Gait event detection using inertial measurement units in people with transfemoral amputation: a comparative study

View-independent gait events detection using CNN-transformer hybrid network

Accurate gait detection is crucial in utilizing the ample health information embedded in it. Vision-based approaches for gait detection have emerged as an alternative to the exacting sensor-based approaches, but their application has been rather limited due to complicated feature engineering processes and heavy reliance on lateral views. Thus, this study aimed to find a simple vision-based approach that is view-independent and accurate. A total of 22 participants performed six different actions representing standard and peculiar gaits, and the videos acquired from these actions were used as the input of the deep learning networks. Four networks, including a 2D convolutional neural network and an attention-based deep learning network, were trained with standard gaits, and their detection performance for both standard and peculiar gaits was assessed using measures including F1-scores. While all networks achieved remarkable detection performance, the CNN-Transformer network achieved the best performance for both standard and peculiar gaits. Little deviation by the speed of actions or view angles was found. The study is expected to contribute to the wider application of vision-based approaches in gait detection and gait-based health monitoring both at home and in clinical settings.

Gait Alteration in Individual with Limb Loss: The Role of Inertial Sensors

Amputation has a big impact on the functioning of patients, with negative effects on locomotion and dexterity. In this context, inertial measurement units represent a useful tool in clinical practice for motion analysis, and in the development of personalized aids to improve a patient's function. To date, there is still a gap of knowledge in the scientific literature on the application of inertial sensors in amputee patients. Thus, the aim of this narrative review was to collect the current knowledge on this topic and stimulate the publication of further research. Pubmed, Embase, Scopus, and Cochrane Library publications were screened until November 2022 to identify eligible studies. Out of 444 results, we selected 26 articles focused on movement analysis, risk of falls, energy expenditure, and the development of sensor-integrated prostheses. The results showed that the use of inertial sensors has the potential to improve the quality of life of patients with prostheses, increasing patient safety through the detection of gait alteration; enhancing the socio-occupational reintegration through the development of highly technologic and personalized prosthesis; and by monitoring the patients during daily life to plan a tailored rehabilitation program.

Classifying Changes in Amputee Gait following Physiotherapy Using Machine Learning and Continuous Inertial Sensor Signals

Wearable sensors allow for the objective analysis of gait and motion both in and outside the clinical setting. However, it remains a challenge to apply such systems to highly diverse patient populations, including individuals with lower-limb amputations (LLA) that present with unique gait deviations and rehabilitation goals. This paper presents the development of a novel method using continuous gyroscope data from a single inertial sensor for person-specific classification of gait changes from a physiotherapist-led gait training session. Gyroscope data at the thigh were collected using a wearable gait analysis system for five LLA before, during, and after completing a gait training session. Data from able-bodied participants receiving no intervention were also collected. Models using dynamic time warping (DTW) and Euclidean distance in combination with the nearest neighbor classifier were applied to the gyroscope data to classify the pre- and post-training gait. The model achieved an accuracy of 98.65% ± 0.69 (Euclidean) and 98.98% ± 0.83 (DTW) on pre-training and 95.45% ± 6.20 (Euclidean) and 94.18% ± 5.77 (DTW) on post-training data across the participants whose gait changed significantly during their session. This study provides preliminary evidence that continuous angular velocity data from a single gyroscope could be used to assess changes in amputee gait. This supports future research and the development of wearable gait analysis and feedback systems that are adaptable to a broad range of mobility impairments.

A pilot case series for concurrent validation of inertial measurement units to motion capture in individuals who use unilateral lower-limb prostheses

Introduction

Inertial measurement units (IMUs) may be viable options to collect gait data in clinics. This study compared IMU to motion capture data in individuals who use unilateral lower-limb prostheses.

Methods

Participants walked with lower-body IMUs and reflective markers in a motion analysis space. Sagittal plane hip, knee, and ankle waveforms were extracted for the entire gait cycle. Discrete points of peak flexion, peak extension, and range of motion were extracted from the waveforms. Stance times were also extracted to assess the IMU software's accuracy at detecting gait events. IMU and motion capture-derived data were compared using absolute differences and root mean square error (RMSE).

Results

Five individuals (n = 3 transtibial; n = 2 transfemoral) participated. IMU prosthetic limb data was similar to motion capture (RMSE: waveform ≤4.65°; discrete point ≤9.04°; stance ≤0.03s). However, one transfemoral participant had larger differences at the microprocessor knee joint (RMSE: waveform ≤15.64°; discrete ≤29.21°) from IMU magnetometer interference. Intact limbs tended to have minimal differences between IMU and motion capture data (RMSE: waveform ≤6.33°; discrete ≤9.87°; stance ≤0.04s).

Conclusion

Findings from this pilot study suggest IMUs have the potential to collect data similar to motion capture systems in sagittal plane kinematics and stance time.

Rules-Based Real-Time Gait Event Detection Algorithm for Lower-Limb Prosthesis Users during Level-Ground and Ramp Walking

Real-time gait event detection (GED) using inertial sensors is important for applications such as remote gait assessments, intelligent assistive devices including microprocessor-based prostheses or exoskeletons, and gait training systems. GED algorithms using acceleration and/or angular velocity signals achieve reasonable performance; however, most are not suited for real-time applications involving clinical populations walking in free-living environments. The aim of this study was to develop and evaluate a real-time rules-based GED algorithm with low latency and high accuracy and sensitivity across different walking states and participant groups. The algorithm was evaluated using gait data collected from seven able-bodied (AB) and seven lower-limb prosthesis user (LLPU) participants for three walking states (level-ground walking (LGW), ramp ascent (RA), ramp descent (RD)). The performance (sensitivity and temporal error) was compared to a validated motion capture system. The overall sensitivity was 98.87% for AB and 97.05% and 93.51% for LLPU intact and prosthetic sides, respectively, across all walking states (LGW, RA, RD). The overall temporal error (in milliseconds) for both FS and FO was 10 (0, 20) for AB and 10 (0, 25) and 10 (0, 20) for the LLPU intact and prosthetic sides, respectively, across all walking states. Finally, the overall error (as a percentage of gait cycle) was 0.96 (0, 1.92) for AB and 0.83 (0, 2.08) and 0.83 (0, 1.66) for the LLPU intact and prosthetic sides, respectively, across all walking states. Compared to other studies and algorithms, the herein-developed algorithm concurrently achieves high sensitivity and low temporal error with near real-time detection of gait in both typical and clinical populations walking over a variety of terrains.

Vestibular Rehabilitation Improves Gait Quality and Activities of Daily Living in People with Severe Traumatic Brain Injury: A Randomized Clinical Trial

Neurorehabilitation research in patients with traumatic brain injury (TBI) showed how vestibular rehabilitation (VR) treatments positively affect concussion-related symptoms, but no studies have been carried out in patients with severe TBI (sTBI) during post-acute intensive neurorehabilitation. We aimed at testing this effect by combining sensor-based gait analysis and clinical scales assessment. We hypothesized that integrating VR in post-acute neurorehabilitation training might improve gait quality and activity of daily living (ADL) in sTBI patients. A two-arm, single-blind randomized controlled trial with 8 weeks of follow-up was performed including thirty sTBI inpatients that underwent an 8-week rehabilitation program including either a VR or a conventional program. Gait quality parameters were obtained using body-mounted magneto-inertial sensors during instrumented linear and curvilinear walking tests. A 4X2 mixed model ANOVA was used to investigate session−group interactions and main effects. Patients undergoing VR exhibited improvements in ADL, showing early improvements in clinical scores. Sensor-based assessment of curvilinear pathways highlighted significant VR-related improvements in gait smoothness over time (p < 0.05), whereas both treatments exhibited distinct improvements in gait quality. Integrating VR in conventional neurorehabilitation is a suitable strategy to improve gait smoothness and ADL in sTBI patients. Instrumented protocols are further promoted as an additional measure to quantify the efficacy of neurorehabilitation treatments.

Estimation of Gait Parameters for Transfemoral Amputees Using Lower Limb Kinematics and Deterministic Algorithms

Accurate estimation of gait parameters depends on the prediction of key gait events of heel strike (HS) and toe-off (TO). Kinematics-based gait event estimation has shown potential in this regard, particularly using leg and foot velocity signals and gyroscopic sensors. However, existing algorithms demonstrate a varying degree of accuracy for different populations. Moreover, the literature lacks evidence for their validity for the amputee population. The purpose of this study is to evaluate this paradigm to predict TO and HS instants and to propose a new algorithm for gait parameter estimation for the amputee population. An open data set containing marker data of 12 subjects with unilateral transfemoral amputation during treadmill walking was used, containing around 3400 gait cycles. Five deterministic algorithms detecting the landmarks (maxima, minima, and zero-crossings [ZC]) in the foot, shank, and thigh angular velocity data indicating HS and TO events were implemented and their results compared against the reference data. Two algorithms based on foot and shank velocity minima performed exceptionally well for the HS prediction, with median accuracy in the range of 6–13 ms. However, both these algorithms produced inferior accuracy for the TO event with consistent early prediction. The peak in the thigh velocity produced the best result for the TO prediction with <25 ms median error. By combining the HS prediction using shank velocity and TO prediction from the thigh velocity, the algorithm produced the best results for temporal gait parameters (step, stride times, stance, and double support timings) with a median error of less than 25 ms. In conclusion, combined shank and thigh velocity-based prediction leads to improved gait parameter estimation than traditional algorithms for the amputee population.

Detection of Movement Events of Long-Track Speed Skating Using Wearable Inertial Sensors

Inertial measurement units (IMUs) have been used increasingly to characterize long-track speed skating. We aimed to estimate the accuracy of IMUs for use in phase identification of long-track speed skating. Twelve healthy competitive athletes on a university long-track speed skating team participated in this study. Foot pressure, acceleration and knee joint angle were recorded during a 1000-m speed skating trial using the foot pressure system and IMUs. The foot contact and foot-off timing were identified using three methods (kinetic, acceleration and integrated detection) and the stance time was also calculated. Kinetic detection was used as the gold standard measure. Repeated analysis of variance, intra-class coefficients (ICCs) and Bland-Altman plots were used to estimate the extent of agreement between the detection methods. The stance time computed using the acceleration and integrated detection methods did not differ by more than 3.6% from the gold standard measure. The ICCs ranged between 0.657 and 0.927 for the acceleration detection method and 0.700 and 0.948 for the integrated detection method. The limits of agreement were between 90.1% and 96.1% for the average stance time. Phase identification using acceleration and integrated detection methods is valid for evaluating the kinematic characteristics during long-track speed skating.

Estimation of 3D Body Center of Mass Acceleration and Instantaneous Velocity from a Wearable Inertial Sensor Network in Transfemoral Amputee Gait: A Case Study

The analysis of the body center of mass (BCoM) 3D kinematics provides insights on crucial aspects of locomotion, especially in populations with gait impairment such as people with amputation. In this paper, a wearable framework based on the use of different magneto-inertial measurement unit (MIMU) networks is proposed to obtain both BCoM acceleration and velocity. The proposed framework was validated as a proof of concept in one transfemoral amputee against data from force plates (acceleration) and an optoelectronic system (acceleration and velocity). The impact in terms of estimation accuracy when using a sensor network rather than a single MIMU at trunk level was also investigated. The estimated velocity and acceleration reached a strong agreement (ρ > 0.89) and good accuracy compared to reference data (normalized root mean square error (NRMSE) < 13.7%) in the anteroposterior and vertical directions when using three MIMUs on the trunk and both shanks and in all three directions when adding MIMUs on both thighs (ρ > 0.89, NRMSE ≤ 14.0% in the mediolateral direction). Conversely, only the vertical component of the BCoM kinematics was accurately captured when considering a single MIMU. These results suggest that inertial sensor networks may represent a valid alternative to laboratory-based instruments for 3D BCoM kinematics quantification in lower-limb amputees.