstrates the ability to distinguish between different human activities to obtain clinically relevant gait information.

User Profiling to Enhance Clinical Assessment and Human-Robot Interaction: A Feasibility Study

Socially Assistive Robots (SARs) are designed to support us in our daily life as a companion, and assistance but also to support the caregivers' work. SARs should show personalized and human-like behavior to improve their acceptance and, consequently, their use. Additionally, they should be trustworthy by caregivers and professionals to be used as support for their work (e.g. objective assessment, decision support tools). In this context the aim of the paper is dual. Firstly, this paper aims to present and discuss the robot behavioral model based on sensing, perception, decision support, and interaction modules. The novel idea behind the proposed model is to extract and use the same multimodal features set for two purposes: (i) to profile the user, so to be used by the caregiver as a decision support tool for the assessment and monitoring of the patient; (ii) to fine-tune the human-robot interaction if they can be correlated to the social cues. Secondly, this paper aims to test in a real environment the proposed model using a SAR robot, namely ASTRO. Particularly, it measures the body posture, the gait cycle, and the handgrip strength during the walking support task. Those collected data were analyzed to assess the clinical profile and to fine-tune the physical interaction. Ten older people (65.2 ± 15.6 years) were enrolled for this study and were asked to walk with ASTRO at their normal speed for 10 m. The obtained results underline a good estimation (p < 0.05) of gait parameters, handgrip strength, and angular excursion of the torso with respect to most used instruments. Additionally, the sensory outputs were combined in the perceptual model to profile the user using non-classical and unsupervised techniques for dimensionality reduction namely T-distributed Stochastic Neighbor Embedding (t-SNE) and non-classic multidimensional scaling (nMDS). Indeed, these methods can group the participants according to their residual walking abilities.

The reliability of gait parameters captured via instrumented walkways: a systematic review and meta-analysis

INTRODUCTION

Electronic pressure-sensitive walkways are commonly available solutions to quantitatively assess gait parameters for clinical and research purposes. Many studies have evaluated their measurement properties in different conditions with variable findings. In order to be informed about the current evidence of their reliability for optimal clinical and scientific decision making, this systematic review provided a quantitative synthesis of the test-retest reliability and minimal detectable change of the captured gait parameters across different test conditions (single and cognitive dual-task conditions) and population groups.

EVIDENCE ACQUISITION

A literature search was conducted in PubMed, Embase, and Scopus until November 2021 to identify articles that examined the test-retest reliability properties of the gait parameters captured by pressure-sensitive walkways (gait speed, cadence, stride length and time, double support time, base of support) in adult healthy individuals or patients. The methodological quality was rated using the Consensus-Based Standards for the Selection of Health Measurement Instruments Checklist. Data were meta-analyzed on intraclass correlation coefficient to examine the test-retest relative reliability. Quantitative synthesis was performed for absolute reliability, examined by the weighted average of minimal detectable change values.

EVIDENCE SYNTHESIS

A total of 44 studies were included in this systematic review. The methodological quality was adequate in half of the included studies. The main finding was that pressure-sensitive walkways are reliable tools for objective assessment of spatial and temporal gait parameters both in single-and cognitive dual-task conditions. Despite few exceptions, the review identified intraclass correlation coefficient higher than 0.75 and minimal detectable change lower than 30%, demonstrating satisfactory relative and absolute reliability in all examined populations (healthy adults, elderly, patients with cognitive impairment, spinocerebellar ataxia type 14, Huntington's disease, multiple sclerosis, Parkinson's disease, rheumatoid arthritis, spinal cord injury, stroke or vestibular dysfunction).

CONCLUSIONS

Current evidence suggested that, despite different populations and testing protocols used in the included studies, the test-retest reliability of the examined gait parameters was acceptable under single and cognitive dual-task conditions. Further high-quality studies with powered sample sizes are needed to examine the reliability findings of the currently understudied and unexplored pathologies and test conditions.

Mobile Technology for Falls Prevention in Older Adults

Falls are the leading cause of accidental death in older adults that result from a complex interplay of risk factors. Recently, the need for person-centered approach utilizing personalization, prediction, prevention and participation, known as the P4 model, in fall prevention has been highlighted. Features of mobile technology make it a suitable technological infrastructure to employ such an approach. This narrative review aims to review the evidence for using mobile technology for personalized fall risk assessment and prevention since 2017 in older adults. We aim to identify lessons learned and future directions for using mobile technology as a fall risk assessment and prevention tool. Articles were searched in PubMed and Web of Science with search terms related to older adults, mobile technology, and falls prevention. A total of 23 articles were included. Articles were identified as those examining aspects of the P4 model including prediction (measurement of fall risk), personalization (usability), prevention, and participation. Mobile technology appears to be comparable to gold-standard technology in measuring well-known fall risk factors including static and dynamic balance. Seven applications were developed to measure different fall risk factors and tested for personalization, and/or participation aspects, and four were integrated into a falls prevention program. Mobile health technology offers an innovative solution to provide tailored fall risk screening, prediction, and participation. Future studies should incorporate multiple, objective fall risk measures and implement them in community settings to determine if mobile technology can offer tailored and scalable interventions.

Measurement, Evaluation, and Control of Active Intelligent Gait Training Systems—Analysis of the Current State of the Art

Gait recognition and rehabilitation has been a research hotspot in recent years due to its importance to medical care and elderly care. Active intelligent rehabilitation and assistance systems for lower limbs integrates mechanical design, sensing technology, intelligent control, and robotics technology, and is one of the effective ways to resolve the above problems. In this review, crucial technologies and typical prototypes of active intelligent rehabilitation and assistance systems for gait training are introduced. The limitations, challenges, and future directions in terms of gait measurement and intention recognition, gait rehabilitation evaluation, and gait training control strategies are discussed. To address the core problems of the sensing, evaluation and control technology of the active intelligent gait training systems, the possible future research directions are proposed. Firstly, different sensing methods need to be proposed for the decoding of human movement intention. Secondly, the human walking ability evaluation models will be developed by integrating the clinical knowledge and lower limb movement data. Lastly, the personalized gait training strategy for collaborative control of human–machine systems needs to be implemented in the clinical applications.

Ground Contact Time Estimating Wearable Sensor to Measure Spatio-Temporal Aspects of Gait

Inpatient gait analysis is an essential part of rehabilitation for foot amputees and includes the ground contact time (GCT) difference of both legs as an essential component. Doctors communicate improvement advice to patients regarding their gait pattern based on a few steps taken at the doctor's visit. A wearable sensor system, called Suralis, consisting of an inertial measurement unit (IMU) and a pressure measuring sock, including algorithms calculating GCT, is presented. Two data acquisitions were conducted to implement and validate initial contact (IC) and toe-off (TO) event detection algorithms as the basis for the GCT difference determination for able-bodied and prosthesis wearers. The results of the algorithms show a median GCT error of -51.7 ms (IMU) and 14.7 ms (sensor sock) compared to the ground truth and thus represent a suitable possibility for wearable gait analysis. The wearable system presented, therefore, enables a continuous feedback system for patients and, above all, a remote diagnosis of spatio-temporal aspects of gait behaviour based on reliable data collected in everyday life.

Proposal for Post Hoc Quality Control in Instrumented Motion Analysis Using Markerless Motion Capture: Development and Usability Study

Background

Instrumented assessment of motor symptoms has emerged as a promising extension to the clinical assessment of several movement disorders. The use of mobile and inexpensive technologies such as some markerless motion capture technologies is especially promising for large-scale application but has not transitioned into clinical routine to date. A crucial step on this path is to implement standardized, clinically applicable tools that identify and control for quality concerns.

Objective

The main goal of this study comprises the development of a systematic quality control (QC) procedure for data collected with markerless motion capture technology and its experimental implementation to identify specific quality concerns and thereby rate the usability of recordings.

Methods

We developed a post hoc QC pipeline that was evaluated using a large set of short motor task recordings of healthy controls (2010 recordings from 162 subjects) and people with multiple sclerosis (2682 recordings from 187 subjects). For each of these recordings, 2 raters independently applied the pipeline. They provided overall usability decisions and identified technical and performance-related quality concerns, which yielded respective proportions of their occurrence as a main result.

Results

The approach developed here has proven user-friendly and applicable on a large scale. Raters’ decisions on recording usability were concordant in 71.5%-92.3% of cases, depending on the motor task. Furthermore, 39.6%-85.1% of recordings were concordantly rated as being of satisfactory quality whereas in 5.0%-26.3%, both raters agreed to discard the recording.

Conclusions

We present a QC pipeline that seems feasible and useful for instant quality screening in the clinical setting. Results confirm the need of QC despite using standard test setups, testing protocols, and operator training for the employed system and by extension, for other task-based motor assessment technologies. Results of the QC process can be used to clean existing data sets, optimize quality assurance measures, as well as foster the development of automated QC approaches and therefore improve the overall reliability of kinematic data sets.

Development of an Area Scan Step Length Measuring System Using a Polynomial Estimate of the Heel Cloud Point

Due to impaired mobility caused by aging, it is very important to employ early detection and monitoring of gait parameters to prevent the inevitable huge amount of medical cost at a later age. For gait training and potential tele-monitoring application outside clinical settings, low-cost yet highly reliable gait analysis systems are needed. This research proposes using a single LiDAR system to perform automatic gait analysis with polynomial fitting. The experimental setup for this study consists of two different walking speeds, fast walk and normal walk, along a 5-m straight line. There were ten test subjects (mean age 28, SD 5.2) who voluntarily participated in the study. We performed polynomial fitting to estimate the step length from the heel projection cloud point laser data as the subject walks forwards and compared the values with the visual inspection method. The results showed that the visual inspection method is accurate up to 6 cm while the polynomial method achieves 8 cm in the worst case (fast walking). With the accuracy difference estimated to be at most 2 cm, the polynomial method provides reliability of heel location estimation as compared with the observational gait analysis. The proposed method in this study presents an improvement accuracy of 4% as opposed to the proposed dual-laser range sensor method that reported 57.87 cm ± 10.48, an error of 10%. Meanwhile, our proposed method reported ±0.0633 m, a 6% error for normal walking.

Applications and limitations of current markerless motion capture methods for clinical gait biomechanics

BACKGROUND

Markerless motion capture has the potential to perform movement analysis with reduced data collection and processing time compared to marker-based methods. This technology is now starting to be applied for clinical and rehabilitation applications and therefore it is crucial that users of these systems understand both their potential and limitations. This literature review aims to provide a comprehensive overview of the current state of markerless motion capture for both single camera and multi-camera systems. Additionally, this review explores how practical applications of markerless technology are being used in clinical and rehabilitation settings, and examines the future challenges and directions markerless research must explore to facilitate full integration of this technology within clinical biomechanics.

METHODOLOGY

A scoping review is needed to examine this emerging broad body of literature and determine where gaps in knowledge exist, this is key to developing motion capture methods that are cost effective and practically relevant to clinicians, coaches and researchers around the world. Literature searches were performed to examine studies that report accuracy of markerless motion capture methods, explore current practical applications of markerless motion capture methods in clinical biomechanics and identify gaps in our knowledge that are relevant to future developments in this area.

RESULTS

Markerless methods increase motion capture data versatility, enabling datasets to be re-analyzed using updated pose estimation algorithms and may even provide clinicians with the capability to collect data while patients are wearing normal clothing. While markerless temporospatial measures generally appear to be equivalent to marker-based motion capture, joint center locations and joint angles are not yet sufficiently accurate for clinical applications. Pose estimation algorithms are approaching similar error rates of marker-based motion capture, however, without comparison to a gold standard, such as bi-planar videoradiography, the true accuracy of markerless systems remains unknown.

CONCLUSIONS

Current open-source pose estimation algorithms were never designed for biomechanical applications, therefore, datasets on which they have been trained are inconsistently and inaccurately labelled. Improvements to labelling of open-source training data, as well as assessment of markerless accuracy against gold standard methods will be vital next steps in the development of this technology.

Experimental Verification of Micro-Doppler Radar Measurements of Fall-Risk-Related Gait Differences for Community-Dwelling Elderly Adults

In a previous study, we developed a classification model to detect fall risk for elderly adults with a history of falls (fallers) using micro-Doppler radar (MDR) gait measurements via simulation. The objective was to create daily monitoring systems that can identify elderly people with a high risk of falls. This study aimed to verify the effectiveness of our model by collecting actual MDR data from community-dwelling elderly people. First, MDR gait measurements were performed in a community setting, and the efficient gait parameters for the classification of fallers were extracted. Then, a support vector machine model that was trained and validated using the simulated MDR data was tested for the gait parameters extracted from the actual MDR data. A classification accuracy of 78.8% was achieved for the actual MDR data. The validity of the experimental results was confirmed based on a comparison with the results of our previous simulation study. Thus, the practicality of the faller classification model constructed using the simulated MDR data was verified for the actual MDR data.

Diagnostic value of a vision-based intelligent gait analyzer in screening for gait abnormalities

BACKGROUND

Early detection of gait abnormalities is critical for preventing severe injuries in future falls. The timed up and go (TUG) test is a commonly used clinical gait screening test; however, the interpretation of its results is limited to the TUG total time.

RESEARCH QUESTION

What is diagnostic accuracy of the low-cost, markerless, automated gait analyzer, with the aid of vision-based artificial intelligence technology, which extract gait spatiotemporal features and screen for abnormal walking patterns through video recordings of the TUG test?

METHODS

Our dataset contained retrospective data from outpatients from the Department of Neurology or Rehabilitation of two tertiary hospitals in Shanghai. A panel of three expert neurologists specialized in movement disorders reviewed the gait performance in each TUG video, and labeled them separately, with the most commonly assigned label being used as the reference standard. The gait analyzer performed the AlphaPose algorithm to track the human joint position and calculated the spatiotemporal parameters by filtering and double-threshold signal detection. Gait spatiotemporal features and expert labels were input into machine learning models, and the accuracy of each model was tested with leave-one-out cross-validation (LOOCV).

RESULTS

A total of 284 participants were recruited. Among these, 100 were labeled as having abnormal gait performance by experts. The Naive Bayes classifier achieved the best performance with a full-data accuracy of 90.14% and a LOOCV accuracy of 89.08% for screening abnormal gait performance.

SIGNIFICANCE

This study is the first to investigate the accuracy of a vision-based intelligent gait analyzer for screening abnormal clinical gait performance. By virtue of a pose estimation algorithm and machine learning models, our intelligent gait analyzer can detect abnormal walking patterns approximate to judgements made by experienced neurologists, which is expected to be a supplementary gait assessment protocol for basic-level doctors in the future.

A Spatiotemporal Deep Learning Approach for Automatic Pathological Gait Classification

Human motion analysis provides useful information for the diagnosis and recovery assessment of people suffering from pathologies, such as those affecting the way of walking, i.e., gait. With recent developments in deep learning, state-of-the-art performance can now be achieved using a single 2D-RGB-camera-based gait analysis system, offering an objective assessment of gait-related pathologies. Such systems provide a valuable complement/alternative to the current standard practice of subjective assessment. Most 2D-RGB-camera-based gait analysis approaches rely on compact gait representations, such as the gait energy image, which summarize the characteristics of a walking sequence into one single image. However, such compact representations do not fully capture the temporal information and dependencies between successive gait movements. This limitation is addressed by proposing a spatiotemporal deep learning approach that uses a selection of key frames to represent a gait cycle. Convolutional and recurrent deep neural networks were combined, processing each gait cycle as a collection of silhouette key frames, allowing the system to learn temporal patterns among the spatial features extracted at individual time instants. Trained with gait sequences from the GAIT-IT dataset, the proposed system is able to improve gait pathology classification accuracy, outperforming state-of-the-art solutions and achieving improved generalization on cross-dataset tests.

Camera-based objective measures of Parkinson's disease gait features

OBJECTIVE

Parkinson's disease is a common, age-related, neurodegenerative disease, affecting gait and other motor functions. Technological developments in consumer imaging are starting to provide high-quality, affordable tools for home-based diagnosis and monitoring. This pilot study aims to investigate whether a consumer depth camera can capture changes in gait features of Parkinson's patients. The dataset consisted of 19 patients (tested in both a practically defined OFF phase and ON phase) and 8 controls, who performed the "Timed-Up-and-Go" test multiple times while being recorded with the Microsoft Kinect V2 sensor. Camera-derived features were step length, average walking speed and mediolateral sway. Motor signs were assessed clinically using the Movement Disorder Society Unified Parkinson's Disease Rating Scale.

RESULTS

We found significant group differences between patients and controls for step length and average walking speed, showing the ability to detect Parkinson's features. However, there were no differences between the ON and OFF medication state, so further developments are needed to allow for detection of small intra-individual changes in symptom severity.

Algorithm based on one monocular video delivers highly valid and reliable gait parameters

Despite its paramount importance for manifold use cases (e.g., in the health care industry, sports, rehabilitation and fitness assessment), sufficiently valid and reliable gait parameter measurement is still limited to high-tech gait laboratories mostly. Here, we demonstrate the excellent validity and test–retest repeatability of a novel gait assessment system which is built upon modern convolutional neural networks to extract three-dimensional skeleton joints from monocular frontal-view videos of walking humans. The validity study is based on a comparison to the GAITRite pressure-sensitive walkway system. All measured gait parameters (gait speed, cadence, step length and step time) showed excellent concurrent validity for multiple walk trials at normal and fast gait speeds. The test–retest-repeatability is on the same level as the GAITRite system. In conclusion, we are convinced that our results can pave the way for cost, space and operationally effective gait analysis in broad mainstream applications. Most sensor-based systems are costly, must be operated by extensively trained personnel (e.g., motion capture systems) or—even if not quite as costly—still possess considerable complexity (e.g., wearable sensors). In contrast, a video sufficient for the assessment method presented here can be obtained by anyone, without much training, via a smartphone camera.

Skeleton Tracking Accuracy and Precision Evaluation of Kinect V1, Kinect V2, and the Azure Kinect

The Azure Kinect, the successor of Kinect v1 and Kinect v2, is a depth sensor. In this paper we evaluate the skeleton tracking abilities of the new sensor, namely accuracy and precision (repeatability). Firstly, we state the technical features of all three sensors, since we want to put the new Azure Kinect in the context of its previous versions. Then, we present the experimental results of general accuracy and precision obtained by measuring a plate mounted to a robotic manipulator end effector which was moved along the depth axis of each sensor and compare them. In the second experiment, we mounted a human-sized figurine to the end effector and placed it in the same positions as the test plate. Positions were located 400 mm from each other. In each position, we measured relative accuracy and precision (repeatability) of the detected figurine body joints. We compared the results and concluded that the Azure Kinect surpasses its discontinued predecessors, both in accuracy and precision. It is a suitable sensor for human–robot interaction, body-motion analysis, and other gesture-based applications. Our analysis serves as a pilot study for future HMI (human–machine interaction) designs and applications using the new Kinect Azure and puts it in the context of its successful predecessors.

Kinect V2-Based Gait Analysis for Children with Cerebral Palsy: Validity and Reliability of Spatial Margin of Stability and Spatiotemporal Variables

Children with cerebral palsy (CP) have high risks of falling. It is necessary to evaluate gait stability for children with CP. In comparison to traditional motion capture techniques, the Kinect has the potential to be utilised as a cost-effective gait stability assessment tool, ensuring frequent and uninterrupted gait monitoring. To evaluate the validity and reliability of this measurement, in this study, ten children with CP performed two testing sessions, of which gait data were recorded by a Kinect V2 sensor and a referential Motion Analysis system. The margin of stability (MOS) and gait spatiotemporal metrics were examined. For the spatiotemporal parameters, intraclass correlation coefficient (ICC_2,k) values were from 0.83 to 0.99 between two devices and from 0.78 to 0.88 between two testing sessions. For the MOS outcomes, ICC_2,k values ranged from 0.42 to 0.99 between two devices and 0.28 to 0.69 between two test sessions. The Kinect V2 was able to provide valid and reliable spatiotemporal gait parameters, and it could also offer accurate outcome measures for the minimum MOS. The reliability of the Kinect V2 when assessing time-specific MOS variables was limited. The Kinect V2 shows the potential to be used as a cost-effective tool for CP gait stability assessment.

Automatic Ankle Angle Detection by Integrated RGB and Depth Camera System

Depth cameras are developing widely. One of their main virtues is that, based on their data and by applying machine learning algorithms and techniques, it is possible to perform body tracking and make an accurate three-dimensional representation of body movement. Specifically, this paper will use the Kinect v2 device, which incorporates a random forest algorithm for 25 joints detection in the human body. However, although Kinect v2 is a powerful tool, there are circumstances in which the device's design does not allow the extraction of such data or the accuracy of the data is low, as is usually the case with foot position. We propose a method of acquiring this data in circumstances where the Kinect v2 device does not recognize the body when only the lower limbs are visible, improving the ankle angle's precision employing projection lines. Using a region-based convolutional neural network (Mask RCNN) for body recognition, raw data extraction for automatic ankle angle measurement has been achieved. All angles have been evaluated by inertial measurement units (IMUs) as gold standard. For the six tests carried out at different fixed distances between 0.5 and 4 m to the Kinect, we have obtained (mean ± SD) a Pearson's coefficient, r = 0.89 ± 0.04, a Spearman's coefficient, ρ = 0.83 ± 0.09, a root mean square error, RMSE = 10.7 ± 2.6 deg and a mean absolute error, MAE = 7.5 ± 1.8 deg. For the walking test, or variable distance test, we have obtained a Pearson's coefficient, r = 0.74, a Spearman's coefficient, ρ = 0.72, an RMSE = 6.4 deg and an MAE = 4.7 deg.

Auditory Cue Based on the Golden Ratio Can Improve Gait Patterns in People with Parkinson's Disease

The harmonic structure of walking relies on an irrational number called the golden ratio (ϕ): in healthy subjects, it coincides with the stride-to-stance ratio, and it is associated with a smooth gait modality. This smoothness is lost in people with Parkinson’s disease (PD), due to deficiencies in the execution of movements. However, external auditory cues seem to facilitate movement, by enabling the timing of muscle activation, and helping in initiating and modulating motor output. Based on a harmonic fractal structure of gait, can the administration of an auditory cue based on individual’s ϕ-rhythm improve, in acute, gait patterns in people with PD? A total of 20 participants (16 males, age 70.9 ± 8.4 years, Hoehn and Yahr stage-II) were assessed through stereophotogrammetry: gait spatio-temporal parameters, and stride-to-stance ratio were computed before, during, and after the ϕ-rhythm administration. Results show improvements in terms of stride length (p = 0.018), walking speed (p = 0.014), and toe clearance (p = 0.013) when comparing gait patterns before and after the stimulus. Furthermore, the stride-to-stance ratio seems to correlate with almost all spatio-temporal parameters, but it shows the main changes in the before–during rhythm comparison. In conclusion, ϕ-rhythm seems an effective cue able to compensate for defective internal rhythm of the basal ganglia in PD.

Evaluation of the Azure Kinect and Its Comparison to Kinect V1 and Kinect V2

The Azure Kinect is the successor of Kinect v1 and Kinect v2. In this paper we perform brief data analysis and comparison of all Kinect versions with focus on precision (repeatability) and various aspects of noise of these three sensors. Then we thoroughly evaluate the new Azure Kinect; namely its warm-up time, precision (and sources of its variability), accuracy (thoroughly, using a robotic arm), reflectivity (using 18 different materials), and the multipath and flying pixel phenomenon. Furthermore, we validate its performance in both indoor and outdoor environments, including direct and indirect sun conditions. We conclude with a discussion on its improvements in the context of the evolution of the Kinect sensor. It was shown that it is crucial to choose well designed experiments to measure accuracy, since the RGB and depth camera are not aligned. Our measurements confirm the officially stated values, namely standard deviation ≤17 mm, and distance error <11 mm in up to 3.5 meters distance from the sensor in all four supported modes. The device, however, has to be warmed up for at least 40-50 min to give stable results. Due to the time-of-flight technology, the Azure Kinect cannot be reliably used in direct sunlight. Therefore, it is convenient mostly for indoor applications.

Instrumental Assessment of Stepping in Place Captures Clinically Relevant Motor Symptoms of Parkinson's Disease

Fluctuations of motor symptoms make clinical assessment in Parkinson's disease a complex task. New technologies aim to quantify motor symptoms, and their remote application holds potential for a closer monitoring of treatment effects. The focus of this study was to explore the potential of a stepping in place task using RGB-Depth (RGBD) camera technology to assess motor symptoms of people with Parkinson's disease. In total, 25 persons performed a 40 s stepping in place task in front of a single RGBD camera (Kinect for Xbox One) in up to two different therapeutic states. Eight kinematic parameters were derived from knee movements to describe features of hypokinesia, asymmetry, and arrhythmicity of stepping. To explore their potential clinical utility, these parameters were analyzed for their Spearman's Rho rank correlation to clinical ratings, and for intraindividual changes between treatment conditions using standard response mean and paired t-test. Test performance not only differed between ON and OFF treatment conditions, but showed moderate correlations to clinical ratings, specifically ratings of postural instability (pull test). Furthermore, the test elicited freezing in some subjects. Results suggest that this single standardized motor task is a promising candidate to assess an array of relevant motor symptoms of Parkinson's disease. The simple technical test setup would allow future use by patients themselves.

Development of a Kinect-Based English Learning System Based on Integrating the ARCS Model with Situated Learning

This study developed a Kinect-based somatosensory English learning system. The main design concept was to integrate Kinect as an interaction technique with theories of situated learning and the attention, relevance, confidence, and satisfaction (ARCS) model, to design relevant learning activities and materials, thereby enhancing students’ learning outcomes. The proposed system allows for planning and designing learning activities and content according to situated learning components and the ARCS model. The somatosensory interaction system Kinect was used to provide users with a virtual learning environment to achieve actual spatial and physical experiences, assisting learners’ engagement in stories and scenarios as well as enhancing their motivation to learn. English vocabulary related to supermarkets was set as the learning objective and 70 students ranging from third to sixth grade at a learning center in Tainan, Taiwan were selected as participants. During the experiment, participants were divided into two groups: the experimental group, which employed the proposed learning system, and the control group, in which students learned using printed materials coupled with mobile devices. Pre- and posttest scores of the two groups were used to assess learning outcomes and analyze the ARCS model-based questionnaire. The results revealed that the proposed system effectively improved learners’ motivation to learn and learning outcomes.