scholarly journals Video-Based Pose Estimation for Gait Analysis in Stroke Survivors during Clinical Assessments: A Proof-of-Concept Study

2022 ◽  
pp. 9-18
Author(s):  
Luca Lonini ◽  
Yaejin Moon ◽  
Kyle Embry ◽  
R. James Cotton ◽  
Kelly McKenzie ◽  
...  
Keyword(s):  
Gait Analysis ◽  
Pose Estimation ◽  
Walking Speed ◽  
Single Camera ◽  
Estimation Model ◽  
Double Support ◽  
Clinical Assessments ◽  
Mean Error ◽  
Double Support Time ◽  
Support Time

Recent advancements in deep learning have produced significant progress in markerless human pose estimation, making it possible to estimate human kinematics from single camera videos without the need for reflective markers and specialized labs equipped with motion capture systems. Such algorithms have the potential to enable the quantification of clinical metrics from videos recorded with a handheld camera. Here we used DeepLabCut, an open-source framework for markerless pose estimation, to fine-tune a deep network to track 5 body keypoints (hip, knee, ankle, heel, and toe) in 82 below-waist videos of 8 patients with stroke performing overground walking during clinical assessments. We trained the pose estimation model by labeling the keypoints in 2 frames per video and then trained a convolutional neural network to estimate 5 clinically relevant gait parameters (cadence, double support time, swing time, stance time, and walking speed) from the trajectory of these keypoints. These results were then compared to those obtained from a clinical system for gait analysis (GAITRite®, CIR Systems). Absolute accuracy (mean error) and precision (standard deviation of error) for swing, stance, and double support time were within 0.04 ± 0.11 s; Pearson’s correlation with the reference system was moderate for swing times (<i>r</i> = 0.4–0.66), but stronger for stance and double support time (<i>r</i> = 0.93–0.95). Cadence mean error was −0.25 steps/min ± 3.9 steps/min (<i>r</i> = 0.97), while walking speed mean error was −0.02 ± 0.11 m/s (<i>r</i> = 0.92). These preliminary results suggest that single camera videos and pose estimation models based on deep networks could be used to quantify clinically relevant gait metrics in individuals poststroke, even while using assistive devices in uncontrolled environments. Such development opens the door to applications for gait analysis both inside and outside of clinical settings, without the need of sophisticated equipment.

scholarly journals THE EFFECTS OF TRAINING ON DIFFERENT SURFACES, ON BALANCE AND GAIT PERFORMANCE IN STROKE HEMIPLEGIA

2021 ◽  
Vol 27 (6) ◽  
pp. 592-596
Author(s):  
Hyun-Seung Rhyu ◽  
Soung-Yob Rhi
Keyword(s):  
Gait Analysis ◽  
Cycle Time ◽  
Dynamic Balance ◽  
Static Balance ◽  
Stroke Patients ◽  
Elderly Male ◽  
Gait Performance ◽  
Double Support ◽  
Double Support Time ◽  
Support Time

ABSTRACT Although many studies have focused on balance exercises for elderly or stroke patients, no comprehensive studies have investigated the use of training on different surfaces (TDS) with analysis of gait performance in elderly male stroke patients. The active properties of balance and subjective reporting of functional gait ability were used to identify the effects of TDS. Static balance (SB), dynamic balance (DB) and gait analysis was measured in 30 elderly stroke patients. The patients were divided into the TDS group (n=15) and a control group (CG, n=15). Fifteen elderly stroke patients underwent TDS five times a week for 12 weeks. The data was analyzed using repeated measures analysis of variance. Significant differences were observed between the two groups (TDS and Control): SB (p < 0.0001), DB (OSI: p < 0.0001, APSI: p < 0.001, MLSI: p < 0.004) and gait analysis (right: temporal step time: p < 0.0001, temporal cycle time: p < 0.001, temporal double support time: p < 0.0001; left: temporal step time: p < 0.0001, temporal cycle time: p < 0.0001, temporal double support time: p < 0.0001). TDS in elderly male stroke patients suggests that the characteristics of gait performance in these patients may be improved by increasing static balance, dynamic balance and gait velocity. It is hoped that the results of this trial will provide new information on the effects of TDS on balance stability and gait ability in stroke patients, through changes in stability of the lower extremities. Level III, Case-control Study.

A Multiple Regression Approach to Normalization of Spatiotemporal Gait Features

2016 ◽  
Vol 32 (2) ◽  
pp. 128-139 ◽  
Author(s):  
Ferdous Wahid ◽  
Rezaul Begg ◽  
Noel Lythgo ◽  
Chris J. Hass ◽  
Saman Halgamuge ◽  
...  
Keyword(s):  
Multiple Regression ◽  
Stride Length ◽  
Walking Speed ◽  
Double Support ◽  
Gait Features ◽  
Regression Approach ◽  
Stance Time ◽  
Double Support Time ◽  
Support Time ◽  
Dimensionless Equations

Normalization of gait data is performed to reduce the effects of intersubject variations due to physical characteristics. This study reports a multiple regression normalization approach for spatiotemporal gait data that takes into account intersubject variations in self-selected walking speed and physical properties including age, height, body mass, and sex. Spatiotemporal gait data including stride length, cadence, stance time, double support time, and stride time were obtained from healthy subjects including 782 children, 71 adults, 29 elderly subjects, and 28 elderly Parkinson’s disease (PD) patients. Data were normalized using standard dimensionless equations, a detrending method, and a multiple regression approach. After normalization using dimensionless equations and the detrending method, weak to moderate correlations between walking speed, physical properties, and spatiotemporal gait features were observed (0.01 < |r| < 0.88), whereas normalization using the multiple regression method reduced these correlations to weak values (|r| < 0.29). Data normalization using dimensionless equations and detrending resulted in significant differences in stride length and double support time of PD patients; however the multiple regression approach revealed significant differences in these features as well as in cadence, stance time, and stride time. The proposed multiple regression normalization may be useful in machine learning, gait classification, and clinical evaluation of pathological gait patterns.

scholarly journals A Comprehensive Analysis of Gait Impairment after Experimental Stroke and the Therapeutic Effect of Environmental Enrichment in Rats

2008 ◽  
Vol 28 (12) ◽  
pp. 1936-1950 ◽  
Author(s):  
Yonggang Wang ◽  
Bruno Bontempi ◽  
Shwehuey M Hong ◽  
Kala Mehta ◽  
Philip R Weinstein ◽  
...  
Keyword(s):  
Gait Analysis ◽  
Environmental Enrichment ◽  
Artery Occlusion ◽  
Experimental Stroke ◽  
Computer Assisted ◽  
Stroke Severity ◽  
Adult Rats ◽  
Double Support ◽  
Double Support Time ◽  
Support Time

Although gait changes are considered as reliable indices of stroke severity and efficacy of rehabilitative therapies in humans, data from animal models of focal ischemia are lacking. To determine the effect of stroke on gait function in adult rats with distal middle cerebral artery occlusion (MCAO), we assessed the longitudinal changes in gait using an automated computer-assisted gait analysis system. Four days after MCAO, intensity, maximal area of contact, and paw angle were significantly decreased in the affected forepaw whereas the double support time using ipsilateral paws increased. Relative print positions between the fore and hindpaws and limb coupling were also altered, suggesting that stroke affected sensorimotor status and reduced limb coordination. Except for paw angle, these impairments persisted for at least 5 weeks. However, unlike human stroke patients, stride length and stance were not affected in rats with MCAO. Environmental enrichment for 4 weeks improved paw contact area and relative print position of the affected limb and reduced double support time in ischemic rats compared with controls. Our results indicate that gait analysis provides great insight into various aspects of motor function changes in ischemic quadrupeds, and that environmental enrichment is beneficial in reducing a variety of poststroke gait impairments possibly through enhanced structural plasticity mechanisms within injured cortical neuronal networks underlying locomotor function.

scholarly journals Split-Belt Treadmill Adaptation Transfers to Overground Walking in Persons Poststroke

2009 ◽  
Vol 23 (7) ◽  
pp. 735-744 ◽  
Author(s):  
Darcy S. Reisman ◽  
Robert Wityk ◽  
Kenneth Silver ◽  
Amy J. Bastian
Keyword(s):  
Step Length ◽  
Overground Walking ◽  
Double Support ◽  
Context Switching ◽  
Before And After ◽  
Partial Transfer ◽  
And Gender ◽  
Double Support Time ◽  
Support Time ◽  
Control Locomotion

Background and Objective. Following stroke, subjects retain the ability to adapt interlimb symmetry on the split-belt treadmill. Critical to advancing our understanding of locomotor adaptation and its usefulness in rehabilitation is discerning whether adaptive effects observed on a treadmill transfer to walking over ground. We examined whether aftereffects following split-belt treadmill adaptation transfer to overground walking in healthy persons and those poststroke. Methods. Eleven poststroke and 11 age-matched and gender-matched healthy subjects walked over ground before and after walking on a split-belt treadmill. Adaptation and aftereffects in step length and double support time were calculated. Results. Both groups demonstrated partial transfer of the aftereffects observed on the treadmill ( P < .001) to overground walking ( P < .05), but the transfer was more robust in the subjects poststroke ( P < .05). The subjects with baseline asymmetry after stroke improved in asymmetry of step length and double limb support ( P = .06). Conclusions. The partial transfer of aftereffects to overground walking suggests that some shared neural circuits that control locomotion for different environmental contexts are adapted during split-belt treadmill walking. The larger adaptation transfer from the treadmill to overground walking in the stroke survivors may be due to difficulty adjusting their walking pattern to changing environmental demands. Such difficulties with context switching have been considered detrimental to function poststroke. However, we propose that the persistence of improved symmetry when changing context to overground walking could be used to advantage in poststroke rehabilitation.

scholarly journals Kinematic and Kinetic Patterns Related to Free-Walking in Parkinson’s Disease

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4224 ◽  
Author(s):  
Martín Martínez ◽  
Federico Villagra ◽  
Juan Castellote ◽  
María Pastor
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Feature Selection ◽  
Clinical Status ◽  
Automatic Classification ◽  
Healthy Controls ◽  
Double Support ◽  
Gait Asymmetry ◽  
Double Support Time ◽  
Support Time

The aim of this study is to compare the properties of free-walking at a natural pace between mild Parkinson’s disease (PD) patients during the ON-clinical status and two control groups. In-shoe pressure-sensitive insoles were used to quantify the temporal and force characteristics of a 5-min free-walking in 11 PD patients, in 16 young healthy controls, and in 12 age-matched healthy controls. Inferential statistics analyses were performed on the kinematic and kinetic parameters to compare groups’ performances, whereas feature selection analyses and automatic classification were used to identify the signature of parkinsonian gait and to assess the performance of group classification, respectively. Compared to healthy subjects, the PD patients’ gait pattern presented significant differences in kinematic parameters associated with bilateral coordination but not in kinetics. Specifically, patients showed an increased variability in double support time, greater gait asymmetry and phase deviation, and also poorer phase coordination. Feature selection analyses based on the ReliefF algorithm on the differential parameters in PD patients revealed an effect of the clinical status, especially true in double support time variability and gait asymmetry. Automatic classification of PD patients, young and senior subjects confirmed that kinematic predictors produced a slightly better classification performance than kinetic predictors. Overall, classification accuracy of groups with a linear discriminant model which included the whole set of features (i.e., demographics and parameters extracted from the sensors) was 64.1%.

Gait differences between K3 and K4 persons with transfemoral amputation across level and non-level walking conditions

2018 ◽  
Vol 42 (6) ◽  
pp. 626-635 ◽  
Author(s):  
James A Sturk ◽  
Edward D Lemaire ◽  
Emily Sinitski ◽  
Nancy L Dudek ◽  
Markus Besemann ◽  
...  
Keyword(s):  
Root Mean Square ◽  
Mean Square ◽  
Transfemoral Amputation ◽  
Lateral Direction ◽  
Double Support ◽  
Margin Of Stability ◽  
Trunk Acceleration ◽  
Standard Deviations ◽  
Double Support Time ◽  
Support Time

Background: A transfemoral amputee’s functional level can be classified from K-level 0 (lowest) to K-level 4 (highest). Knowledge of the biomechanical differences between K3 and K4 transfemoral amputation could help inform clinical professionals and researchers in amputee care and gait assessment. Objectives: Explore gait differences between K3- and K4-level transfemoral amputation across different surface conditions. Study design: Cross-sectional study. Methods: Four K3 and six K4 transfemoral amputation and 10 matched able-bodied individuals walked in a virtual environment with simulated level and non-level surfaces on a self-paced treadmill. Stability measures included medial-lateral margin of stability, step parameters, and gait variability (standard deviations for speed, temporal-spatial parameters, root-mean-square of medial-lateral trunk acceleration). Results: K3 walked slower than K4 with wider steps, greater root-mean-square of medial-lateral trunk acceleration, and greater medial-lateral margin of stability standard deviations, indicating their stability was further challenged. K3 participants had greater asymmetry in double support time and trunk acceleration root-mean-square in the medial-lateral direction, but similar asymmetry overall. K3 participants had larger differences from AB and in more parameters than K4, although K4 differed from AB in trunk acceleration root-mean-square in the medial-lateral direction, walking speed, and double support time standard deviations. Conclusion: The findings improve our understanding of K3 and K4 transfemoral amputation gait on slopes and simulated uneven surfaces. Clinical relevance High performing and community ambulatory transfemoral amputees cannot match the ambulatory abilities of ablebodied individuals. Understanding gait differences between these groups under conditions that challenge balance is required to develop rehabilitation protocols and prosthetic componentry targeted at improving transfemoral amputee gait and overall mobility in their chosen environment.

scholarly journals Gait performance of the elderly under dual-task conditions: Review of instruments employed and kinematic parameters

2016 ◽  
Vol 19 (1) ◽  
pp. 165-182 ◽  
Author(s):  
Gisele de Cássia Gomes ◽  
Luci Fuscaldi Teixeira-Salmela ◽  
Flávia Alexandra Silveira de Freitas ◽  
Maria Luísa Morais Fonseca ◽  
Marina de Barros Pinheiro ◽  
...  
Keyword(s):  
The Elderly ◽  
Elderly Persons ◽  
Step Width ◽  
Kinematic Parameters ◽  
Time Step ◽  
Double Support ◽  
Gait Parameters ◽  
Task Conditions ◽  
Double Support Time ◽  
Support Time

Introduction The physiological deterioration associated with ageing exposes elderly persons to greater risks of falls, especially during the performance of simultaneous tasks during gait. Objectives To evaluate the effects of dual tasks (DT) on spatiotemporal gait parameters and to identify the tools and tasks most commonly used to assess the performance of DT among the elderly. Method Searches of the MEDLINE, PsycINFO, CINAHL, and SciELO databases were conducted. Observational studies, which evaluated gait changes during the performance of DT, published up to April 2014, were selected. Results A total of 385 articles were found, of which 28 were selected. Decreases in speed and increases in stride variability, stride time, step width, and double support time were observed under DT conditions. Motion analysis systems, such as the GAITRite walkway(r) system were the mostly commonly used instruments for the analyses of kinematic parameters (16 studies). DT was most commonly assessed by arithmetic calculations in 20 studies, followed by verbal fluency, in nine studies. The gait parameters most commonly assessed were speed (19 studies), followed by stride variability (14 studies). Conclusion The elderly showed changes in spatiotemporal gait parameters under DT conditions. Gait speed and stride variability were often assessed and, together, were considered good indicators of risks of falls.

The use of double support time for monitoring the gait of muscular dystrophy patients

1987 ◽  
Vol 2 (2) ◽  
pp. 68-70 ◽  
Author(s):  
S. Khodadadeh ◽  
M.R. McClelland ◽  
A.V. Nene ◽  
J.H. Patrick
Keyword(s):  
Muscular Dystrophy ◽  
Double Support ◽  
Double Support Time ◽  
Support Time

Gait adaptations of transfemoral prosthesis users across multiple walking tasks

2015 ◽  
Vol 40 (1) ◽  
pp. 89-95 ◽  
Author(s):  
Cynthia Kendell ◽  
Edward D Lemaire ◽  
Jonathan Kofman ◽  
Nancy Dudek
Keyword(s):  
Plantar Pressure ◽  
Dynamic Instability ◽  
Center Of Pressure ◽  
Loading Frequency ◽  
Double Support ◽  
Prosthetic Limb ◽  
Sensor Cell ◽  
Double Support Time ◽  
Support Time ◽  
Anterior Posterior

Background: For people with lower extremity amputations, the decreased confidence and suboptimal gait associated with dynamic instability can negatively affect mobility and quality of life. Quantifying dynamic instability could enhance clinical decision making related to lower extremity prosthetics and inform future prosthetic research. Objective: To quantitatively examine gait adaptations in transfemoral amputees across various walking conditions. Study design: Cross-sectional study. Methods: Plantar-pressure data were collected from 11 individuals with unilateral transfemoral amputations using an in-shoe plantar-pressure measurement system while navigating rigid and soft ground, ramp, and stair conditions. Six parameters were examined: anterior–posterior and medial–lateral center-of-pressure direction changes, sensor cell loading frequency (cell triggering), maximum lateral force position, double support time, and stride time. Paired t-tests and analyses of variance were used to examine differences between limbs and walking conditions, respectively. Results: Values for medial–lateral center-of-pressure direction change, sensor cell loading frequency, and double support time were significantly greater on the intact limb than the prosthetic limb. Significant differences between conditions occurred only for anterior–posterior center-of-pressure direction change and double support time on the prosthetic limb. Conclusion: Higher values on the intact limb suggest that it plays a key role in maintaining stability and optimizing body progression during different tasks. Differences between participants, limbs, and walking condition indicate parameter sensitivity to adaptive gait strategies. Clinical relevance This plantar-pressure-based approach is a viable option for point-of-care evaluation of locomotor performance, across common various mobility tasks and activities of daily living. The information obtained could be valuable for prosthetic prescription and optimization of prosthetic fit and alignment, potentially improving mobility for prosthetic users with dynamic stability deficits.

scholarly journals Synchronized Sensor Insoles for Clinical Gait Analysis in Home-Monitoring Applications

2018 ◽  
Vol 4 (1) ◽  
pp. 433-437 ◽  
Author(s):  
Nils Roth ◽  
Christine F. Martindale ◽  
Bjoern M. Eskofier ◽  
Heiko Gaßner ◽  
Zacharias Kohl ◽  
...  
Keyword(s):  
Gait Analysis ◽  
Pressure Sensors ◽  
Home Monitoring ◽  
Fully Integrated ◽  
Double Support ◽  
Timing Offset ◽  
System A ◽  
Gait Parameters ◽  
Double Support Time ◽  
Clinical Gait Analysis

AbstractWearable sensor systems are of increasing interest in clinical gait analysis. However, little information about gait dynamics of patients under free living conditions is available, due to the challenges of integrating such systems unobtrusively into a patient’s everyday live. To address this limitation, new, fully integrated low power sensor insoles are proposed, to target applications particularly in home-monitoring scenarios. The insoles combine inertial as well as pressure sensors and feature wireless synchronization to acquire biomechanical data of both feet with a mean timing offset of 15.0 μs. The proposed system was evaluated on 15 patients with mild to severe gait disorders against the GAITRite® system as reference. Gait events based on the insoles’ pressure sensors were manually extracted to calculate temporal gait features such as double support time and double support. Compared to the reference system a mean error of 0.06 s ±0.06 s and 3.89 % ±2.61 % was achieved, respectively. The proposed insoles proved their ability to acquire synchronized gait parameters and address the requirements for home-monitoring scenarios, pushing the boundaries of clinical gait analysis.

Sign in / Sign up

Export Citation Format

Share Document