BlazePose-Seq2Seq: Leveraging Regular RGB Cameras for Robust Gait Assessment.

Evaluation of human gait through smartphone-based pose estimation algorithms provides an attractive alternative to costly lab-bound instrumented assessment and offers a paradigm shift with real time gait capture for clinical assessment. Systems based on smart phones, such as OpenPose and BlazePose have demonstrated potential for virtual motion assessment but still lack the accuracy and repeatability standards required for clinical viability. Seq2seq architecture offers an alternative solution to conventional deep learning techniques for predicting joint kinematics during gait. This study introduces a novel enhancement to the low-powered BlazePose algorithm by incorporating a Seq2seq autoencoder deep learning model. To ensure data accuracy and reliability, synchronized motion capture involving an RGB camera and ten Vicon cameras were employed across three distinct self-selected walking speeds. This investigation presents a groundbreaking avenue for remote gait assessment, harnessing the potential of Seq2seq architectures inspired by natural language processing (NLP) to enhance pose estimation accuracy. When comparing BlazePose alone to the combination of BlazePose and 1D convolution Long Short-term Memory Network (1D-LSTM), Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), the average mean absolute errors decreased from 13.4° to 5.3° for fast gait, from 16.3° to 7.5° for normal gait, and from 15.5° to 7.5° for slow gait at the left ankle joint angle respectively. The strategic utilization of synchronized data and rigorous testing methodologies further bolsters the robustness and credibility of these findings.

Can the F-Scan in-shoe pressure system be combined with the GAITRite® temporal and spatial parameter-recording walkway as a cost-effective alternative in clinical gait analysis? A validation study.

BACKGROUND: Clinical gait analysis is widely used to aid the assessment and diagnosis of symptomatic pathologies. Foot function pressure systems such as F-scan and analysis of the spatial-temporal parameters of gait using GAITRite® can provide clinicians with a more comprehensive assessment. There are systems however, such as Strideway™ that can measure these parameters simultaneously but can be expensive. F-Scan in-shoe pressure data is normally collected whilst the person is walking on a hard floor surface. The effects of the softer Gaitrite® mat upon the F-Scan in-shoe sensor pressure data is unknown. This study therefore aimed to assess the agreement between F-Scan pressure measurements taken from a standard walkway (normal hard floor), and those from a GAITRite® walkway to establish whether these two pieces of equipment (in-shoe F-Scan and GAITRite®) can be used simultaneously, as a cost-effective alternative. METHOD: Twenty-three participants first walked on a standard floor and then on a GAITRite® walkway wearing F-Scan pressure sensor insoles with same footwear. They repeated these walks three times on each surface. Mid gait protocols were utilised by analysing the contact pressure of the first and second metatarsophalangeal joint of the third, fifth and seventh step from each walk. For both joints, 95% Bland-Altman Limits of Agreement was used to determine a level of agreement between the two surfaces, using mean values from pressure data collected from participants who successfully completed all required walks. The intraclass correlation coefficient (ICC) and Lin's concordance correlation coefficient were calculated as indices of reliability. FINDINGS: ICC results for the hard surface and the GAITRrite® walkway at the first and second metatarsophalangeal joints were 0.806 and 0.991 respectively. Lin's concordance correlation coefficient for the first and second metatarsophalangeal joints were calculated to be 0.899 and 0.956 respectively. Both sets of statistics indicate very good reproducibility. Bland-Altman plots revealed good repeatability of data at both joints. CONCLUSION: The level of agreement in F-Scan plantar pressures observed between walking on a normal hard floor and on a GAITRite® walkway was very high, suggesting that it is feasible to use F-Scan with GAITRite® together in a clinical setting, as an alternative to other less cost-effective standalone systems. Although it is assumed combining F-Scan with GAITRite® does not affect spatiotemporal analysis, this was not validated in this study.

Investigating Temporal Kinematic Differences Caused by Unexpected Stimulation during Gait Termination through the Waveform-Level Variance Equality Test.

The efficacy of the variance equality test in steady-state gait analysis is well documented; however, temporal information on where differences in variability occur during gait subtasks, especially during gait termination caused by unexpected stimulation, is poorly understood. Therefore, the purpose of the current study was to further verify the efficacy of the waveform-level variance equality test in gait subtasks by comparing temporal kinematical variability between planned gait termination (PGT) and unplanned gait termination (UGT) caused by unexpected stimulation. Thirty-two asymptomatic male subjects were recruited to participate in the study. A Vicon motion capture system was utilized to measure lower extremity kinematics during gait termination tasks with and without unexpected stimulation conditions. The F-statistic for each interval of the temporal kinematic waveform was compared to the critical value using a variance equality test to identify significant differences in the waveform. Comparative tests between two types of gait terminations found that subjects may exhibit greater kinematics variance in most lower limb joints during UGT caused by unexpected stimulation (especially at stimulus delay and reaction phases). Significant greater variances during PGT were exhibited only in the MPJ sagittal and frontal planes at the early stimulus delay phase (4-15% and 1-15%). This recorded dataset of temporal kinematic changes caused by unexpected stimuli during gait termination is essential for interpreting lower limb biomechanical function and injury prediction in relation to UGT. Given the complexity of the gait termination task, which involves both internal and external variability, the variance equality test can be used as a valuable method to compare temporal differences in the variability of biomechanical variables.

A Low-Cost, Autonomous Gait Detection and Estimation System for Analyzing Gait Impairments in Mice.

With the advancement in imaging technology, many commercial systems have been developed for performing motion analysis in mice. However, available commercial systems are expensive and use proprietary software. In this paper, we describe a low-cost, camera-based design of an autonomous gait acquisition and analysis system for inspecting gait deficits in C57BL/6 mice. Our system includes video acquisition, autonomous gait-event detection, gait-parameter extraction, and result visualization. We provide a simple, user-friendly, step-by-step detailed methodology to apply well-known image processing techniques for detecting mice footfalls and calculating various gait parameters for analyzing gait abnormalities in healthy and neurotraumatic mice. The system was used in a live animal study for assessing recovery in a mouse model of Parkinson's disease. Using the videos acquired in the study, we validate the performance of our system with receiver operating characteristic (ROC) and Hit : Miss : False (H : M : F) detection analyses. Our system correctly detected the mice footfalls with an average H : M : F score of 92.1 : 2.3 : 5.6. The values for the area under an ROC curve for all the ROC plots are above 0.95, which indicates an almost perfect detection model. The ROC and H : M : F analyses show that our system produces accurate gait detection. The results observed from the gait assessment study are in agreement with the known literature. This demonstrates the practical viability of our system as a gait analysis tool.

Computer-aided identification of degenerative neuromuscular diseases based on gait dynamics and ensemble decision tree classifiers.

This study proposes a reliable computer-aided framework to identify gait fluctuations associated with a wide range of degenerative neuromuscular disease (DNDs) and health conditions. Investigated DNDs included amyotrophic lateral sclerosis (ALS), Parkinson's disease (PD), and Huntington's disease (HD). We further performed a statistical and classification comparison elucidating the discriminative capability of different gait signals, including vertical ground reaction force (VGRF), stride duration, stance duration, and swing duration. Feature representation of these gait signals was based on statistical amplitude quantification using the root mean square (RMS), variance, kurtosis, and skewness metrics. We investigated various decision tree (DT) based ensemble methods such as bagging, adaptive boosting (AdaBoost), random under-sampling boosting (RUSBoost), and random subspace to tackle the challenge of multi-class classification. Experimental results showed that AdaBoost ensembling provided a 6.49%, 0.78%, 2.31%, and 2.72% prediction rate improvement for the VGRF, stride, stance, and swing signals, respectively. The proposed approach achieved the highest classification accuracy of 99.17%, sensitivity of 98.23%, and specificity of 99.43%, using the VGRF-based features and the adaptive boosting classification model. This work demonstrates the effective capability of using simple gait fluctuation analysis and machine learning approaches to detect DNDs. Computer-aided analysis of gait fluctuations provides a promising advent to enhance clinical diagnosis of DNDs.

Rater agreement for assessment of equine back mobility at walk and trot compared to quantitative gait analysis.

BACKGROUND: Lameness assessment in horses is still predominantly performed using subjective methods. Visual assessment is known to have moderate to good intra-rater agreement but relatively poor inter-rater agreement. Little is known about inter- and intra-rater agreement on the evaluation of back motion, for which no objective measurement technique in a clinical setting is available thus far. OBJECTIVES: To describe inter- and intra-rater agreement of visual evaluation of equine back mobility. STUDY DESIGN: Rater reliability study using a fully crossed design in which all horses are rated by all observers. This data is compared with objective gait analysis. METHODS: Seventy equine professionals (veterinarians and physiotherapists) and veterinary students evaluated videos of 12 healthy horses at walk and trot on a hard, straight line. Nine parameters related to back mobility were scored: general mobility, thoracic, lumbar, lumbosacral flexion and extension and left and right thoracolumbar latero-flexion. All parameters were compared with simultaneously measured quantitative motion parameters. After 1 month, six randomly chosen horses were re-evaluated by 57 observers. RESULTS: For each parameter inter- and intra-rater agreements were calculated using intra-class correlation coefficients. For all parameters, inter-rater agreement was very poor (<0.2). The mean intra-rater agreement of all observers and for all parameters was poor (~0.4) but varied between 0.0 and 0.96 for individual observers. There was no correlation between the visual subjective scoring and objective gait analysis measurements. MAIN LIMITATIONS: Horses were scored from videos and by lack of any existing (semi-) quantitative system, a custom-made system had to be used. CONCLUSIONS: The poor inter- and intra-rater agreements of visual scoring of mobility of the equine back and the disagreement between subjective and objective gait analysis data, demonstrate the need for the development and introduction of objective, quantitative and repeatable techniques to assess equine back motion.

Agreement and consistency of five different clinical gait analysis systems in the assessment of spatiotemporal gait parameters.

BACKGROUND: Measuring gait function has become an essential tool in the assessment of mobility in aging populations for both, clinicians and researchers. A variety of systems exist that assess gait parameters such as gait cycle time, gait speed or duration of relative gait phases. Due to different measurement principles such as inertial or pressure sensors, accurate detection of spatiotemporal events may vary between systems. RESEARCH QUESTION: To compare the absolute agreement and consistency in spatiotemporal gait parameters among five different clinical gait analysis systems using different sensor technologies. METHODS: We compared two devices using inertial sensors (GaitUp & Mobility Lab), two devices using pressure sensor systems (GAITRite & Zebris) as well as one optical system (OptoGait). Twelve older adults walked at self-selected speed through a walkway integrating all of the above systems. Basic spatiotemporal parameters (gait cycle time, cadence, gait speed and stride length) as well as measures of relative phase (stance phase, swing phase, double stance phase, single limb support) were extracted from all systems. We used Intraclass Correlation Coefficients as measures of agreement and consistency. RESULTS: High agreement and consistency between all systems was found for basic spatiotemporal parameters, whereas parameters of relative phase showed poorer agreement and consistency. Overground measurement (GAITRite & OptoGait) showed generally higher agreement with each other as compared to inertial sensor-based systems. SIGNIFICANCE: Our results indicate that accurate detection of both, the heel-strike and toe-off event are crucial for reliable results. Systematic errors in the detection of one or both events may only have a small impact on basic spatiotemporal outcomes as errors remain consistent from step to step. Relative phase parameters on the other hand may be affected to a much larger extent as these differences lead to a systematic increase or reduction of relative phase durations.

3D gait analysis, haemophilia joint health score, leg muscle laterality and biomarkers of joint damage: A cross-sectional comparative assessment of haemophilic arthropathy.

INTRODUCTION: 3D gait analysis has been proposed as a reproducible and valid method to assess abnormal gait patterns and to monitor disease progression in patients with haemophilia (PWH). AIM: This study aimed at comparing Gait Deviation Index (GDI) between adult PWH and healthy controls, and at assessing the agreement between outcome measures of haemophilic arthropathy. METHODS: Male PWH aged 18-49 years (prespecified subgroups: 18-25 vs 26-49 years) on prophylactic replacement therapy, and male healthy age-matched controls passed through a cross-sectional assessment panel. Besides the 3D gait analysis derived GDI, secondary outcomes included kinematic, kinetic and spatio-temporal gait parameters, the Haemophilia Joint Health Score (HJHS), electric impedance derived leg muscle laterality and inflammatory biomarkers. RESULTS: Patients with haemophilia (n = 18) walked slower, in shorter steps and accordingly with less functional range of motion in the hips and ankles, as compared to healthy controls (n = 24). Overall, PWH did not differ significantly in GDI and specific gait parameters. PWH had a higher mean HJHS (18.8 vs 2.6, P = .000) and leg muscle laterality (4.3% vs 1.5%, P = .004). A subgroup analysis revealed progressed gait pathology in PWH aged 26-49 years (not statistically significant). Leg muscle laterality was strongly correlated with HJHS (r = .76, P = .000), whereas GDI just moderately (r = -.39, P = .110). PWH had higher levels of the inflammatory markers CRP and IL-6. CONCLUSION: Progressed gait pathology was found in PWH, mainly those aged 26-49 years. Leg muscle laterality correlated strongly with HJHS and was identified as a promising tool for detecting progression and physiological consequences of haemophilic joint arthropathy.

Real-life gait assessment in degenerative cerebellar ataxia: Toward ecologically valid biomarkers.

OBJECTIVES: With disease-modifying drugs on the horizon for degenerative ataxias, ecologically valid motor biomarkers are highly warranted. In this observational study, we aimed to unravel and validate markers of ataxic gait in real life by using wearable sensors. METHODS: We assessed gait characteristics of 43 patients with degenerative cerebellar disease (Scale for the Assessment and Rating of Ataxia [SARA] 9.4 ± 3.9) compared with 35 controls by 3 body-worn inertial sensors in 3 conditions: (1) laboratory-based walking; (2) supervised free walking; (3) real-life walking during everyday living (subgroup n = 21). Movement analysis focused on measures of spatiotemporal step variability and movement smoothness. RESULTS: A set of gait variability measures was identified that allowed us to consistently identify ataxic gait changes in all 3 conditions. Lateral step deviation and a compound measure of spatial step variability categorized patients vs controls with a discrimination accuracy of 0.86 in real life. Both were highly correlated with clinical ataxia severity (effect size ρ = 0.76). These measures allowed detecting group differences even for patients who differed only 1 point in the clinical SARAposture&gait subscore, with highest effect sizes for real-life walking (d = 0.67). CONCLUSIONS: We identified measures of ataxic gait that allowed us not only to capture the gait variability inherent in ataxic gait in real life, but also to demonstrate high sensitivity to small differences in disease severity, with the highest effect sizes in real-life walking. They thus represent promising candidates for motor markers for natural history and treatment trials in ecologically valid contexts. CLASSIFICATION OF EVIDENCE: This study provides Class I evidence that a set of gait variability measures, even if accessed in real life, correlated with the clinical severity of ataxia in patients with degenerative cerebellar disease.

Longitudinal Assessment of Sensorimotor Function after Controlled Cortical Impact in Mice: Comparison of Beamwalk, Rotarod, and Automated Gait Analysis Tests.

Traumatic brain injury (TBI) patients are reported to experience long-term sensorimotor dysfunction, with gait deficits evident up to 2 years after the initial brain trauma. Experimental TBI including rodent models of penetrating ballistic-like brain injury and severe controlled cortical impact (CCI) can induce impairments in static and dynamic gait parameters. It is reported that the majority of deficits in gait-related parameters occur during the acute phase post-injury, as functional outcomes return toward baseline levels at chronic time points. In the present study, we carried out a longitudinal analysis of static, temporal and dynamic gait patterns following moderate-level CCI in adult male C57Bl/6J mice using the automated gait analysis apparatus, CatWalk. For comparison, we also performed longitudinal assessment of fine-motor coordination and function in CCI mice using more traditional sensorimotor behavioral tasks such as the beamwalk and accelerating rotarod tasks. We determined that longitudinal CatWalk analysis did not detect TBI-induced deficits in static, temporal, or dynamic gait parameters at acute or chronic time points. In contrast, the rotarod and beamwalk tasks showed that CCI mice had significant motor function impairments as demonstrated by deficits in balance and fine-motor coordination through 28 days post-injury. Stereological analysis confirmed that CCI produced a significant lesion in the parietal cortex at 28 days post-injury. Overall, these findings demonstrate that CatWalk analysis of gait parameters is not useful for assessment of long-term sensorimotor dysfunction after CCI, and that more traditional neurobehavioral tests should be used to quantify acute and chronic deficits in sensorimotor function.

The CatWalk XT® is a valid tool for objective assessment of motor function in the acute phase after controlled cortical impact in mice.

BACKGROUND: Despite multiple experimental models of traumatic brain injury (TBI) being available, objective assessment of gait and motor function in rodents remains difficult; therefore, we studied the value of the CatWalk XT® gait analysis as an observer independent, automated method for outcome assessment in one of the most frequently used preclinical TBI model, the controlled cortical impact (CCI), in mice. METHODS: C57Bl/6 mice were subjected to either right parietal CCI or a sham procedure. Functional outcome was assessed using the CatWalk XT® (Version 10.6) as well as the hole board test at days one, three and seven after trauma induction. RESULTS: CCI led to diffuse, asymmetric and bilateral disturbances of both static and dynamic parameters in the CatWalk XT® gait analysis. The CatWalk XT® detected even minimal but statistically significant impairments that could not have been detected by clinical assessments. Impairments of static parameters were most pronounced within the first three days and diminished thereafter, while dynamic parameters were impaired until seven days after CCI. Fittingly, mice explored the hole board significantly less on day three trauma induction. CONCLUSIONS: The CatWalk XT® is a valid tool for objective assessment of motor function in the acute phase after controlled cortical impact TBI in mice. Similar to observations made in humans, CCI leads to impairments of both static and dynamic parameters of gait and motor function which persist throughout the first week after the injury.

Difference in eye movements during gait analysis between professionals and trainees.

INTRODUCTION: Observational gait analysis is a widely used skill in physical therapy. Meanwhile, the skill has not been investigated using objective assessments. The present study investigated the differences in eye movement between professionals and trainees, while observing gait analysis. METHODS: The participants included in this study were 26 professional physical therapists and 26 physical therapist trainees. The participants, wearing eye tracker systems, were asked to describe gait abnormalities of a patient as much as possible. The eye movement parameters of interest were fixation count, average fixation duration, and total fixation duration. RESULTS: The number of gait abnormalities described was significantly higher in professionals than in trainees, overall and in limbs of the patient. The fixation count was significantly higher in professionals when compared to trainees. Additionally, the average fixation duration and total fixation duration were significantly shorter in professionals. Conversely, in trunks, the number of gait abnormalities and eye movements showed no significant differences between groups. CONCLUSIONS: Professionals require shorter fixation durations on areas of interest than trainees, while describing a higher number of gait abnormalities.

Reliability of a New Clinical Gait Assessment Scale for Children with Idiopathic Toe Walking Gait - A Pilot Study.

AIMS: Children with idiopathic toe walking (ITW) gait are increasingly referred to physical therapists. The purpose of this study was to evaluate the intra-rater and inter-rater reliability of the Clinical Gait Assessment Scale (CGAS), a newly developed observational rating scale. METHODS: Four raters evaluated videos of four children. Foot, arm and head/trunk movement was scored as children walked over four surfaces. Intra-class correlation coefficients (ICC), model (3,k) were calculated to determine intra-rater and inter-rater reliability of each dependent variable. RESULTS: The key findings of this study indicate robust intra- and inter-rater reliability, particularly of the foot (Inter-rater reliability, ICC (3,2)=0.9) and head and trunk (Inter-rater reliability, ICC (3,2)=1.0) subsections. Arm movements were more challenging to rate and showed moderate reliability (Inter-rater reliability, ICC (3,2)=0.7). Highest total impairment score; the highest value occurred while walking on the obstacle course (38 ± 29). CONCLUSIONS: Overall, the CGAS showed adequate/acceptable reliability across different surfaces (linoleum, textured surface, narrow base, obstacle), however the obstacle surface was most challenging surface to the rater.

Assessment of Patient Ambulation Profiles to Predict Hospital Readmission, Discharge Location, and Length of Stay in a Cardiac Surgery Progressive Care Unit.

Importance: Promoting patient mobility during hospitalization is associated with improved outcomes and reduced risk of hospitalization-associated functional decline. Therefore, accurate measurement of mobility with high-information content data may be key to improved risk prediction models, identification of at-risk patients, and the development of interventions to improve outcomes. Remote monitoring enables measurement of multiple ambulation metrics incorporating both distance and speed. Objective: To evaluate novel ambulation metrics in predicting 30-day readmission rates, discharge location, and length of stay using a real-time location system to continuously monitor the voluntary ambulations of postoperative cardiac surgery patients. Design, Setting, and Participants: This prognostic cohort study of the mobility of 100 patients after cardiac surgery in a progressive care unit at Johns Hopkins Hospital was performed using a real-time location system. Enrollment occurred between August 29, 2016, and April 4, 2018. Data analysis was performed from June 2018 to December 2019. Main Outcomes and Measures: Outcome measures included 30-day readmission, discharge location, and length of stay. Digital records of all voluntary ambulations were created where each ambulation consisted of multiple segments defined by distance and speed. Ambulation profiles consisted of 19 parameters derived from the digital ambulation records. Results: A total of 100 patients (81 men [81%]; mean [SD] age, 63.1 [11.6] years) were evaluated. Distance and speed were recorded for more than 14 000 segments in 840 voluntary ambulations, corresponding to a total of 127.8 km (79.4 miles) using a real-time location system. Patient ambulation profiles were predictive of 30-day readmission (sensitivity, 86.7%; specificity, 88.2%; C statistic, 0.925 [95% CI, 0.836-1.000]), discharge to acute rehabilitation (sensitivity, 84.6%; specificity, 86.4%; C statistic, 0.930 [95% CI, 0.855-1.000]), and length of stay (correlation coefficient, 0.927). Conclusions and Relevance: Remote monitoring provides a high-information content description of mobility, incorporating elements of step count (ambulation distance and related parameters), gait speed (ambulation speed and related parameters), frequency of ambulation, and changes in parameters on successive ambulations. Ambulation profiles incorporating multiple aspects of mobility enables accurate prediction of clinically relevant outcomes.

A Quality of Experience assessment of haptic and augmented reality feedback modalities in a gait analysis system.

Gait analysis is a technique that is used to understand movement patterns and, in some cases, to inform the development of rehabilitation protocols. Traditional rehabilitation approaches have relied on expert guided feedback in clinical settings. Such efforts require the presence of an expert to inform the re-training (to evaluate any improvement) and the patient to travel to the clinic. Nowadays, potential opportunities exist to employ the use of digitized "feedback" modalities to help a user to "understand" improved gait technique. This is important as clear and concise feedback can enhance the quality of rehabilitation and recovery. A critical requirement emerges to consider the quality of feedback from the user perspective i.e. how they process, understand and react to the feedback. In this context, this paper reports the results of a Quality of Experience (QoE) evaluation of two feedback modalities: Augmented Reality (AR) and Haptic, employed as part of an overall gait analysis system. The aim of the feedback is to reduce varus/valgus misalignments, which can cause serious orthopedics problems. The QoE analysis considers objective (improvement in knee alignment) and subjective (questionnaire responses) user metrics in 26 participants, as part of a within subject design. Participants answered 12 questions on QoE aspects such as utility, usability, interaction and immersion of the feedback modalities via post-test reporting. In addition, objective metrics of participant performance (angles and alignment) were also considered as indicators of the utility of each feedback modality. The findings show statistically significant higher QoE ratings for AR feedback. Also, the number of knee misalignments was reduced after users experienced AR feedback (35% improvement with AR feedback relative to baseline when compared to haptic). Gender analysis showed significant differences in performance for number of misalignments and time to correct valgus misalignment (for males when they experienced AR feedback). The female group self-reported higher utility and QoE ratings for AR when compared to male group.

Comparison of Gait Assessment Scales in Dogs with Spinal Cord Injury from Intervertebral Disc Herniation.

Naturally occurring thoracolumbar spinal cord injury (SCI) is common in dogs, and multi-center veterinary clinical studies can serve as translational tools to identify potentially effective therapies for human clinical trials. Assessment of gait is a key outcome, and several scales are used in dogs. The purpose of this study was to determine whether an international group of researchers could score gait reliably, to compare and contrast the performance of gait scales and to describe appropriate data analysis techniques. A training module was developed for a binary scale, modified Frankel Scale (MFS), Texas SCI Scale (TSCIS), and Open Field Scale (OFS). Raters viewed the training module, scored five training video clips to achieve proficiency, then scored 30 video clips from 10 dogs recovering from SCI. Interrater reliability was calculated, and correlation between scales was examined. Ceiling effect was described. Twenty raters with differing experience participated. The training module took 16 min to view. Raters chose identical binary outcomes in 597 of 600 observations. Intraclass correlation for MFS, TSCIS, and OFS was excellent at 0.85, 0.96, and 0.96, respectively, regardless of rater expertise. Ceiling effect occurred in all dogs that recovered ambulation, particularly using MFS and binary outcome. The TSCIS and OFS captured recovery of ambulatory dogs better, and addition of scores on hopping and proprioception mitigated ceiling effect. We conclude that gait in dogs with SCI can be scored reliably after training. A variety of different gait scales can be used in multi-center trials to capture outcome in different ways.

Dual-Task Gait Assessment in a Clinical Sample: Implications for Improved Detection of Mild Cognitive Impairment.

OBJECTIVES: Research has longitudinally linked dual-task gait dysfunction to mild cognitive impairment (MCI) and dementia risk. Our group previously demonstrated that dual-task gait speed assessment distinguished between subjective cognitive complaints (SCC) and MCI in a memory clinic setting, and also found that differences in dual-task gait speed were largely attributable to executive attention processes. This study aimed to reproduce these findings in a larger diverse sample and to extend them by examining whether there were group differences in single- versus dual-task cognitive performance (number of letters correctly sequenced backward). METHOD: Two-hundred fifty-two patients (M age = 66.01 years, SD = 10.46; 119 MCI, 133 SCC) presenting with cognitive complaints in an academic medical setting underwent comprehensive neuropsychological and gait assessment (single- and dual-task conditions). RESULTS: Patients with MCI walked slower and showed greater decrement in cognitive performance than those with SCC during dual-task conditions. Neuropsychological measures of executive attention accounted for significant variance in dual-task gait performance across diagnostic groups beyond demographic and health risk factors. DISCUSSION: Reproduction of our results within a sample over four times the previous size provides support for the use of dual-task gait assessment as a marker of MCI risk in clinical settings.

Estimation of Vertical Ground Reaction Force Using Low-Cost Insole With Force Plate-Free Learning From Single Leg Stance and Walking.

For the evaluation of pathological gait, a machine learning-based estimation of the vertical ground reaction force (vGRF) using a low-cost insole is proposed as an alternative to costly force plates. However, learning a model for estimation still relies on the use of force plates, which is not accessible in small clinics and individuals. Therefore, this paper presents a force plate-free learning from a single leg stance (SLS) and natural walking measured only by the insoles. This method used a linear least squares regression that fits insole measurements during SLS to body weight in order to learn a model to estimate vGRF during walking. Constraints were added to the regression so that vGRF estimates during walking were of proper magnitude, and the constraint bounds were newly defined as a linear function of stance duration. Moreover, a lower bound for the estimated vGRF in mid-stance was added to the constraints to enhance estimation accuracy. The vGRF estimated by the proposed method was compared with force platforms for 4 healthy young adults and 13 elderly adults including patients with mild osteoarthritis, knee pain, and valgus hallux. Through the experiments, the proposed learning method had a normalized root mean squared error under 10% for healthy young and elderly adults with stance durations within a certain range (600-800 ms). From these results, the validity of the proposed learning method was verified for various users requiring assessment in the field of medicine and healthcare.

Technical Validation of an Automated Mobile Gait Analysis System for Hereditary Spastic Paraplegia Patients.

Hereditary spastic paraplegias (HSP) represents a group of orphan neurodegenerative diseases with gait disturbance as the predominant clinical feature. Due to its rarity, research within this field is still limited. Aside from clinical analysis using established scales, gait analysis has been employed to enhance the understanding of the mechanisms behind the disease. However, state of the art gait analysis systems are often large, immobile and expensive. To overcome these limitations, this paper presents the first clinically relevant mobile gait analysis system for HSP patients. We propose an unsupervised model based on local cyclicity estimation and hierarchical hidden Markov models (LCE-hHMM). The system provides stride time, swing time, stance time, swing duration and cadence. These parameters are validated against a GAITRite system and manual sensor data labelling using a total of 24 patients within 2 separate studies. The proposed system achieves a stride time error of -0.00  ± 0.09 s (correlation coefficient, r = 1.00) and a swing duration error of -0.67  ± 3.27 % (correlation coefficient, r = 0.93) with respect to the GAITRite system. We show that these parameters are also correlated to the clinical spastic paraplegia rating scale (SPRS) in a similar manner to other state of the art gait analysis systems, as well as to supervised and general versions of the proposed model. Finally, we show a proof of concept for this system to be used to analyse alterations in the gait of individual patients. Thus, with further clinical studies, due to its automated approach and mobility, this system could be used to determine treatment effects in future clinical trials.

Smartphone-Based Assessment of Gait During Straight Walking, Turning, and Walking Speed Modulation in Laboratory and Free-Living Environments.

As turns and walking speed modulation are crucial for functional mobility, development of a field-based tool to objectively evaluate non-steady-state gait is essential. This study aimed to quantify spatiotemporal gait using three Android smartphones during steady-state walking, turns, and gait speed modulation in laboratory and free-living environments. In total, 24 adults ambulated along a 10-m walkway in both environments under seven conditions: straight walking, 90° left or right turn, and modulating gait speed from usual-slow, usual-fast, slow-fast, and fast-slow. Two smartphones were attached to the body, with another phone placed in a shoulder bag. Gait velocity, step time, step length, cadence, and symmetry were computed from smartphone-based tri-axial accelerometers and validated with motion capture and video, in laboratory and free-living environments, respectively. Validity was assessed using Pearson's correlation and Bland-Altman analysis. Gait velocity results revealed moderate to very high validity across all walking conditions, smartphone models, smartphone locations, and environments. Correlations for gait velocity ranged between 0.87-0.91 and 0.79-0.83 for straight walking, 0.86-0.95 and 0.86-0.89 for turning, and 0.51-0.90 and 0.67-0.89 for speed modulation trials, in laboratory and free-living environments, respectively. Step time, step length, and cadence demonstrated high to very high correlations for straight walking and turns. However, symmetry results revealed high correlations only during straight walking in the laboratory. Conditions that included slow walking showed negligible to moderate validity with a high bias. In conclusion, smartphones can be employed as field-based devices to assess steady-state walking, turning, and speed modulation across environment, model, and placement when walking faster than 0.5 m/s.