Inertial Sensor-based Gait Analysis Research Articles

Validity of an inertial sensor-based system for the assessment of spatio-temporal parameters in people with multiple sclerosis.

Gait variability in people with multiple sclerosis (PwMS) reflects disease progression or may be used to evaluate treatment response. To date, marker-based camera systems are considered as gold standard to analyze gait impairment in PwMS. These systems might provide reliable data but are limited to a restricted laboratory setting and require knowledge, time, and cost to correctly interpret gait parameters. Inertial mobile sensors might be a user-friendly, environment- and examiner-independent alternative. The purpose of this study was to evaluate the validity of an inertial sensor-based gait analysis system in PwMS compared to a marker-based camera system. A sample N = 39 PwMS and N = 19 healthy participants were requested to repeatedly walk a defined distance at three different self-selected walking speeds (normal, fast, slow). To measure spatio-temporal gait parameters (i.e., walking speed, stride time, stride length, the duration of the stance and swing phase as well as max toe clearance), an inertial sensor system as well as a marker-based camera system were used simultaneously. All gait parameters highly correlated between both systems (r > 0.84) with low errors. No bias was detected for stride time. Stance time was marginally overestimated (bias = -0.02 ± 0.03 s) and gait speed (bias = 0.03 ± 0.05 m/s), swing time (bias = 0.02 ± 0.02 s), stride length (0.04 ± 0.06 m), and max toe clearance (bias = 1.88 ± 2.35 cm) were slightly underestimated by the inertial sensors. The inertial sensor-based system captured appropriately all examined gait parameters in comparison to a gold standard marker-based camera system. Stride time presented an excellent agreement. Furthermore, stride length and velocity presented also low errors. Whereas for stance and swing time, marginally worse results were observed.

Validation of wearable inertial sensor-based gait analysis system for measurement of spatiotemporal parameters and lower extremity joint kinematics in sagittal plane.

Wearable inertial sensor-based motion analysis systems are promising alternatives to standard camera-based motion capture systems for the measurement of gait parameters and joint kinematics. These wearable sensors, unlike camera-based gold standard systems, find usefulness in outdoor natural environment along with confined indoor laboratory-based environment due to miniature size and wireless data transmission. This study reports validation of our developed (i-Sens) wearable motion analysis system against standard motion capture system. Gait analysis was performed at self-selected speed on non-disabled volunteers in indoor (n = 15) and outdoor (n = 8) environments. Two i-Sens units were placed at the level of knee and hip along with passive markers (for indoor study only) for simultaneous 3D motion capture using a motion capture system. Mean absolute percentage error (MAPE) was computed for spatiotemporal parameters from the i-Sens system versus the motion capture system as a true reference. Mean and standard deviation of kinematic data for a gait cycle were plotted for both systems against normative data. Joint kinematics data were analyzed to compute the root mean squared error (RMSE) and Pearson's correlation coefficient. Kinematic plots indicate a high degree of accuracy of the i-Sens system with the reference system. Excellent positive correlation was observed between the two systems in terms of hip and knee joint angles (Indoor: hip 3.98° ± 1.03°, knee 6.48° ± 1.91°, Outdoor: hip 3.94° ± 0.78°, knee 5.82° ± 0.99°) with low RMSE. Reliability characteristics (defined using standard statistical thresholds of MAPE) of stride length, cadence, walking speed in both outdoor and indoor environment were well within the "Good" category. The i-Sens system has emerged as a potentially cost-effective, valid, accurate, and reliable alternative to expensive, standard motion capture systems for gait analysis. Further clinical trials using the i-Sens system are warranted on participants across different age groups.

An Inertial Sensor-Based Gait Analysis Pipeline for the Assessment of Real-World Stair Ambulation Parameters

An Inertial Sensor-Based Gait Analysis Pipeline for the Assessment of Real-World Stair Ambulation Parameters

An Inertial Sensor-Based Gait Analysis Pipeline for the Assessment of Real-World Stair Ambulation Parameters.

Climbing stairs is a fundamental part of daily life, adding additional demands on the postural control system compared to level walking. Although real-world gait analysis studies likely contain stair ambulation sequences, algorithms dedicated to the analysis of such activities are still missing. Therefore, we propose a new gait analysis pipeline for foot-worn inertial sensors, which can segment, parametrize, and classify strides from continuous gait sequences that include level walking, stair ascending, and stair descending. For segmentation, an existing approach based on the hidden Markov model and a feature-based gait event detection were extended, reaching an average segmentation F1 score of 98.5% and gait event timing errors below ±10 for all conditions. Stride types were classified with an accuracy of 98.2% using spatial features derived from a Kalman filter-based trajectory reconstruction. The evaluation was performed on a dataset of 20 healthy participants walking on three different staircases at different speeds. The entire pipeline was additionally validated end-to-end on an independent dataset of 13 Parkinson’s disease patients. The presented work aims to extend real-world gait analysis by including stair ambulation parameters in order to gain new insights into mobility impairments that can be linked to clinically relevant conditions such as a patient’s fall risk and disease state or progression.

Ambulatory Human Gait Phase Detection Using Wearable Inertial Sensors and Hidden Markov Model.

Gait analysis, as a common inspection method for human gait, can provide a series of kinematics, dynamics and other parameters through instrumental measurement. In recent years, gait analysis has been gradually applied to the diagnosis of diseases, the evaluation of orthopedic surgery and rehabilitation progress, especially, gait phase abnormality can be used as a clinical diagnostic indicator of Alzheimer Disease and Parkinson Disease, which usually show varying degrees of gait phase abnormality. This research proposed an inertial sensor based gait analysis method. Smoothed and filtered angular velocity signal was chosen as the input data of the 15-dimensional temporal characteristic feature. Hidden Markov Model and parameter adaptive model are used to segment gait phases. Experimental results show that the proposed model based on HMM and parameter adaptation achieves good recognition rate in gait phases segmentation compared to other classification models, and the recognition results of gait phase are consistent with ground truth. The proposed wearable device used for data collection can be embedded on the shoe, which can not only collect patients’ gait data stably and reliably, ensuring the integrity and objectivity of gait data, but also collect data in daily scene and ambulatory outdoor environment.

Gait asymmetry in glucocerebrosidase mutation carriers with Parkinson's disease.

BackgroundGBA mutation carriers with PD (PD-GBA) are at higher risk of cognitive decline, but there is limited data regarding whether there are differences in gait dysfunction between GBA mutation and non-mutation carriers with PD.Objectives/MethodsThe primary aim of this study was to use quantitative inertial sensor-based gait analysis to compare gait asymmetry in 17 PD-GBA subjects, 17 non-mutation carriers with PD, and 15 healthy control subjects using parameters that had gait laterality and were markers of bradykinesia, in particular arm swing velocity and arm swing range of motion and stride length.ResultsArm swing velocity was more symmetric in PD-GBA subjects vs. non-mutation carriers in the OFF state (12.5 +/- 8.3 vs. 22.9 +/- 11.8%, respectively, p = 0.018). In the ON-medication state, non-mutation carriers with PD, but not PD-GBA subjects, exhibited arm swing velocity (16.8 +/- 8.6 vs. 22.9 +/- 11.8%, p = 0.006) and arm range of motion (26.7 +/- 16.3 vs. 33.4 +/- 18.6%, p = 0.02) that was more asymmetric compared with the OFF-medication state.ConclusionsIn the OFF medication state, arm swing velocity asymmetry may be a useful parameter in helping to distinguish GBA mutation carriers with PD from non-mutation carriers.

Development of a Wearable Inertial Sensor-based Gait Analysis Device Using Machine Learning Algorithms -Validity of the Temporal Gait Parameter in Healthy Young Adults

Development of a Wearable Inertial Sensor-based Gait Analysis Device Using Machine Learning Algorithms -Validity of the Temporal Gait Parameter in Healthy Young Adults

Deep Learning for Fall Risk Assessment With Inertial Sensors: Utilizing Domain Knowledge in Spatio-Temporal Gait Parameters.

Fall risk assessment is essential to predict and prevent falls in geriatric populations, especially patients with life-long conditions like neurological disorders. Inertial sensor-based pervasive gait analysis systems have become viable means to facilitate continuous fall risk assessment in non-hospital settings. However, a gait analysis system is not sufficient to detect the characteristics leading to increased fall risk, and powerful inference models are required to detect the underlying factors specific to fall risk. Machine learning models and especially the recently proposed deep learning methods offer the needed predictive power. Deep neural networks have the potential to produce models that can operate directly on the raw data, thus alleviating the need for feature engineering. However, the domain knowledge inherent in the well-established spatio-temporal gait parameters are still valuable to help a model achieve high inference accuracies. In this study, we explore deep learning methods, specifically long short-term memory (LSTM) neural networks, for the problem of fall risk assessment. We utilize sequences of spatio-temporal gait parameters extracted by an inertial sensor-based gait analysis system as input features. To quantify the performance of the proposed approach, we compare it with more traditional machine learning methods. The proposed LSTM model, trained with a gait dataset collected from 60 neurological disorder patients, achieves a superior classification accuracy of 92.1% on a separate test dataset collected from 16 patients. This study serves as one of the first attempts to employ deep learning approaches in this domain and the results demonstrate their potential.

Inertial Sensor-Based Robust Gait Analysis in Non-Hospital Settings for Neurological Disorders.

The gold standards for gait analysis are instrumented walkways and marker-based motion capture systems, which require costly infrastructure and are only available in hospitals and specialized gait clinics. Even though the completeness and the accuracy of these systems are unquestionable, a mobile and pervasive gait analysis alternative suitable for non-hospital settings is a clinical necessity. Using inertial sensors for gait analysis has been well explored in the literature with promising results. However, the majority of the existing work does not consider realistic conditions where data collection and sensor placement imperfections are imminent. Moreover, some of the underlying assumptions of the existing work are not compatible with pathological gait, decreasing the accuracy. To overcome these challenges, we propose a foot-mounted inertial sensor-based gait analysis system that extends the well-established zero-velocity update and Kalman filtering methodology. Our system copes with various cases of data collection difficulties and relaxes some of the assumptions invalid for pathological gait (e.g., the assumption of observing a heel strike during a gait cycle). The system is able to extract a rich set of standard gait metrics, including stride length, cadence, cycle time, stance time, swing time, stance ratio, speed, maximum/minimum clearance and turning rate. We validated the spatio-temporal accuracy of the proposed system by comparing the stride length and swing time output with an IR depth-camera-based reference system on a dataset comprised of 22 subjects. Furthermore, to highlight the clinical applicability of the system, we present a clinical discussion of the extracted metrics on a disjoint dataset of 17 subjects with various neurological conditions.

Examination of the reliability of an inertial sensor-based gait analysis system

Gait analysis is an important and useful part of the daily therapeutic routine. InvestiGAIT, an inertial sensor-based system, was developed for using in different research projects with a changing number and position of sensors and because commercial systems do not capture the motion of the upper body. The current study is designed to evaluate the reliability of InvestiGAIT consisting of four off-the-shelf inertial sensors and in-house capturing and analysis software. Besides the determination of standard gait parameters, the motion of the upper body (pelvis and spine) can be investigated. Kinematic data of 25 healthy individuals (age: 25.6±3.3 years) were collected using a test-retest design with 1 week between measurement sessions. We calculated different parameters for absolute [e.g. limits of agreement (LoA)] and relative reliability [intraclass correlation coefficients (ICC)]. Our results show excellent ICC values for most of the gait parameters. Midswing height (MH), height difference (HD) of initial contact (IC) and terminal contact (TC) and stride length (SL) are the gait parameters, which did not exhibit acceptable values representing absolute reliability. Moreover, the parameters derived from the motion of the upper body (pelvis and spine) show excellent ICC values or high correlations. Our results indicate that InvestiGAIT is suitable for reliable measurement of almost all the considered gait parameters.

Mobile inertial sensor based gait analysis: Validity and reliability of spatiotemporal gait characteristics in healthy seniors

Gait analysis is commonly used to identify gait changes and fall risk in clinical populations and seniors. Body-worn inertial sensor based gait analyses provide a feasible alternative to optometric and pressure based measurements of spatiotemporal gait characteristics. We assessed validity and relative and absolute reliability of a body-worn inertial sensor system (RehaGait®) for measuring spatiotemporal gait characteristics compared to a standard stationary treadmill (Zebris®). Spatiotemporal gait parameters (walking speed, stride length, cadence and stride time) were collected for 24 healthy seniors (age: 75.3±6.7 years) tested on 2 days (1 week apart) simultaneously using the sensor based system and instrumented treadmill. Each participant completed walking tests (200 strides) at different walking speeds and slopes. The difference between the RehaGait® system and the treadmill was trivial (Cohen’s d<0.2) except for speed and stride length at slow speed (Cohen’s d, 0.35 and 0.49, respectively). Intraclass correlation coefficients (ICC) were excellent for temporal gait characteristics (cadence and stride time; ICC: 0.99–1.00) and moderate for stride length (ICC: 0.73–0.89). Both devices had excellent day-to-day reliability for all gait parameters (ICC: 0.82–0.99) except for stride length at slow speed (ICC: 0.74). The RehaGait® is a valid and reliable tool for assessing spatiotemporal gait parameters for treadmill walking at different speeds and slopes.

Disability and Fatigue Can Be Objectively Measured in Multiple Sclerosis.

BackgroundThe available clinical outcome measures of disability in multiple sclerosis are not adequately responsive or sensitive.ObjectiveTo investigate the feasibility of inertial sensor-based gait analysis in multiple sclerosis.MethodsA cross-sectional study of 80 multiple sclerosis patients and 50 healthy controls was performed. Lower-limb kinematics was evaluated by using a commercially available magnetic inertial measurement unit system. Mean and standard deviation of range of motion (mROM, sROM) for each joint of lower limbs were calculated in one minute walking test. A motor performance index (E) defined as the sum of sROMs was proposed.ResultsWe established two novel observer-independent measures of disability. Hip mROM was extremely sensitive in measuring lower limb motor impairment, being correlated with muscle strength and also altered in patients without clinically detectable disability. On the other hand, E index discriminated patients according to disability, being altered only in patients with moderate and severe disability, regardless of walking speed. It was strongly correlated with fatigue and patient-perceived health status.ConclusionsInertial sensor-based gait analysis is feasible and can detect clinical and subclinical disability in multiple sclerosis.

Assessment of physical function following total hip arthroplasty: Inertial sensor based gait analysis is supplementary to patient-reported outcome measures

BackgroundFunctional outcome assessment after total hip arthroplasty often involves subjective patient-reported outcome measures whereas analysis of gait is more objective. The study's aims were to compare subjective and objective functional outcomes after total hip arthroplasty between patients with low and high self-reported levels of pre-operative physical function. MethodsPatients undergoing total hip arthroplasty (n=36; m/f=18/18; mean age=63.9; SD=9.8years; BMI=26.3; SD=3.5) were divided into a low and high function subgroup, and prospective measures of WOMAC (Western Ontario and McMaster Universities Osteoarthritis Index) function score and gait were compared at baseline and 3 and 12months post-operatively. FindingsWOMAC function scores significantly improved in both low and high function subgroups at 3months post-operatively whereas gait parameters only improved in patients with a low pre-operative function. Between 3 and 12months post-operatively, WOMAC function scores had not significantly further improved whereas several gait parameters significantly improved in the low function group. WOMAC function scores and gait parameters were only moderately correlated (Spearman's r=0.33–0.51). InterpretationIn a cohort of patients undergoing total hip arthroplasty, pre-operative differences in mean WOMAC function scores and gait parameters between low and high function subgroups disappeared by 3months post-operatively. Gait parameters only improved significantly during the first 3 post-operative months in patients with a low pre-operative function, highlighting the importance of investigating relative changes rather than the absolute changes and the need to consider patients with high and low functions separately.

Experimental evaluation of accuracy and repeatability of a novel body-to-sensor calibration procedure for inertial sensor-based gait analysis

This paper describes a novel functional body-to-sensor calibration procedure for inertial sensor-based gait analysis. The procedure is designed to be easily and autonomously performable by the subject, without the need for precise sensor positioning, or the performance of specific movements. The procedure consists in measuring the vertical axis during two static positions, and is not affected by magnetic field distortion. The procedure has been validated on ten healthy subjects using an optoelectronic system to measure the actual body-to-sensor rotation matrices.The effects of different sensor positions on each body segment, or different levels of subject inclination during the second static position of the procedure, resulted unnoticeable. The procedure showed accuracy and repeatability values less than 4° for each angle except for the ankle int–external rotation (9.7°, 7.2°). The results demonstrate the validity of the procedure, since they are comparable with those reported for the most-adopted protocols in gait analysis.

Movement Symmetry Patterns During Lungeing in Trot on Hard and Soft Surface Differ Between Sound and Mildly Forelimb Lame Horses

AimsLungeing on hard and soft surfaces is crucial to clinical lameness and prepurchase examinations. Here we 1) quantify movement symmetry (MS) in sound horses trotting on hard and soft surfaces, and 2) compare MS patterns for different rein and surface combinations between sound and mildly forelimb lame horses.MethodsTwenty‐three riding horses were equipped with an inertial sensor based gait analysis system and assessed in‐hand on the straight and during lungeing (10 m diameter circle), both on hard and soft surfaces. Assessment of rein (left/right) was performed in a randomised order. Seven published MS parameters (3 poll, 4 pelvis) were quantified from an average of 38 strides per condition. Horses were subdivided into 3 groups: control (9 horses), left (5) and right (9) forelimb lame. Statistical analysis was performed using paired samples t test, ANOVA and post hoc comparisons.ResultsFor control horses, only one MS measure was significantly different between the surfaces; Symmetry Index (P = 0.0122, increased asymmetry on hard ground). When comparing left and right forelimb lame horses, increased head movement asymmetry was found with the affected limb on the inside of the circle on both surfaces (P values between P = 0.0006 and P = 0.0481); circle and lameness induced asymmetry adding up. No differences in pelvic MS were identified between sound and mildly forelimb lame horses.ConclusionsSound horses show similar amounts of movement asymmetry during lungeing on hard and soft surfaces. Mildly forelimb lame horses show characteristic patterns of increased asymmetry in particular with the affected limb on the inside of the circle.Practical significanceThe observed differences between sound and mildly forelimb lame horses will contribute to higher specificity in identification of mildly lame horses based on objective gait analysis. It is recommended to include lungeing into objective gait assessments.AcknowledgementsWe are grateful to the owners of the horses that participated.Ethical animal researchThis project was granted ethical approval by the RVC Ethics and Welfare Committee as part of Hazel Mitchell's and Charlotte Jennings' final year research project and conducted with owners' informed consent. Sources of funding: RVC. Competing interests: None.

Inertial sensor based gait analysis: a clinical application in patients with osteoarthritis

Inertial sensor based gait analysis: a clinical application in patients with osteoarthritis