Beyond gait speed: exploring the added value of Inertial Measurement Unit-based measurements of gait in the estimation of the walking ability in daily life.

BACKGROUND: Gait speed is often used to estimate the walking ability in daily life in people after stroke. While measuring gait with inertial measurement units (IMUs) during clinical assessment yields additional information, it remains unclear if this information can improve the estimation of the walking ability in daily life beyond gait speed. OBJECTIVE: We evaluated the additive value of IMU-based gait features over a simple gait-speed measurement in the estimation of walking ability in people after stroke. METHODS: Longitudinal data during clinical stroke rehabilitation were collected. The assessment consisted of two parts and was administered every three weeks. In the first part, participants walked for two minutes (2MWT) on a fourteen-meter path with three IMUs attached to low back and feet, from which multiple gait features, including gait speed, were calculated. The dimensionality of the corresponding gait features was reduced with a principal component analysis. In the second part, gait was measured for two consecutive days using one ankle-mounted IMU. Next, three measures of walking ability in daily life were calculated, including the number of steps per day, and the average and maximal gait speed. A gait-speed-only Linear Mixed Model was used to estimate the association between gait speed and each of the three measures of walking ability. Next, the principal components (PC), derived from the 2MWT, were added to the gait-speed-only model to evaluate if they were confounders or effect modifiers. RESULTS: Eighty-one participants were measured during rehabilitation, resulting in 198 2MWTs and 135 corresponding walking-performance measurements. 106 Gait features were reduced to nine PCs with 85.1% explained variance. The linear mixed models demonstrated that gait speed was weakly associated with the average and maximum gait speed in daily life and moderately associated with the number of steps per day. The PCs did not considerably improve the outcomes in comparison to the gait speed only models. CONCLUSIONS: Gait in people after stroke assessed in a clinical setting with IMUs differs from their walking ability in daily life. More research is needed to determine whether these discrepancies also occur in non-laboratory settings, and to identify additional non-gait factors that influence walking ability in daily life.

Minimal detectable change of gait and balance measures in older neurological patients: estimating the standard error of the measurement from before-after rehabilitation data thanks to the linear mixed-effects models.

BACKGROUND: Tracking gait and balance impairment in time is paramount in the care of older neurological patients. The Minimal Detectable Change (MDC), built upon the Standard Error of the Measurement (SEM), is the smallest modification of a measure exceeding the measurement error. Here, a novel method based on linear mixed-effects models (LMMs) is applied to estimate the standard error of the measurement from data collected before and after rehabilitation and calculate the MDC of gait and balance measures. METHODS: One hundred nine older adults with a gait impairment due to neurological disease (66 stroke patients) completed two assessment sessions before and after inpatient rehabilitation. In each session, two trials of the 10-meter walking test and the Timed Up and Go (TUG) test, instrumented with inertial sensors, have been collected. The 95% MDC was calculated for the gait speed, TUG test duration (TTD) and other measures from the TUG test, including the angular velocity peak (ωpeak) in the TUG test's turning phase. Random intercepts and slopes LMMs with sessions as fixed effects were used to estimate SEM. LMMs assumptions (residuals normality and homoscedasticity) were checked, and the predictor variable ln-transformed if needed. RESULTS: The MDC of gait speed was 0.13 m/s. The TTD MDC, ln-transformed and then expressed as a percentage of the baseline value to meet LMMs' assumptions, was 15%, i.e. TTD should be < 85% of the baseline value to conclude the patient's improvement. ωpeak MDC, also ln-transformed and expressed as the baseline percentage change, was 25%. CONCLUSIONS: LMMs allowed calculating the MDC of gait and balance measures even if the test-retest steady-state assumption did not hold. The MDC of gait speed, TTD and ωpeak from the TUG test with an inertial sensor have been provided. These indices allow monitoring of the gait and balance impairment, which is central for patients with an increased falling risk, such as neurological old persons. TRIAL REGISTRATION: NA.

Quantifying Asymmetric Gait Pattern Changes Using a Hidden Markov Model Similarity Measure (HMM-SM) on Inertial Sensor Signals.

Wearable gait analysis systems using inertial sensors offer the potential for easy-to-use gait assessment in lab and free-living environments. This can enable objective long-term monitoring and decision making for individuals with gait disabilities. This study explores a novel approach that applies a hidden Markov model-based similarity measure (HMM-SM) to assess changes in gait patterns based on the gyroscope and accelerometer signals from just one or two inertial sensors. Eleven able-bodied individuals were equipped with a system which perturbed gait patterns by manipulating stance-time symmetry. Inertial sensor data were collected from various locations on the lower body to train hidden Markov models. The HMM-SM was evaluated to determine whether it corresponded to changes in gait as individuals deviated from their baseline, and whether it could provide a reliable measure of gait similarity. The HMM-SM showed consistent changes in accordance with stance-time symmetry in the following sensor configurations: pelvis, combined upper leg signals, and combined lower leg signals. Additionally, the HMM-SM demonstrated good reliability for the combined upper leg signals (ICC = 0.803) and lower leg signals (ICC = 0.795). These findings provide preliminary evidence that the HMM-SM could be useful in assessing changes in overall gait patterns. This could enable the development of compact, wearable systems for unsupervised gait assessment, without the requirement to pre-identify and measure a set of gait parameters.

Gait Variability as a Potential Motor Marker of Cerebellar Disease-Relationship between Variability of Stride, Arm Swing and Trunk Movements, and Walking Speed.

Excessive stride variability is a characteristic feature of cerebellar ataxias, even in pre-ataxic or prodromal disease stages. This study explores the relation of variability of arm swing and trunk deflection in relationship to stride length and gait speed in previously described cohorts of cerebellar disease and healthy elderly: we examined 10 patients with spinocerebellar ataxia type 14 (SCA), 12 patients with essential tremor (ET), and 67 healthy elderly (HE). Using inertial sensors, recordings of gait performance were conducted at different subjective walking speeds to delineate gait parameters and respective coefficients of variability (CoV). Comparisons across cohorts and walking speed categories revealed slower stride velocities in SCA and ET patients compared to HE, which was paralleled by reduced arm swing range of motion (RoM), peak velocity, and increased CoV of stride length, while no group differences were found for trunk deflections and their variability. Larger arm swing RoM, peak velocity, and stride length were predicted by higher gait velocity in all cohorts. Lower gait velocity predicted higher CoV values of trunk sagittal and horizontal deflections, as well as arm swing and stride length in ET and SCA patients, but not in HE. These findings highlight the role of arm movements in ataxic gait and the impact of gait velocity on variability, which are essential for defining disease manifestation and disease-related changes in longitudinal observations.

Development of a Gait Analysis Application for Assessing Upper and Lower Limb Movements to Detect Pathological Gait.

Pathological gait in patients with Hakim's disease (HD, synonymous with idiopathic normal-pressure hydrocephalus; iNPH), Parkinson's disease (PD), and cervical myelopathy (CM) has been subjectively evaluated in this study. We quantified the characteristics of upper and lower limb movements in patients with pathological gait. We analyzed 1491 measurements of 1 m diameter circular walking from 122, 12, and 93 patients with HD, PD, and CM, respectively, and 200 healthy volunteers using the Three-Dimensional Pose Tracker for Gait Test. Upper and lower limb movements of 2D coordinates projected onto body axis sections were derived from estimated 3D relative coordinates. The hip and knee joint angle ranges on the sagittal plane were significantly smaller in the following order: healthy > CM > PD > HD, whereas the shoulder and elbow joint angle ranges were significantly smaller, as follows: healthy > CM > HD > PD. The outward shift of the leg on the axial plane was significantly greater, as follows: healthy < CM < PD < HD, whereas the outward shift of the upper limb followed the order of healthy > CM > HD > PD. The strongest correlation between the upper and lower limb movements was identified in the angle ranges of the hip and elbow joints on the sagittal plane. The lower and upper limb movements during circular walking were correlated. Patients with HD and PD exhibited reduced back-and-forth swings of the upper and lower limbs.

Prognostic relevance of gait-related cognitive functions for dementia conversion in amnestic mild cognitive impairment.

BACKGROUND: Increasing research suggests that gait abnormalities can be a risk factor for Alzheimer's Disease (AD). Notably, there is growing evidence highlighting this risk factor in individuals with amnestic Mild Cognitive Impairment (aMCI), however further studies are needed. The aim of this study is to analyze cognitive tests results and brain-related measures over time in aMCI and examine how the presence of gait abnormalities (neurological or orthopedic) or normal gait affects these trends. Additionally, we sought to assess the significance of gait and gait-related measures as prognostic indicators for the progression from aMCI to AD dementia, comparing those who converted to AD with those who remained with a stable aMCI diagnosis during the follow-up. METHODS: Four hundred two individuals with aMCI from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database were included. Robust linear mixed-effects models were used to study the impact of gait abnormalities on a comprehensive neuropsychological battery over 36 months while controlling for relevant medical variables at baseline. The impact of gait on brain measures was also investigated. Lastly, the Cox proportional-hazards model was used to explore the prognostic relevance of abnormal gait and neuropsychological associated tests. RESULTS: While controlling for relevant covariates, we found that gait abnormalities led to a greater decline over time in attention (DSST) and global cognition (MMSE). Intriguingly, psychomotor speed (TMT-A) and divided attention (TMT-B) declined uniquely in the abnormal gait group. Conversely, specific AD global cognition tests (ADAS-13) and auditory-verbal memory (RAVLT immediate recall) declined over time independently of gait profile. All the other cognitive tests were not significantly affected by time or by gait profile. In addition, we found that ventricles size increased faster in the abnormal gait group compared to the normal gait group. In terms of prognosis, abnormal gait (HR = 1.7), MMSE (HR = 1.09), and DSST (HR = 1.03) covariates showed a higher impact on AD dementia conversion. CONCLUSIONS: The importance of the link between gait and related cognitive functions in terms of diagnosis, prognosis, and rehabilitation in aMCI is critical. We showed that in aMCI gait abnormalities lead to executive functions/attention deterioration and conversion to AD dementia.

Stepping beyond Counts in Recovery of Total Knee Arthroplasty: A Prospective Study on Passively Collected Gait Metrics.

Advances in algorithms developed from sensor-based technology data allow for the passive collection of qualitative gait metrics beyond step counts. The purpose of this study was to evaluate pre- and post-operative gait quality data to assess recovery following primary total knee arthroplasty. This was a multicenter, prospective cohort study. From 6 weeks pre-operative through to 24 weeks post-operative, 686 patients used a digital care management application to collect gait metrics. Average weekly walking speed, step length, timing asymmetry, and double limb support percentage pre- and post-operative values were compared with a paired-samples t-test. Recovery was operationally defined as when the respective weekly average gait metric was no longer statistically different than pre-operative. Walking speed and step length were lowest, and timing asymmetry and double support percentage were greatest at week two post-operative (p < 0.0001). Walking speed recovered at 21 weeks (1.00 m/s, p = 0.063) and double support percentage recovered at week 24 (32%, p = 0.089). Asymmetry percentage was recovered at 13 weeks (14.0%, p = 0.23) and was consistently superior to pre-operative values at week 19 (11.1% vs. 12.5%, p < 0.001). Step length did not recover during the 24-week period (0.60 m vs. 0.59 m, p = 0.004); however, this difference is not likely clinically relevant. The data suggests that gait quality metrics are most negatively affected two weeks post-operatively, recover within the first 24-weeks following TKA, and follow a slower trajectory compared to previously reported step count recoveries. The ability to capture new objective measures of recovery is evident. As more gait quality data is accrued, physicians may be able to use passively collected gait quality data to help direct post-operative recovery using sensor-based care pathways.

Quantitative Gait Feature Assessment on Two-Dimensional Body Axis Projection Planes Converted from Three-Dimensional Coordinates Estimated with a Deep Learning Smartphone App.

To assess pathological gaits quantitatively, three-dimensional coordinates estimated with a deep learning model were converted into body axis plane projections. First, 15 healthy volunteers performed four gait patterns; that is, normal, shuffling, short-stepped, and wide-based gaits, with the Three-Dimensional Pose Tracker for Gait Test (TDPT-GT) application. Second, gaits of 47 patients with idiopathic normal pressure hydrocephalus (iNPH) and 92 healthy elderly individuals in the Takahata cohort were assessed with the TDPT-GT. Two-dimensional relative coordinates were calculated from the three-dimensional coordinates by projecting the sagittal, coronal, and axial planes. Indices of the two-dimensional relative coordinates associated with a pathological gait were comprehensively explored. The candidate indices for the shuffling gait were the angle range of the hip joint < 30° and relative vertical amplitude of the heel < 0.1 on the sagittal projection plane. For the short-stepped gait, the angle range of the knee joint < 45° on the sagittal projection plane was a candidate index. The candidate index for the wide-based gait was the leg outward shift > 0.1 on the axial projection plane. In conclusion, the two-dimensional coordinates on the body axis projection planes calculated from the 3D relative coordinates estimated by the TDPT-GT application enabled the quantification of pathological gait features.

Stepping Beyond Counts in Recovery of Total Hip Arthroplasty: A Prospective Study on Passively Collected Gait Metrics.

Gait quality parameters have been used to measure recovery from total hip arthroplasty (THA) but are time-intensive and previously could only be performed in a lab. Smartphone sensor data and algorithmic advances presently allow for the passive collection of qualitative gait metrics. The purpose of this prospective study was to observe the recovery of physical function following THA by assessing passively collected pre- and post-operative gait quality metrics. This was a multicenter, prospective cohort study. From six weeks pre-operative through to a minimum 24 weeks post-operative, 612 patients used a digital care management application that collected gait metrics. Average weekly walking speed, step length, timing asymmetry, and double limb support percentage pre- and post-operative values were compared with a paired-sample t-test. Recovery was defined as the post-operative week when the respective gait metric was no longer statistically inferior to the pre-operative value. To control for multiple comparison error, significance was set at p < 0.002. Walking speeds and step length were lowest, and timing asymmetry and double support percentage were greatest at week two post-post-operative (p < 0.001). Walking speed (1.00 ± 0.14 m/s, p = 0.04), step length (0.58 ± 0.06 m/s, p = 0.02), asymmetry (14.5 ± 19.4%, p = 0.046), and double support percentage (31.6 ± 1.5%, p = 0.0089) recovered at 9, 8, 7, and 10 weeks post-operative, respectively. Walking speed, step length, asymmetry, and double support all recovered beyond pre-operative values at 13, 17, 10, and 18 weeks, respectively (p < 0.002). Functional recovery following THA can be measured via passively collected gait quality metrics using a digital care management platform. The data suggest that metrics of gait quality are most negatively affected two weeks post-operative; recovery to pre-operative levels occurs at approximately 10 weeks following primary THA, and follows a slower trajectory compared to previously reported step count recovery trajectories.

Uncovering Subtle Gait Deterioration in People with Early-Stage Multiple Sclerosis Using Inertial Sensors: A 2-Year Multicenter Longitudinal Study.

Limited longitudinal studies have been conducted on gait impairment progression overtime in non-disabled people with multiple sclerosis (PwMS). Therefore, a deeper understanding of gait changes with the progression of the disease is essential. The objective of the present study was to describe changes in gait quality in PwMS with a disease duration ≤ 5 years, and to verify whether a change in gait quality is associated with a change in disability and perception of gait deterioration. We conducted a multicenter prospective cohort study. Fifty-six subjects were assessed at baseline (age: 38.2 ± 10.7 years, Expanded Disability Status Scale (EDSS): 1.5 ± 0.7 points) and after 2 years, participants performed the six-minute walk test (6MWT) wearing inertial sensors. Quality of gait (regularity, symmetry, and instability), disability (EDSS), and walking perception (multiple sclerosis walking scale-12, MSWS-12) were collected. We found no differences on EDSS, 6MWT, and MSWS-12 between baseline and follow-up. A statistically significant correlation between increased EDSS scores and increased gait instability was found in the antero-posterior (AP) direction (r = 0.34, p = 0.01). Seventeen subjects (30%) deteriorated (increase of at least 0.5 point at EDSS) over 2 years. A multivariate analysis on deteriorated PwMS showed that changes in gait instability medio-lateral (ML) and stride regularity, and changes in ML gait symmetry were significantly associated with changes in EDSS (F = 7.80 (3,13), p = 0.003, R2 = 0.56). Moreover, gait changes were associated with a decrease in PwMS perception on stability (p < 0.05). Instrumented assessment can detect subtle changes in gait stability, regularity, and symmetry not revealed during EDSS neurological assessment. Moreover, instrumented changes in gait quality impact on subjects' perception of gait during activities of daily living.

Artificial Intelligence Distinguishes Pathological Gait: The Analysis of Markerless Motion Capture Gait Data Acquired by an iOS Application (TDPT-GT).

Distinguishing pathological gait is challenging in neurology because of the difficulty of capturing total body movement and its analysis. We aimed to obtain a convenient recording with an iPhone and establish an algorithm based on deep learning. From May 2021 to November 2022 at Yamagata University Hospital, Shiga University, and Takahata Town, patients with idiopathic normal pressure hydrocephalus (n = 48), Parkinson's disease (n = 21), and other neuromuscular diseases (n = 45) comprised the pathological gait group (n = 114), and the control group consisted of 160 healthy volunteers. iPhone application TDPT-GT captured the subjects walking in a circular path of about 1 meter in diameter, a markerless motion capture system, with an iPhone camera, which generated the three-axis 30 frames per second (fps) relative coordinates of 27 body points. A light gradient boosting machine (Light GBM) with stratified k-fold cross-validation (k = 5) was applied for gait collection for about 1 min per person. The median ability model tested 200 frames of each person's data for its distinction capability, which resulted in the area under a curve of 0.719. The pathological gait captured by the iPhone could be distinguished by artificial intelligence.

Instrumented Gait Classification Using Meaningful Features in Patients with Impaired Coordination.

Early onset ataxia (EOA) and developmental coordination disorder (DCD) both affect cerebellar functioning in children, making the clinical distinction challenging. We here aim to derive meaningful features from quantitative SARA-gait data (i.e., the gait test of the scale for the assessment and rating of ataxia (SARA)) to classify EOA and DCD patients and typically developing (CTRL) children with better explainability than previous classification approaches. We collected data from 18 EOA, 14 DCD and 29 CTRL children, while executing both SARA gait tests. Inertial measurement units were used to acquire movement data, and a gait model was employed to derive meaningful features. We used a random forest classifier on 36 extracted features, leave-one-out-cross-validation and a synthetic oversampling technique to distinguish between the three groups. Classification accuracy, probabilities of classification and feature relevance were obtained. The mean classification accuracy was 62.9% for EOA, 85.5% for DCD and 94.5% for CTRL participants. Overall, the random forest algorithm correctly classified 82.0% of the participants, which was slightly better than clinical assessment (73.0%). The classification resulted in a mean precision of 0.78, mean recall of 0.70 and mean F1 score of 0.74. The most relevant features were related to the range of the hip flexion-extension angle for gait, and to movement variability for tandem gait. Our results suggest that classification, employing features representing different aspects of movement during gait and tandem gait, may provide an insightful tool for the differential diagnoses of EOA, DCD and typically developing children.

Adaptive Control Method for Gait Detection and Classification Devices with Inertial Measurement Unit.

Cueing and feedback training can be effective in maintaining or improving gait in individuals with Parkinson's disease. We previously designed a rehabilitation assist device that can detect and classify a user's gait at only the swing phase of the gait cycle, for the ease of data processing. In this study, we analyzed the impact of various factors in a gait detection algorithm on the gait detection and classification rate (GDCR). We collected acceleration and angular velocity data from 25 participants (1 male and 24 females with an average age of 62 ± 6 years) using our device and analyzed the data using statistical methods. Based on these results, we developed an adaptive GDCR control algorithm using several equations and functions. We tested the algorithm under various virtual exercise scenarios using two control methods, based on acceleration and angular velocity, and found that the acceleration threshold was more effective in controlling the GDCR (average Spearman correlation -0.9996, p < 0.001) than the gyroscopic threshold. Our adaptive control algorithm was more effective in maintaining the target GDCR than the other algorithms (p < 0.001) with an average error of 0.10, while other tested methods showed average errors of 0.16 and 0.28. This algorithm has good scalability and can be adapted for future gait detection and classification applications.

Older Persons Displaying Parkinsonian Gait: Prediction and Explanation of the Recurrent Falling Phenomenon and Its Related Poor Prognosis.

INTRODUCTION: Parkinsonian gait in older persons is a major risk factor for recurrent falling. This prospective, longitudinal study (named EVAMAR-AGEX) aimed to validate the threshold value of two or more falls per year for distinguishing non-recurrent (NRF) from recurrent fallers (RF), to explore predictive factors for recurrent falling, and to identify factors which underlie the transition of patients from NRF to RF. The study took place over 2 years, with an intermediate analysis at 1 year of follow-up. Herein, we report results after 2 years of follow-up. METHODS: Participants over the age of 65, diagnosed with parkinsonian gait, were followed over the course of 2 years. Induced parkinsonian syndrome and uncontrolled orthostatic hypotension were excluded. Assessments of motor, visual, and cognitive functions were carried out during visits at baseline. Between visits at 12 and 24 months of follow-up, data were collected by phone call every 2 months (falls, traumatic falls, hospitalizations, cognitive fluctuations, delirium, and mortality). Odds ratios (ORs) for a panel of predictive factors for recurrent falling were established using a Bayesian model. RESULTS: Sixty-six of the 79 initially enrolled participants progressed to the second year of the study, with a mean age of 80.57 (SD 6.3), 56% male, presenting parkinsonian gait (53% Parkinson's disease, 15% atypical neurodegenerative parkinsonism, 21% vascular parkinsonism, and 11% diffuse Lewy body disease). At 2 years of follow-up, 67% were RF. Univariate analysis revealed a previous history of falls to be the most significant predictive factor of recurrent falls (OR 13.16, credibility interval [CrI] [95%] 4.04-53.73), and this was reinforced at 2 years of follow-up compared to the intermediate 1-year analysis (OR 11.73, CrI [95%] 4.33-35.28). Multivariate analysis confirmed a previous history of falls (OR 13.20, CrI [95%] 3.29-72.08) and abnormal posture (OR 3.59, CrI [95%] 1.37-11.26) to be predictive factors for recurrent falling. Cognitive decline and fluctuating cognition were associated with the transition from NRF to RF (-3.5 MMSE points for participants transitioning from NRF to RF). CONCLUSION: Within this population of older persons presenting parkinsonian gait, a previous history of falls and abnormal posture may be used to easily identify individuals at risk of recurrent falls. Cognitive decline and fluctuations may underlie the transition of NRF to RF.

Keep it simple: comparing functional assessments in individuals with Down syndrome.

BACKGROUND: A number of assessments exist that evaluate function in ambulatory adults. However, these assessments take for granted the cognitive abilities required for the participant to understand what is being asked of them in order to demonstrate their functional abilities. It has been shown that individuals with Down syndrome (DS) demonstrate lower functional levels when asked to perform additional tasks while walking. Therefore, measurements of function may not be reflective of actual function if the assessment requires additional tasks in those with DS. It is for these reasons the current investigation sought to evaluate four common functional assessments, two with [modified Berg balance test (mBERG) and Functional Gait Assessment (FGA)] and two without [Timed Up and Go (TUG) and Established Populations for Epidemiologic Study in the Elderly (EPESE)] complex tasks. METHODS: Adults with DS (n = 19) completed four functional assessments, which were later compared using bivariate Pearson correlation coefficients. RESULTS: There were large associations between simple assessments (TUG-EPESE: r = -0.525, P = 0.021) and complex assessments (FGA-mBERG: r = 0.612, P = 0.005), respectively. The TUG also inversely correlated with the FGA (r = -0.476, P = 0.039), and the EPESE had a large association with mBERG (r = 0.508, P = 0.027). CONCLUSIONS: The mBERG may be the best test to replicate real-world scenarios through its tasks, although it may also be confounded by the cognitive load required to perform the movements as asked. The TUG and EPESE may be more appropriate as mobility assessments because they require very little cognitive attention when completing the tasks. True assessments of mobility ought to err on the side of simple so to not confuse the outcomes with executive functionality.

Association between Self-Reported Prior Night's Sleep and Single-Task Gait in Healthy, Young Adults: A Study Using Machine Learning.

Failure to obtain the recommended 7−9 h of sleep has been associated with injuries in youth and adults. However, most research on the influence of prior night's sleep and gait has been conducted on older adults and clinical populations. Therefore, the objective of this study was to identify individuals who experience partial sleep deprivation and/or sleep extension the prior night using single task gait. Participants (n = 123, age 24.3 ± 4.0 years; 65% female) agreed to participate in this study. Self-reported sleep duration of the night prior to testing was collected. Gait data was collected with inertial sensors during a 2 min walk test. Group differences (<7 h and >9 h, poor sleepers; 7−9 h, good sleepers) in gait characteristics were assessed using machine learning and a post-hoc ANCOVA. Results indicated a correlation (r = 0.79) between gait parameters and prior night's sleep. The most accurate machine learning model was a Random Forest Classifier using the top 9 features, which had a mean accuracy of 65.03%. Our findings suggest that good sleepers had more asymmetrical gait patterns and were better at maintaining gait speed than poor sleepers. Further research with larger subject sizes is needed to develop more accurate machine learning models to identify prior night's sleep using single-task gait.

Development of Smartphone Application for Markerless Three-Dimensional Motion Capture Based on Deep Learning Model.

To quantitatively assess pathological gait, we developed a novel smartphone application for full-body human motion tracking in real time from markerless video-based images using a smartphone monocular camera and deep learning. As training data for deep learning, the original three-dimensional (3D) dataset comprising more than 1 million captured images from the 3D motion of 90 humanoid characters and the two-dimensional dataset of COCO 2017 were prepared. The 3D heatmap offset data consisting of 28 × 28 × 28 blocks with three red-green-blue colors at the 24 key points of the entire body motion were learned using the convolutional neural network, modified ResNet34. At each key point, the hottest spot deviating from the center of the cell was learned using the tanh function. Our new iOS application could detect the relative tri-axial coordinates of the 24 whole-body key points centered on the navel in real time without any markers for motion capture. By using the relative coordinates, the 3D angles of the neck, lumbar, bilateral hip, knee, and ankle joints were estimated. Any human motion could be quantitatively and easily assessed using a new smartphone application named Three-Dimensional Pose Tracker for Gait Test (TDPT-GT) without any body markers or multipoint cameras.

Reliability of IMU-Based Gait Assessment in Clinical Stroke Rehabilitation.

BACKGROUND: Gait is often impaired in people after stroke, restricting personal independence and affecting quality of life. During stroke rehabilitation, walking capacity is conventionally assessed by measuring walking distance and speed. Gait features, such as asymmetry and variability, are not routinely determined, but may provide more specific insights into the patient's walking capacity. Inertial measurement units offer a feasible and promising tool to determine these gait features. OBJECTIVE: We examined the test-retest reliability of inertial measurement units-based gait features measured in a two-minute walking assessment in people after stroke and while in clinical rehabilitation. METHOD: Thirty-one people after stroke performed two assessments with a test-retest interval of 24 h. Each assessment consisted of a two-minute walking test on a 14-m walking path. Participants were equipped with three inertial measurement units, placed at both feet and at the low back. In total, 166 gait features were calculated for each assessment, consisting of spatio-temporal (56), frequency (26), complexity (63), and asymmetry (14) features. The reliability was determined using the intraclass correlation coefficient. Additionally, the minimal detectable change and the relative minimal detectable change were computed. RESULTS: Overall, 107 gait features had good-excellent reliability, consisting of 50 spatio-temporal, 8 frequency, 36 complexity, and 13 symmetry features. The relative minimal detectable change of these features ranged between 0.5 and 1.5 standard deviations. CONCLUSION: Gait can reliably be assessed in people after stroke in clinical stroke rehabilitation using three inertial measurement units.

Validation of Non-Restrictive Inertial Gait Analysis of Individuals with Incomplete Spinal Cord Injury in Clinical Settings.

Inertial Measurement Units (IMUs) have gained popularity in gait analysis and human motion tracking, and they provide certain advantages over stationary line-of-sight-dependent Optical Motion Capture (OMC) systems. IMUs appear as an appropriate alternative solution to reduce dependency on bulky, room-based hardware and facilitate the analysis of walking patterns in clinical settings and daily life activities. However, most inertial gait analysis methods are unpractical in clinical settings due to the necessity of precise sensor placement, the need for well-performed calibration movements and poses, and due to distorted magnetometer data in indoor environments as well as nearby ferromagnetic material and electronic devices. To address these limitations, recent literature has proposed methods for self-calibrating magnetometer-free inertial motion tracking, and acceptable performance has been achieved in mechanical joints and in individuals without neurological disorders. However, the performance of such methods has not been validated in clinical settings for individuals with neurological disorders, specifically individuals with incomplete Spinal Cord Injury (iSCI). In the present study, we used recently proposed inertial motion-tracking methods, which avoid magnetometer data and leverage kinematic constraints for anatomical calibration. We used these methods to determine the range of motion of the Flexion/Extension (F/E) hip and Abduction/Adduction (A/A) angles, the F/E knee angles, and the Dorsi/Plantar (D/P) flexion ankle joint angles during walking. Data (IMU and OMC) of five individuals with no neurological disorders (control group) and five participants with iSCI walking for two minutes on a treadmill in a self-paced mode were analyzed. For validation purposes, the OMC system was considered as a reference. The mean absolute difference (MAD) between calculated range of motion of joint angles was 5.00°, 5.02°, 5.26°, and 3.72° for hip F/E, hip A/A, knee F/E, and ankle D/P flexion angles, respectively. In addition, relative stance, swing, double support phases, and cadence were calculated and validated. The MAD for the relative gait phases (stance, swing, and double support) was 1.7%, and the average cadence error was 0.09 steps/min. The MAD values for RoM and relative gait phases can be considered as clinically acceptable. Therefore, we conclude that the proposed methodology is promising, enabling non-restrictive inertial gait analysis in clinical settings.

Effects of Hallux Valgus Surgery on Balance and Gait in Middle Aged and Older Adults.

Hallux valgus is associated with balance deficits, and has been implicated as an independent risk factor for falls in older adults. However, it is unknown what effect hallux valgus surgery has on static and dynamic (i.e., while walking) balance in older adults. We enrolled 13 middle-aged and older aged adults (mean age 54.3 ± 12.7 years, range 47 to 70) who underwent isolated hallux valgus surgery and followed them for 12 months. Preoperative and postoperative gait and balance performance was assessed using non-invasive body worn sensors with standardized and validated testing protocols. Visual analog scale (VAS) for pain and radiographic angles were also assessed. All subjects reported improvements in pain (VAS mean change -38.3 ± 10.3 mm), and all subjects demonstrated improvements in their hallux valgus angles and first/second intermetatarsal angles (mean change 16.3 ± 8.8°, and 5.5 ± 3.0°, respectively). While standing in full tandem, center of mass (COM) sway was improved upon by 59% at 1 year postoperative (p < .05, paired t-test). While most gait parameters demonstrated little change postoperatively, patients tended to spend less time in double support (p = .08, paired t-test), while gait variability increased by 55% (p = .03, paired t-test) and medial-lateral sway while walking increased by 43% (p = .08, paired t-test) 12 months postoperatively. Balance improved after hallux valgus surgery in our population, particularly when subjects were forced to rely on their operative foot for support (e.g., full tandem). Patients also seemed to walk with greater variability in stride velocity and with greater medial-lateral sway postoperatively, suggesting perhaps increased ambulatory confidence after successful hallux valgus surgery.