Portable Gait Analysis System Research Articles

Threshold-Free Phase Segmentation and Zero Velocity Detection for Gait Analysis Using Foot-Mounted Inertial Sensors

Gait analysis is a prosperous tool for the clinical evaluation and diagnosis. In this article, a portable gait analysis system based on foot-mounted inertial sensors is established. A threshold-free method using a long short-term memory recurrent neural network is constructed to segment four typical gait phases in a gait sequence for the temporal parameters analysis. Segmentation accuracy reaches over 95% across recruited subjects with distinct gait patterns, which is significantly superior when compared with traditional machine learning methods. The zero-velocity indicator is generated successively according to the segmented sequence to accomplish zero velocity update for the spatial parameter calculation. The accuracy of the proposed system is also validated through the OptiTrack in the lab. The comparison result of the stride length shows that the error between the two systems is less than 2%, which demonstrates that our system can satisfy the demand in the clinical.

The test-retest reliability of gait kinematic data measured using a portable gait analysis system in healthy adults

The test-retest reliability of gait kinematic data measured using a portable gait analysis system in healthy adults

Portable Gait Analysis System with an Integration of Kinect sensor and Inertial Measurement Units

Clinical gait analysis is used for diagnosing, assessing, and for monitoring a patient by analyzing their kinetics, kinematics and electromyography while walking. Traditionally, gait analysis is performed in a formal laboratory environment making use of several high-resolution cameras, either video or infrared. The subject is asked to walk on a force platform or a treadmill with several markers attached to their body, allowing cameras to capture the joint coordinates across time. The space required for such a laboratory is non-trivial and often the associated costs of such an experimental setup is prohibitively expensive. The current work aims to investigate the coupled use of a Microsoft Kinect and Inertial Measurement Units as a portable and cost-efficient gait analysis system. Past studies on assessing gait using either Kinect or Inertial Measurement Units concluded that they achieve medium reliability individually due to some drawbacks related to each sensor. In this study, we propose that a combined system is efficient in detecting different phases of human gait, and the combination of sensors complement each other by overcoming the individual sensor drawbacks. Preliminary findings indicate that the IMU sensors are efficient in providing gait kinematics such as step length, stride length, velocity, cadence, etc., whereas the Kinect sensor helps in studying the gait asymmetries by comparing the right and left joint, such as hips, knees, and ankle.

Gait-Based Machine Learning for Classifying Patients with Different Types of Mild Cognitive Impairment.

Mild cognitive impairment (MCI) may be caused by Alzheimer's disease, Parkinson's disease (PD), cerebrovascular accident, nutritional or metabolic disorders, or mental disorders. It is important to determine the cause and treatment of dementia as early as possible because dementia may appear in remission. Decline in MCI cognitive function may affect a patient's walking performance. Therefore, all participants in this study participated in an experiment using a portable gait analysis system to perform walk, time up and go, and jump tests. The collected gait parameters are used in a machine learning classification model based on a support vector machine (SVM) and principal component analysis (PCA). The aim of the study is to predict different types of MCI patients based on gait information. It is shown that the machine learning classification model can predict different types of MCI patients. Specifically, the PCA-SVM model demonstrated better classification performance with 91.67% accuracy and 0.9714 area under the receiver operating characteristic curve (ROC AUC) using the polynomial kernel function in classifying PD-MCI and non-PD-MCI patients.

Altered rodent gait characteristics after ~35 days in orbit aboard the International Space Station

The long-term adaptations to microgravity and other spaceflight challenges within the confines of a spacecraft, and readaptations to weight-bearing upon reaching a destination, are unclear. While post-flight gait change in astronauts have been well documented and reflect multi-system deficits, no data from rodents have been collected. Thus, the purpose of this study was to evaluate gait changes in response to spaceflight. A prospective collection of gait data was collected on 3 groups of mice: those who spent~35 days in orbit (FLIGHT) aboard the International Space Station (ISS); a ground-based control with the same habitat conditions as ISS (Ground Control; GC); and a vivarium control with typical rodent housing conditions (VIV). Pre-flight and post-flight gait measurements were conducted utilizing an optimized and portable gait analysis system (DigiGait, Mouse Specifics, Inc). The total data acquisition time for gait patterns of FLIGHT and control mice was 1.5–5 min/mouse, allowing all 20 mice per group to be assessed in less than an hour. Patterns of longitudinal gait changes were observed in the hind limbs and the forelimbs of the FLIGHT mice after ~35 days in orbit; few differences were observed in gait characteristics within the GC and VIV controls from the initial to the final gait assessment, and between groups. For FLIGHT mice, 12 out of 18 of the evaluated gait characteristics in the hind limbs were significantly changed, including: stride width variability; stride length and variance; stride, swing, and stance duration; paw angle and area at peak stance; and step angle, among others. Gait characteristics that decreased included stride frequency, and others. Moreover, numerous forelimb gait characteristics in the FLIGHT mice were changed at post-flight measures relative to pre-flight. This rapid DigiGait gait measurement tool and customized spaceflight protocol is useful for providing preliminary insight into how spaceflight could affect multiple systems in rodents in which deficits are reflected by altered gait characteristics.

Reliability of joint angle during sit-to-stand movements in persons with stroke using portable gait analysis system based wearable sensors

Reliability of joint angle during sit-to-stand movements in persons with stroke using portable gait analysis system based wearable sensors

Criterion-related validity of self-report walking time from the EPIC questionnaire in older adults

ABSTRACTTools for measuring walking time make use of objective and subjective methods. One subjective approach is to administer physical activity questionnaires (PAQ), mainly because they are inexpensive and easy to give to large groups. The European Prospective Investigation into Cancer and Nutrition (EPIC) study has a brief PAQ (EPIC-PAQ) and includes one question referencing walking time. The objective of this study was to assess the validity of the question about time spent walking included in the EPIC-PAQ.The sample included 200 older adults (113 women). To assess daily walking time, participants responded to the EPIC-PAQ in an interview and wore a portable gait analysis system and physical activity monitor for 48 consecutive hours in free-living condition.Results indicated that the mean of bias between the EPIC-PAQ and objetive measurement was −64.6 min/day. Also, the correlation was low compared to an objective measurement (rho = 0.196) and was positively correlated with the time spent at speeds below 2.5 mph but the correlation was low (slow walking rho = 0.154 and pace walking rho = 0.163).The EPIC-PAQ shows low correlations with the objective measurement of walking time, that suggests it may be inaccurate and affecting the estimate of the EPIC-PAQ’s PA energy expenditure in this age group.

Clinical gait evaluation of patients with knee osteoarthritis

Knee osteoarthritis (KOA) is the most common osteoarthritis in lower limbs, and gait measurement is important to evaluate walking function of KOA patients before and after treatment. The third generation Intelligent Device for Energy Expenditure and Activity (IDEEA3) is a portable gait analysis system to evaluate gaits. This study is to evaluate the accuracy and reliability of IDEEA3 for gait measurement of KOA patients. Meanwhile, gait differences between KOA patients and healthy subjects are examined. Twelve healthy volunteers were recruited for measurement comparison of gait cycle (GC), cadence, step length, velocity and step counts between a motion analysis system and a high-speed camera (GoPro Hero3). Twenty-three KOA patients were recruited for measurement comparison of former five parameters between GoPro Hero3 and IDEEA3. Paired t-test, Concordance Correlation Coefficient (CCC) and Intraclass Correlation Coefficient (ICC) were used for data analysis. All p-values of paired t-tests for GC, cadence, step length and velocity were greater than 0.05 while all CCC and ICC results were above 0.95. The measurements of GC, cadence, step length, velocity and step counts by motion analysis system are highly consistent with the measurements by GoPro Hero3. The measurements of former parameters by GoPro Hero3 are not statistically different from the measurements by IDEEA3. IDEEA3 can be effectively used for the measurement of GC, cadence, step length, velocity and step counts in KOA patients. The KOA patients walk with longer GC, lower cadence, shorter step length and slower speed compared with healthy subjects in natural speed with flat shoes.

Reliabilitätsstudie zum Ganganalysesystem RehaWatch / Reliability of the novel gait analysis system RehaWatch

Quantitative gait analysis plays an important role in neurological and orthopedic rehabilitation regarding the evaluation of rehabilitation progress. However, most of the currently available gait analysis systems share the disadvantage of being expensive, time-consuming, and complex. A promising alternative is the portable gait analysis system RehaWatch. It is based on inertial sensors that allow the quantitative measurement of the important kinemetric variables acceleration and angular velocity. The associated software analyzes the sensor signals and calculates temporal (e.g., stride duration, gait phases) and spatial (e.g., stride length, foot angle) parameters on this basis. The aim of this study was to investigate the intraobserver reliability of RehaWatch. A total of 44 healthy subjects (age: 27.7±4.2 years) were included in the study. Each participant underwent three measurements (walking distance: 20 m) for each of the three sessions with a time interval of 48 h in-between. Variance analysis (General Linear Model) revealed no significant differences between gait parameters at different measuring points. ICCs (Average Measure Intraclass Correlations) were between 0.691 and 0.959. In addition to the results of the variance and correlation analysis the Bland-Altman plots suggest high reliability.

Concurrent validity of SMTEC ® footswitches system for the measurement of temporal gait parameters

The GAITRite ® system is a validated portable gait analysis system that allows simple objective gait measurements. The limited length of the active area of the GAITRite ® system may be a limitation in obtaining reliable measures of stride-to-stride variability. In contrast, the SMTEC ® footswitches system provides a continuous measurement of temporal step parameters for a long distance and a long period (around 24 h). The aim of the study was to examine the concurrent validity of the SMTEC ® footswitches system with the GAITRite ® system for the measurement of temporal steps parameters. Step, stride, swing and stance time were simultaneously recorded using SMTEC ® and GAITRite ® systems while walking at normal, slow and fast self-selected walking speed among 13 healthy young adults. The level of agreement between both systems was high as for the stride time with intra-class correlation coefficients (ICC) between 0.95 and 0.99 ( P < 0.001) and repeatability coefficients (RC) between 1.1% and 1.5% of mean values, whereas the lowest level of agreement was shown at fast self-selected walking speed and for stance time (ICC = 0.52 with P < 0.001 and RC = 4.9%). Furthermore, the measurement of individual footstep data was excellent with an agreement ranging between −0.04 and 0.04 s (Pitman's test of difference in variance: r = −0.009, P = 0.772). The present results suggest that the SMTEC ® footswitches system provides a valid and reliable measurement of temporal gait parameters in healthy young adults.

A practical gait analysis system using gyroscopes

This study investigated the possibility of using uni-axial gyroscopes to develop a simple portable gait analysis system. Gyroscopes were attached on the skin surface of the shank and thigh segments and the angular velocity for each segment was recorded in each segment. Segment inclinations and knee angle were derived from segment angular velocities. The angular signals from a motion analysis system were used to evaluate the angular velocities and the derived signals from the gyroscopes. There was a good correlation between these signals. When performing a turn the signals of segment inclination and knee angle drifted. Two methods were used to solve this: automatically resetting the system to re-initialise the angle in each gait cycle, and high-pass filtering. They both successfully corrected this drift. A single gyroscope on the shank segment could provide information on segment inclination range, cadence, number of steps, and an estimation of stride length and walking speed.

Development of a portable gait analysis system

Development of a portable gait analysis system