Assessment Methods of Post-stroke Gait: A Scoping Review of Technology-Driven Approaches to Gait Characterization and Analysis

Manual assessment of cylinder rearing behavior is more sensitive than automated gait evaluations in young, male mice post-stroke of the forepaw somatosensory cortex

BACKGROUND

Stroke is a leading cause of long-term adult disability. Behavioral testing with animal stroke models, which offers a way to evaluate the effectiveness of new interventions, currently relies on methods that are time- and labor-intensive. Automated behavioral assessments of locomotion and gait have been proposed as an alternative, but it is currently unknown whether they are sensitive enough to assess behavioral deficits following stroke of the forepaw somatosensory cortex. The purpose of this study was to compare a validated, manually assessed behavioral test, cylinder rearing (a measure of forepaw asymmetry during exploration), with automated behavior tests of locomotion in a rodent photothrombotic stroke model.

METHODS

We induced a focal photothrombotic stroke in young (12-16 week old) male mice over the left forepaw somatosensory cortex, conducted behavioral testing at acute (48 h) and sub-acute (4 weeks) time points post-stroke, and then correlated behavior deficits to histological measures.

RESULTS

Three automated behavioral tests were used in comparison to cylinder rearing: CatWalk (spontaneous gait), DigiGait (forced treadmill locomotion), and open field (a measure of general locomotor activity). Cylinder rearing testing showed significant forepaw asymmetry between stroke and sham groups acutely and sub-acutely after stroke. Catwalk, DigiGait, and open field tests showed no significant differences between groups. When correlating behavior to histological measures of stroke, the presence of secondary thalamic injury (STI) was associated with forepaw asymmetry on cylinder rearing.

CONCLUSIONS

These findings illustrate the need to find alternative automated behavioral measures for mouse photothrombotic stroke of the forepaw somatosensory cortex.

May Patients with Chronic Stroke Benefit from Robotic Gait Training with an End-Effector? A Case-Control Study

Background: Gait and balance alterations in post-stroke patients are one of the most disabling symptoms that can persist in chronic stages of the disease. In this context, rehabilitation has the fundamental role of promoting functional recovery, mitigating gait and balance deficits, and preventing falling risk. Robotic end-effector devices, like the G-EO system (e.g., G-EO system, Reha Technology, Olten, Switzerland), can be a useful device to promote gait recovery in patients with chronic stroke. Materials and Methods: Twelve chronic stroke patients were enrolled and evaluated at baseline (T0) and at post-treatment (T1). These patients received forty sessions of robotic gait training (RGT) with the G-EO system (experimental group, EG), for eight weeks consecutively, in addition to standard rehabilitation therapy. The data of these subjects were compared with those coming from a sample of twelve individuals (control group, CG) matched for clinical and demographic features who underwent the same amount of conventional gait training (CGT), in addition to standard rehabilitation therapy. Results: All patients completed the trial, and none reported any side effects either during or following the training. The EG showed significant improvements in balance (p = 0.012) and gait (p = 0.004) functions measured with the Tinetti Scale (TS) after RGT. Both groups (EG and CG) showed significant improvement in functional independence (FIM, p < 0.001). The Fugl-Meyer Assessment-Lower Extremity (FMA-LE) showed significant improvements in motor function (p = 0.001, p = 0.031) and passive range of motion (p = 0.031) in EG. In EG, gait and balance improvements were influenced by session, age, gender, time since injury (TSI), cadence, and velocity (p < 0.05), while CG showed fewer significant effects, mainly for age, TSI, and session. EG showed significantly greater improvements than CG in balance (p = 0.003) and gait (p = 0.05) based on the TS. Conclusions: RGT with end-effectors, like the G-EO system, can be a valuable complementary treatment in neurorehabilitation, even for chronic stroke patients. Our findings suggest that RGT may improve gait, balance, and lower limb motor functions, enhancing motor control and coordination.

Advancing personalised care in atrial fibrillation and stroke: The potential impact of AI from prevention to rehabilitation

Atrial fibrillation (AF) is a complex condition caused by various underlying pathophysiological disorders and is the most common heart arrhythmia worldwide, affecting 2 % of the European population. This prevalence increases with age, imposing significant financial, economic, and human burdens. In Europe, stroke is the second leading cause of death and the primary cause of disability, with numbers expected to rise due to ageing and improved survival rates. Functional recovery from AF-related stroke is often unsatisfactory, leading to prolonged hospital stays, severe disability, and high mortality. Despite advances in AF and stroke research, the full pathophysiological and management issues between AF and stroke increasingly need innovative approaches such as artificial intelligence (AI) and machine learning (ML). Current risk assessment tools focus on static risk factors, neglecting the dynamic nature of risk influenced by acute illness, ageing, and comorbidities. Incorporating biomarkers and automated ECG analysis could enhance pathophysiological understanding. This paper highlights the need for personalised, integrative approaches in AF and stroke management, emphasising the potential of AI and ML to improve risk prediction, treatment personalisation, and rehabilitation outcomes. Further research is essential to optimise care and reduce the burden of AF and stroke on patients and healthcare systems.

Influence of Observers' Motor Imagery Abilities on Observational Gait Analysis Using the Wisconsin Gait Scale: A Study Among Physical Therapists Treating Stroke Patients

Observational gait analysis is a simple gait assessment commonly used in rehabilitation. However, the effect of an observer's experience and ability on gait analysis has not been clarified. This study aimed to describe observers' motor imagery ability using the Wisconsin Gait Scale (WGS), an evaluation index for observational gait analysis in patients with stroke. Thirty-two physical therapists participated in this study. All participants observed a gait video of a patient with a stroke and performed observational gait analysis using the WGS. The number of correct answers to the WGS for each participant was then calculated according to the correct answers created by two physical therapists with experience in treating patients with stroke. In addition, we evaluated the participants' motor imagery ability using the Controllability of Motor Imagery Test (CMI-T). Multiple regression analysis was performed to examine the factors related to the number of correct WGS answers, with the dependent variable being the number of correct WGS answers and the independent variables being years of experience and CMI-T scores. Next, a hierarchical cluster analysis was performed using the number of correct WGS answers and years of experience as variables, and the CMI-T scores were compared between the two clusters. The results showed that the number of years of experience was selected as a factor significantly related to the number of correct WGS answers. Clusters with more correct WGS answers and more years of experience had substantially higher CMI-T scores than those with fewer correct answers and less experience. In conclusion, physical therapists with better observational gait analysis and more years of experience have better motor imagery skills than their counterparts.

Understanding the implication of task conditions on asymmetry in gait of post-stroke individuals using an Integrated Wearable System

Hemiplegic individuals often demonstrate gait abnormality causing asymmetry in lower-limb muscle activation-related (implicit) and gait-related (explicit) measures (offering complementary information on one's gait) while walking. Added to hemiplegia, such asymmetry can be aggravated while walking under varying task conditions, namely, walking without speaking (single task), walking while counting backwards (dual task), and walking while holding an object and counting backwards (multiple task). This emphasizes the need to quantify the extent of aggravated implication of multiple-task and dual-task on gait asymmetry compared to single task. Here, we used Integrated Wearable System and carried out a study with a group of age-matched hemiplegic (Grp_S) and healthy (Grp_H) individuals to understand the potential of our system in quantifying asymmetry in explicit and implicit measures of gait, implication of hemiplegic condition and varying task conditions on these asymmetry measures along with their clinical relevance. Results showed the potential of our system in quantifying asymmetry in both explicit and implicit measures of gait, and these measures were statistically higher (p-value < 0.05) in Grp_S than Grp_H irrespective of the task conditions. Also, for Grp_S, these asymmetry measures became more pronounced as task demand increased, and again, these measures have shown a correlation with their risk of fall specifically during more attention-demanding tasks that could be clinically relevant.

Clinical Application Research on Stroke Situational Intelligent Rehabilitation Training System Based on Wearable Devices: A Randomized Controlled Trial

Background/Objectives: With the advancement of intelligent sensing technology, rehabilitation systems based on wearable devices have a positive impact on the functional recovery and quality of life of stroke patients. This study aims to evaluate the application value of a contextualized intelligent rehabilitation training system for stroke survivors, which is based on wearable devices, in the rehabilitation of motor function impairments following stroke. Methods: A randomized controlled trial design was employed, in which 100 stroke patients were randomly divided into a control group (n = 50, receiving standard physical therapy rehabilitation interventions) and an experimental group (n = 50). The experimental group additionally underwent motor function rehabilitation interventions and intelligent assessments through a wearable device-based contextual intelligent rehabilitation training system, with sessions conducted twice daily for 30 min each, five days a week, over a duration of eight weeks. Both groups of patients underwent clinical scale evaluations and data collection before and after the treatment, with primary outcome measures including motor ability (Fugl-Meyer Assessment, FMA), activities of daily living (Modified Barthel Index, MBI), and participation in rehabilitation therapy. The intervention effects of both groups were compared after eight weeks of rehabilitation. Results: Prior to the intervention, there were no significant differences in Fugl-Meyer Assessment (FMA) and Modified Barthel Index (MBI) scores between the experimental group and the control group (p > 0.05). After eight weeks of rehabilitation, the experimental group demonstrated significantly superior performance in motor function (FMA scores) and activities of daily living (MBI scores) compared to the control group (p < 0.01). Conclusions: The intelligent rehabilitation system significantly enhances motor function and activities of daily living in stroke survivors. Compared to traditional rehabilitation methods, it improves patient adherence to rehabilitation training and overall outcomes.

Development of an IMU-Based Post-Stroke Gait Data Acquisition and Analysis System for the Gait Assessment and Intervention Tool

Stroke is the fifth leading cause of death in Taiwan. In the process of stroke treatment, rehabilitation for gait recovery is one of the most critical aspects of treatment. The Gait Assessment and Intervention Tool (G.A.I.T.) is currently used in clinical practice to assess the gait recovery level; however, G.A.I.T. heavily depends on physician training and clinical judgment. With the advancement of technology, today's small, lightweight inertial measurement unit (IMU) wearable sensors are rapidly revolutionizing gait assessment and may be incorporated into routine clinical practice. In this paper, we developed a gait data acquisition and analysis system based on IMU wearable devices, proposed a simple yet accurate calibration process to reduce the IMU drifting errors, designed a machine learning algorithm to obtain real-time coordinates from IMU data, computed gait parameters, and derived a formula for G.A.I.T. scores with significant correlation with the physician's observational scores.

IMU-Based quantitative assessment of stroke from gait

Gait impairment, which is commonly observed in stroke survivors, underscores the imperative of rehabilitating walking function. Wearable inertial measurement units (IMUs) can capture gait parameters in stroke patients, becoming a promising tool for objective and quantifiable gait assessment. Optimal sensor placement for stroke assessment that involves optimal combinations of features (kinematics) is required to improve stroke assessment accuracy while reducing the number of sensors to achieve a convenient IMU scheme for both clinical and home assessment; however, previous studies lack comprehensive discussions on the optimal sensor placement and features. To obtain an optimal sensor placement for stroke assessment, this study investigated the impact of IMU placement on stroke assessment based on gait data and clinical scores of 16 stroke patients. Stepwise regression was performed to select the kinematics most correlated with stroke assessment (lower limb part of Fugl-Meyer assessment). Sensors at different locations were combined into 28 sensor groups and their stroke assessment was compared. First, the reduced number of gait features does not significantly impact the stroke assessment. Second, the selected gait parameters by stepwise regression are found all from sensors at the hip and bilateral thighs. Last, a three-sensor scheme-sensors at the hip and bilateral thighs was suggested, which achieved a high accuracy with an adjusted R2 = 0.999, MAE = 0.07, and RMSE = 0.08. Further, the prediction error is zero if the predicted lower limb Fugl-Meyer scales are rounded to the nearest integer. These findings offer a convenient IMU solution for quantitatively assessing stroke patients. Therefore, the IMU-based stroke assessment provides a promising complementary tool for clinical assessment and home rehabilitation of stroke patients.

Explainable Siamese Neural Networks for Detection of High Fall Risk Older Adults in the Community Based on Gait Analysis

BACKGROUND/OBJECTIVES

Falls among the older adult population represent a significant public health concern, often leading to diminished quality of life and serious injuries that escalate healthcare costs, and they may even prove fatal. Accurate fall risk prediction is therefore crucial for implementing timely preventive measures. However, to date, there is no definitive metric to identify individuals with high risk of experiencing a fall. To address this, the present study proposes a novel approach that transforms biomechanical time-series data, derived from gait analysis, into visual representations to facilitate the application of deep learning (DL) methods for fall risk assessment.

METHODS

By leveraging convolutional neural networks (CNNs) and Siamese neural networks (SNNs), the proposed framework effectively addresses the challenges of limited datasets and delivers robust predictive capabilities.

RESULTS

Through the extraction of distinctive gait-related features and the generation of class-discriminative activation maps using Grad-CAM, the random forest (RF) machine learning (ML) model not only achieves commendable accuracy (83.29%) but also enhances explainability.

CONCLUSIONS

Ultimately, this study underscores the potential of advanced computational tools and machine learning algorithms to improve fall risk prediction, reduce healthcare burdens, and promote greater independence and well-being among the older adults.

Typical Changes in Gait Biomechanics in Patients with Subacute Ischemic Stroke

Background/Objectives: Gait dysfunction occurs in 80% of stroke survivors. It increases the risk of falls, reduces functional independence, and thus affects the quality of life. Therefore, it is very important to restore the gait function in post-stroke survivors. The purpose of this study was to investigate the functional changes of gait biomechanics in patients with hemiplegia in the subacute stage of ischemic stroke based on spatiotemporal, kinematic, and EMG parameters. Methods: Initial biomechanical gait analyses of 31 patients and 34 controls were selected. The obtained parameters were assessed and compared within and across the study groups (post-stroke hemiparetic patients and healthy controls) to determine the pathognomonic features of the hemiplegic gait. Results: The gait function asymmetry was characterized by reciprocal changes, i.e., harmonic sequences of gait cycles. The most significant changes were in the kinematics of the knee joint and the EMG activity in the anterior tibialis, gastrocnemius, and hamstring muscles on the paretic side. The movements in the lower extremity joints ranged from a typical amplitude decrease to an almost complete lack of movement or involuntary excessive movement, as can occur in the ankle joint. The knee joint showed two distinct patterns: a slight flexion throughout the entire gait cycle and knee hyperextension during the middle stance phase. Conclusions: The gait function asymmetry is characterized by reciprocal changes (in temporal gait parameters). The most significant changes included decreased amplitude in the knee joint and decreased amplitude of EMG of all muscles under study, except for the m. quadriceps femoris.

Toward Convenient and Accurate IMU-Based Gait Analysis

While inertial measurement unit (IMU)-based systems have shown their potential in quantifying medically significant gait parameters, it remains to be determined whether they can provide accurate and reliable parameters both across various walking conditions and in healthcare settings. Using an IMU-based system we previously developed, with one IMU module on each subject's heel, we quantify the gait parameters of 55 men and 46 women, all healthy and aged 40-65, in normal, dual-task, and fast walking conditions. We evaluate their intra-session reliability, and we establish a new reference database of such parameters showing good to excellent reliability. ICC(2,1) assesses relative reliability, while SEM% and MDC% assess absolute reliability. The reliability is excellent for all spatiotemporal gait parameters and the stride length (SL) symmetry ratio (ICC ≥ 0.90, SEM% ≤ 4.5%, MDC% ≤ 12.4%) across all conditions. It is good to excellent for the fast walking performance (FWP) indices of stride (Sr), stance (Sa), double-support (DS), and step (St) times; gait speed (GS); and the GS normalized to leg length (GSn1) and body height (GSn2) (ICC ≥ 0.91, |SEM%| ≤ 10.0%, |MDC%| ≤ 27.6%). Men have a higher swing time (Sw) and SL across all conditions. The following parameters are gender-independent: (1) Sa, DS, GSn1, GSn2; (2) the symmetry ratios of SL and GS, as well as Sa% and Sw% (representing Sa and Sw as percentages of Sr); and (3) the FWPs of Sr, Sa, Sw, DS, St, cadence, Sa% and Sw%. Our results provide reference values with new insights into gender FWP comparisons rarely reported in the literature. The advantages and reliability of our IMU-based system make it suitable in medical applications such as prosthetic evaluation, fall risk assessment, and rehabilitation.

PROTOCOLO DIGITAL PARA PROJETO CONCEITUAL E VALIDAÇÃO DE UMA ÓRTESE TORNOZELO-PÉ

Objective

This original article aimed to develop a digital protocol for the conceptual design and validation of Ankle-Foot Orthoses (AFO) using 3D mapping technologies.

Methods

A scanned model of the ankle-foot complex of a 12-year-old child with a drop foot was utilized, along with a generic AFO model from a Computer-Aided Design environment. Autodesk Meshmixer and Fusion software were employed for conceptual design and static load analysis.

Results

The static load analysis using the Von Mises failure criterion on the AFO model with ABS material demonstrated structural integrity under critical loading conditions. The digital protocol facilitated the design of a functional and patient-specific AFO orthosis.

Conclusions

The study successfully established a digital workflow for AFO design and validation, showcasing the potential of 3D technologies in creating customized orthoses for lower limb rehabilitation. Level of Evidence IV; Descriptive Study.

Intelligent Diagnosis and Predictive Rehabilitation Assessment of Chronic Ankle Instability Using Shoe-Integrated Sensor System

Ankle sprains, the leading injuries in the emergency department that affect people worldwide, often leading to chronic ankle instability (CAI) characterized by recurring pain and weakness. However, challenges are presented in accurately identifying CAI-related abnormal gait patterns and assessing rehabilitation effects. Traditional plantar pressure systems lack portability and can only be used in limited specific actions, while a few early proposed portable systems have demonstrated insufficient accuracy. Besides, no previous studies have yet focused on assessing rehabilitation effects, which is crucial to providing the treatment selection and rehabilitation evaluation of CAI. Considering this, we propose a novel approach to improve the diagnostic process for CAI. A Shoe-Integrated Sensor System (SISS) which can accurately capture gait data during various activities was implemented. We collected and processed level walking data from 80 CAI patients diagnosed by professional experts and 42 healthy individuals using the system, including feature extraction and filtering algorithms. An artificial intelligence diagnosis was applied to the data, achieving a classification accuracy of 93.39% and an area under the curve (AUC) of 0.959, satisfying the clinical requirements for accuracy. Furthermore, a novel methodology was proposed to assess the level of patient rehabilitation. The validation results of rehabilitation status prediction demonstrated highly consistent results with doctors' diagnoses. Due to the significant impact of gait data in assisting the diagnosis of various neurological and musculoskeletal diseases that result in gait abnormalities, the proposed system can also be extended and utilized in other similar medical fields for diagnosing and real-time monitoring, promoting the development of smart healthcare.

Steps to Facilitate the Use of Clinical Gait Analysis in Stroke Patients: The Validation of a Single 2D RGB Smartphone Video-Based System for Gait Analysis

Clinical gait analysis plays a central role in the rehabilitation of stroke patients. However, practical and technical challenges limit their use in clinical settings. This study aimed to validate SMARTGAIT, a deep learning-based gait analysis system that addresses these limitations. Eight stroke patients took part in the study at the Human Performance Research Centre of the University of Konstanz. Gait measurements were taken using both the marker-based Vicon motion capture system and the single-smartphone-based SMARTGAIT system. We evaluated the agreement for knee, hip, and ankle joint angle kinematics in the frontal and sagittal plane and spatiotemporal gait parameters between the two systems. The results mostly demonstrated high levels of agreement between the two systems, with Pearson correlations of ≥0.79 for all lower body angle kinematics in the sagittal plane and correlations of ≥0.71 in the frontal plane. RMSE values were ≤4.6°. The intraclass correlation coefficients for all derived gait parameters showed good to excellent levels of agreement. SMARTGAIT is a promising tool for gait analysis in stroke, particularly for quantifying gait characteristics in the sagittal plane, which is very relevant for clinical gait analysis. However, further analyses are required to validate the use of SMARTGAIT in larger samples and its transferability to different types of pathological gait. In conclusion, a single smartphone recording (monocular 2D RGB camera) could make gait analysis more accessible in clinical settings, potentially simplifying the process and making it more feasible for therapists and doctors to use in their day-to-day practice.

Center of Pressure- and Machine Learning-based Gait Score and Clinical Risk Factors for Predicting Functional Outcome in Acute Ischemic Stroke

OBJECTIVES

To investigate whether machine learning (ML)-based center of pressure (COP) analysis for gait assessment, when used in conjunction with clinical information, offers additive benefits in predicting functional outcomes in patients with acute ischemic stroke.

DESIGN

A prospective, single-center cohort study.

SETTING

A tertiary hospital setting.

PARTICIPANTS

A total of 185 patients with acute ischemic stroke, capable of walking 10 m with or without a gait aid by day 7 postadmission. From these patients, 10,804 pairs of consecutive footfalls were included for analysis.

INTERVENTIONS

Not applicable.

MAIN OUTCOME MEASURES

The dependent variable was a 3-month poor functional outcome, defined as modified Rankin scale score ≥2. For independent variables, 65 clinical variables including demographics, anthropometrics, comorbidities, laboratory data, questionnaires, and drug history were included. Gait function was evaluated using a pressure-sensitive mat. Time-series COP data were parameterized into spatial and temporal variables and analyzed with logistic regression and 2 ML models (light gradient-boosting machine and multilayer perceptron [MLP]). We derived GAIT-AI output scores from the best-performing model analyzed COP data and constructed multivariable logistic regression models using clinical variables and the GAIT scores.

RESULTS

Among the included patients, 70 (37.8%) experienced unfavorable outcomes. The MLP model demonstrated the highest predictive performance with an area under the receiver operating characteristic curve (AUROC) of 0.799. Multivariable logistic regression identified age, initial National Institutes of Health Stroke Scale, and initial Fall Efficacy Scale-International as associated factors with unfavorable outcomes. The combined multivariable logistic regression incorporating COP-derived output scores improved the AUROC to 0.812.

CONCLUSIONS

Gait function, assessed through COP analysis, serves as a significant predictor of functional outcome in patients with acute ischemic stroke. ML-based COP analysis, when combined with clinical data, enhances the prediction of poor functional outcomes.

Smartphone videos-driven musculoskeletal multibody dynamics modelling workflow to estimate the lower limb joint contact forces and ground reaction forces

The estimation of joint contact forces in musculoskeletal multibody dynamics models typically requires the use of expensive and time-consuming technologies, such as reflective marker-based motion capture (Mocap) system. In this study, we aim to propose a more accessible and cost-effective solution that utilizes the dual smartphone videos (SPV)-driven musculoskeletal multibody dynamics modeling workflow to estimate the lower limb mechanics. Twelve participants were recruited to collect marker trajectory data, force plate data, and motion videos during walking and running. The smartphone videos were initially analyzed using the OpenCap platform to identify key joint points and anatomical markers. The markers were used as inputs for the musculoskeletal multibody dynamics model to calculate the lower limb joint kinematics, joint contact forces, and ground reaction forces, which were then evaluated by the Mocap-based workflow. The root mean square error (RMSE), mean absolute deviation (MAD), and Pearson correlation coefficient (ρ) were adopted to evaluate the results. Excellent or strong Pearson correlations were observed in most lower limb joint angles (ρ = 0.74 ~ 0.94). The averaged MADs and RMSEs for the joint angles were 1.93 ~ 6.56° and 2.14 ~ 7.08°, respectively. Excellent or strong Pearson correlations were observed in most lower limb joint contact forces and ground reaction forces (ρ = 0.78 ~ 0.92). The averaged MADs and RMSEs for the joint lower limb joint contact forces were 0.18 ~ 1.07 bodyweight (BW) and 0.28 ~ 1.32 BW, respectively. Overall, the proposed smartphone video-driven musculoskeletal multibody dynamics simulation workflow demonstrated reliable accuracy in predicting lower limb mechanics and ground reaction forces, which has the potential to expedite gait dynamics analysis in a clinical setting.

Repetitive Transcranial Magnetic Stimulation Coupled With Visual-Feedback Cycling Exercise Improves Walking Ability and Walking Stability After Stroke: A Randomized Pilot Study

Background: Stroke survivors exhibit persistent abnormal gait patterns, particularly in diminished walking ability and stability, limiting mobility and increasing the risk of falling. The purpose of the study was to determine the effects of repetitive transcranial magnetic stimulation (rTMS) coupled with cycling exercise on walking ability and stability in patients with stroke and explore the potential mechanisms underlying motor cortex recovery. Methods: In this double-blinded randomized pilot trial, 32 stroke patients were randomly separated into the real-rTMS group (RG, receiving rTMS during active cycling exercise) and the sham-rTMS group (SG, receiving sham rTMS during active cycling exercise). Participants completed 10 exercise sessions (5 times per week). Lower extremity function was measured using the Fugl-Meyer assessment of lower extremity (FMA-LE), and functional balance ability was measured by the Berg balance scale (BBS). The 2-min walk test (2MWT) and standing balance test were employed to evaluate walking and balance ability. Motor evoked potentials (MEPs) were measured to evaluate cortical excitability. The above assessments were administered at baseline and after the intervention. Additionally, the cycling exercise performance was recorded after the initial and final exercise sessions to evaluate the motor control during exercise. Results: The RG showed significant improvements in lower extremity function (FMA-LE) and functional balance ability (BBS) compared to the SG at postintervention. The walking and balance abilities, as well as the motor asymmetry of cycling exercise, significantly improved in RG. Additionally, participants in RG exhibited a higher elicitation rate of ipsilesional MEPs than that in SG. The improvements in motor asymmetry of cycling exercise in RG were significantly associated with increases in FMA-LE scores and walking ability. Conclusion: The combination of rTMS and cycling exercise effectively improves walking ability and walking stability in patients with stroke, which may be related to the excitability modulation of the motor cortex induced by rTMS. Trial Registration: Clinical Trial Registry identifier: ChiCTR2400079360.

A wearable gait lab powered by sensor-driven digital twins for quantitative biomechanical analysis post-stroke

Commonly, quantitative gait analysis post-stroke is performed in fully equipped laboratories housing costly technologies for quantitative evaluation of a patient's movement capacity. Combining such technologies with an electromyography (EMG)-driven musculoskeletal model can estimate muscle force properties non-invasively, offering clinicians insights into motor impairment mechanisms. However, lab-constrained areas and time-demanding sensor setup and data processing limit the practicality of these technologies in routine clinical care. We presented wearable technology featuring a multi-channel EMG-sensorized garment and an automated muscle localization technique. This allows unsupervised computation of muscle-specific activations, combined with five inertial measurement units (IMUs) for assessing joint kinematics and kinetics during various walking speeds. Finally, the wearable system was combined with a person-specific EMG-driven musculoskeletal model (referred to as human digital twins), enabling the quantitative assessment of movement capacity at a muscle-tendon level. This human digital twin facilitates the estimation of ankle dorsi-plantar flexion torque resulting from individual muscle-tendon forces. Results demonstrate the wearable technology's capability to extract joint kinematics and kinetics. When combined with EMG signals to drive a musculoskeletal model, it yields reasonable estimates of ankle dorsi-plantar flexion torques (R 2 = 0.65 ± 0.21) across different walking speeds for post-stroke individuals. Notably, EMG signals revealing an individual's control strategy compensate for inaccuracies in IMU-derived kinetics and kinematics when input into a musculoskeletal model. Our proposed wearable technology holds promise for estimating muscle kinetics and resulting joint torque in time-limited and space-constrained environments. It represents a crucial step toward translating human movement biomechanics outside of controlled lab environments for effective motor impairment monitoring.

Application of Isokinetic Dynamometry Data in Predicting Gait Deviation Index Using Machine Learning in Stroke Patients: A Cross-Sectional Study

BACKGROUND

Three-dimensional gait analysis, supported by advanced sensor systems, is a crucial component in the rehabilitation assessment of post-stroke hemiplegic patients. However, the sensor data generated from such analyses are often complex and challenging to interpret in clinical practice, requiring significant time and complicated procedures. The Gait Deviation Index (GDI) serves as a simplified metric for quantifying the severity of pathological gait. Although isokinetic dynamometry, utilizing sophisticated sensors, is widely employed in muscle function assessment and rehabilitation, its application in gait analysis remains underexplored.

OBJECTIVE

This study aims to investigate the use of sensor-acquired isokinetic muscle strength data, combined with machine learning techniques, to predict the GDI in hemiplegic patients. This study utilizes data captured from sensors embedded in the Biodex dynamometry system and the Vicon 3D motion capture system, highlighting the integration of sensor technology in clinical gait analysis.

METHODS

This study was a cross-sectional, observational study that included a cohort of 150 post-stroke hemiplegic patients. The sensor data included measurements such as peak torque, peak torque/body weight, maximum work of repeated actions, coefficient of variation, average power, total work, acceleration time, deceleration time, range of motion, and average peak torque for both flexor and extensor muscles on the affected side at three angular velocities (60°/s, 90°/s, and 120°/s) using the Biodex System 4 Pro. The GDI was calculated using data from a Vicon 3D motion capture system. This study employed four machine learning models-Lasso Regression, Random Forest (RF), Support Vector regression (SVR), and BP Neural Network-to model and validate the sensor data. Model performance was evaluated using mean squared error (MSE), the coefficient of determination (R2), and mean absolute error (MAE). SHapley Additive exPlanations (SHAP) analysis was used to enhance model interpretability.

RESULTS

The RF model outperformed others in predicting GDI, with an MSE of 16.18, an R2 of 0.89, and an MAE of 2.99. In contrast, the Lasso Regression model yielded an MSE of 22.29, an R2 of 0.85, and an MAE of 3.71. The SVR model had an MSE of 31.58, an R2 of 0.82, and an MAE of 7.68, while the BP Neural Network model exhibited the poorest performance with an MSE of 50.38, an R2 of 0.79, and an MAE of 9.59. SHAP analysis identified the maximum work of repeated actions of the extensor muscles at 60°/s and 120°/s as the most critical sensor-derived features for predicting GDI, underscoring the importance of muscle strength metrics at varying speeds in rehabilitation assessments.

CONCLUSIONS

This study highlights the potential of integrating advanced sensor technology with machine learning techniques in the analysis of complex clinical data. The developed GDI prediction model, based on sensor-acquired isokinetic dynamometry data, offers a novel, streamlined, and effective tool for assessing rehabilitation progress in post-stroke hemiplegic patients, with promising implications for broader clinical application.

Application of Muscle Synergies for Gait Rehabilitation After Stroke: Implications for Future Research

BACKGROUND/OBJECTIVE

Muscle synergy analysis based on machine learning has significantly advanced our understanding of the mechanisms underlying the central nervous system motor control of gait and has identified abnormal gait synergies in stroke patients through various analytical approaches. However, discrepancies in experimental conditions and computational methods have limited the clinical application of these findings. This review seeks to integrate the results of existing studies on the features of muscle synergies in stroke-related gait abnormalities and provide clinical and research insights into gait rehabilitation.

METHODS

A systematic search of Web of Science, PubMed, and Scopus was conducted, yielding 10 full-text articles for inclusion.

RESULTS

By comprehensively reviewing the consistencies and differences in the study outcomes, we emphasize the need to segment the gait cycle into specific phases (e.g., weight acceptance, push-off, foot clearance, and leg deceleration) during the treatment process of gait rehabilitation and to develop rehabilitation protocols aimed at restoring normal synergy patterns in each gait phase and fractionating reduced synergies.

CONCLUSIONS

Future research should focus on validating these protocols to improve clinical outcomes and introducing indicators to assess abnormalities in the temporal features of muscle synergies.

Targeted Biofeedback Training to Improve Gait Parameters in Subacute Stroke Patients: A Single-Blind Randomized Controlled Trial

Biofeedback (BFB) is a rehabilitation method, which, among other things, is used for the restitution of motor and gait function. As of now, it has become technically feasible to use BFB training based on target gait parameters to improve the gait function in stroke patients. The walking patterns of stroke patients are generally characterized by significant gait phase asymmetries, mostly of the stance phase and the single stance phase. The aim of the study was to investigate the restoration of gait function using BFB training with gait phases as feedback targets. The study included two patient groups, each of 20 hemiparetic patients in the subacute stage of stroke and a control group of 20 healthy subjects. Each patient group received BFB training with either stance phase or single stance phase as the feedback target, respectively. The patients received a total of 8 to 11 training sessions. Assessments based on clinical scales and gait analysis data (spatiotemporal, kinematic, and EMG parameters) were performed before and after the training course. The score-based clinical assessments showed a significant improvement in both patient groups. According to the assessments of gait biomechanics, the subjects in the Single Stance Phase group had significantly more severe dysfunctions. In both patient groups, the unaffected limb responded to the BFB training, while the stance phase significantly changed after training in the unaffected limb only. The other patient group, trained using the single stance phase as the feedback target, showed no changes in the target parameter either in the affected or in the contralateral limb. The clinical and instrumental assessments showed different, non-equivalent sensitivity. The results of the study demonstrated the possibility to use targeted BFB training to improve walking function. However, a significant effect of such training was only observed with stance phase as the target parameter. A response to training was observed predominantly in the unaffected limb and facilitated the desired increase in the functional ability of the paretic limb. Training based on stance phase as the target parameter is probably preferable for the patient population under study.

AI Applications in Adult Stroke Recovery and Rehabilitation: A Scoping Review Using AI

Stroke is a leading cause of long-term disability worldwide. With the advancements in sensor technologies and data availability, artificial intelligence (AI) holds the promise of improving the amount, quality and efficiency of care and enhancing the precision of stroke rehabilitation. We aimed to identify and characterize the existing research on AI applications in stroke recovery and rehabilitation of adults, including categories of application and progression of technologies over time. Data were collected from peer-reviewed articles across various electronic databases up to January 2024. Insights were extracted using AI-enhanced multi-method, data-driven techniques, including clustering of themes and topics. This scoping review summarizes outcomes from 704 studies. Four common themes (impairment, assisted intervention, prediction and imaging, and neuroscience) were identified, in which time-linked patterns emerged. The impairment theme revealed a focus on motor function, gait and mobility, while the assisted intervention theme included applications of robotic and brain-computer interface (BCI) techniques. AI applications progressed over time, starting from conceptualization and then expanding to a broader range of techniques in supervised learning, artificial neural networks (ANN), natural language processing (NLP) and more. Applications focused on upper limb rehabilitation were reviewed in more detail, with machine learning (ML), deep learning techniques and sensors such as inertial measurement units (IMU) used for upper limb and functional movement analysis. AI applications have potential to facilitate tailored therapeutic delivery, thereby contributing to the optimization of rehabilitation outcomes and promoting sustained recovery from rehabilitation to real-world settings.

Biomechanical Gait Analysis Using a Smartphone-Based Motion Capture System (OpenCap) in Patients with Neurological Disorders

This study evaluates the utility of OpenCap (v0.3), a smartphone-based motion capture system, for performing gait analysis in patients with neurological disorders. We compared kinematic and kinetic gait parameters between 10 healthy controls and 10 patients with neurological conditions, including stroke, Parkinson's disease, and cerebral palsy. OpenCap captured 3D movement dynamics using two smartphones, with data processed through musculoskeletal modeling. The key findings indicate that the patient group exhibited significantly slower gait speeds (0.67 m/s vs. 1.10 m/s, p = 0.002), shorter stride lengths (0.81 m vs. 1.29 m, p = 0.001), and greater step length asymmetry (107.43% vs. 91.23%, p = 0.023) compared to the controls. Joint kinematic analysis revealed increased variability in pelvic tilt, hip flexion, knee extension, and ankle dorsiflexion throughout the gait cycle in patients, indicating impaired motor control and compensatory strategies. These results indicate that OpenCap can effectively identify significant gait differences, which may serve as valuable biomarkers for neurological disorders, thereby enhancing its utility in clinical settings where traditional motion capture systems are impractical. OpenCap has the potential to improve access to biomechanical assessments, thereby enabling better monitoring of gait abnormalities and informing therapeutic interventions for individuals with neurological disorders.

Position paper on how technology for human motion analysis and relevant clinical applications have evolved over the past decades: Striking a balance between accuracy and convenience

BACKGROUND

Over the past decades, tremendous technological advances have emerged in human motion analysis (HMA).

RESEARCH QUESTION

How has technology for analysing human motion evolved over the past decades, and what clinical applications has it enabled?

METHODS

The literature on HMA has been extensively reviewed, focusing on three main approaches: Fully-Instrumented Gait Analysis (FGA), Wearable Sensor Analysis (WSA), and Deep-Learning Video Analysis (DVA), considering both technical and clinical aspects.

RESULTS

FGA techniques relying on data collected using stereophotogrammetric systems, force plates, and electromyographic sensors have been dramatically improved providing highly accurate estimates of the biomechanics of motion. WSA techniques have been developed with the advances in data collection at home and in community settings. DVA techniques have emerged through artificial intelligence, which has marked the last decade. Some authors have considered WSA and DVA techniques as alternatives to "traditional" HMA techniques. They have suggested that WSA and DVA techniques are destined to replace FGA.

SIGNIFICANCE

We argue that FGA, WSA, and DVA complement each other and hence should be accounted as "synergistic" in the context of modern HMA and its clinical applications. We point out that DVA techniques are especially attractive as screening techniques, WSA methods enable data collection in the home and community for extensive periods of time, and FGA does maintain superior accuracy and should be the preferred technique when a complete and highly accurate biomechanical data is required. Accordingly, we envision that future clinical applications of HMA would favour screening patients using DVA in the outpatient setting. If deemed clinically appropriate, then WSA would be used to collect data in the home and community to derive relevant information. If accurate kinetic data is needed, then patients should be referred to specialized centres where an FGA system is available, together with medical imaging and thorough clinical assessments.

Psychometric properties of wearable technologies to assess post-stroke gait parameters: A systematic review

BACKGROUND

Wearable technologies using inertial sensors are an alternative for gait assessment. However, their psychometric properties in evaluating post-stroke patients are still being determined. This systematic review aimed to evaluate the psychometric properties of wearable technologies used to assess post-stroke gait and analyze their reliability and measurement error. The review also investigated which wearable technologies have been used to assess angular changes in post-stroke gait.

METHODS

The present review included studies in English with no publication date restrictions that evaluated the psychometric properties (e.g., validity, reliability, responsiveness, and measurement error) of wearable technologies used to assess post-stroke gait. Searches were conducted from February to March 2023 in the following databases: Cochrane Central Registry of Controlled Trials (CENTRAL), Medline/PubMed, EMBASE Ovid, CINAHL EBSCO, PsycINFO Ovid, IEEE Xplore Digital Library (IEEE), and Physiotherapy Evidence Database (PEDro); the gray literature was also verified. The Consensus-based Standards for the Selection of Health Measurement Instruments (COSMIN) risk-of-bias tool was used to assess the quality of the studies that analyzed reliability and measurement error.

RESULTS

Forty-two studies investigating validity (37 studies), reliability (16 studies), and measurement error (6 studies) of wearable technologies were included. Devices presented good reliability in measuring gait speed and step count; however, the quality of the evidence supporting this was low. The evidence of measurement error in step counts was indeterminate. Moreover, only two studies obtained angular results using wearable technology.

SIGNIFICANCE

Wearable technologies have demonstrated reliability in analyzing gait parameters (gait speed and step count) among post-stroke patients. However, higher-quality studies should be conducted to improve the quality of evidence and to address the measurement error assessment. Also, few studies used wearable technology to analyze angular changes during post-stroke gait.

Ground Reaction Forces and Moments in Stroke Survivors: Experimental versus AnyBody Model Predictions

Multibody dynamics models and simulations offer an efficient alternative to traditional methods, such as force plates, pressure sensing mats, and instrumented treadmills, for computing ground reaction forces (GRF) and moments (GRM), valuable in the quantification of the gait of neurological patients. Accurate determination of GRF and GRM magnitudes, with a specific focus on the disruptive shear components affecting gait, is essential for post-stroke gait assessment and rehabilitation. This study explored the predictive capability of musculoskeletal models equipped with foot contact elements, by comparing them with experimental data from a published dataset. The results yielded peak normalized Root Mean Square Errors (n-RMSE) of 0.51±0.31% and 0.46±0.28% for mediolateral shear components, 0.4±0.13% and 0.35±0.16% for anteroposterior shear components, and 0.34±0.16% and 0.32±0.12% for compressive components of GRF for the right and left foot respectively. For GRM, nRMSE peaks in the sagittal plane were 4.72±3.55%, followed by 2.51±2% in the frontal plane, and 2±1.44% in the transverse plane for the right foot. On the left side, nRMSE peaks were 3.73±3.12% in sagittal plane, 2.75±2.7% in frontal plane, and 2.65±2% in the transverse plane. This study underscores the potential of musculoskeletal modeling and simulation software, such as AnyBody, as a time and cost-effective alternative for evaluating the biomechanics of stroke survivors.

Association between gait video information and general cardiovascular diseases: a prospective cross-sectional study

Aims

Cardiovascular disease (CVD) may not be detected in time with conventional clinical approaches. Abnormal gait patterns have been associated with pathological conditions and can be monitored continuously by gait video. We aim to test the association between non-contact, video-based gait information and general CVD status.

Methods and results

Individuals undergoing confirmatory CVD evaluation were included in a prospective, cross-sectional study. Gait videos were recorded with a Kinect camera. Gait features were extracted from gait videos to correlate with the composite and individual components of CVD, including coronary artery disease, peripheral artery disease, heart failure, and cerebrovascular events. The incremental value of incorporating gait information with traditional CVD clinical variables was also evaluated. Three hundred fifty-two participants were included in the final analysis [mean (standard deviation) age, 59.4 (9.8) years; 25.3% were female]. Compared with the baseline clinical variable model [area under the receiver operating curve (AUC) 0.717, (0.690-0.743)], the gait feature model demonstrated statistically better performance [AUC 0.753, (0.726-0.780)] in predicting the composite CVD, with further incremental value when incorporated with the clinical variables [AUC 0.764, (0.741-0.786)]. Notably, gait features exhibited varied association with different CVD component conditions, especially for peripheral artery disease [AUC 0.752, (0.728-0.775)] and heart failure [0.733, (0.707-0.758)]. Additional analyses also revealed association of gait information with CVD risk factors and the established CVD risk score.

Conclusion

We demonstrated the association and predictive value of non-contact, video-based gait information for general CVD status. Further studies for gait video-based daily living CVD monitoring are promising.

Meta-analysis of the quantitative assessment of lower extremity motor function in elderly individuals based on objective detection

OBJECTIVE

To avoid deviation caused by the traditional scale method, the present study explored the accuracy, advantages, and disadvantages of different objective detection methods in evaluating lower extremity motor function in elderly individuals.

METHODS

Studies on lower extremity motor function assessment in elderly individuals published in the PubMed, Web of Science, Cochrane Library and EMBASE databases in the past five years were searched. The methodological quality of the included trials was assessed using RevMan 5.4.1 and Stata, followed by statistical analyses.

RESULTS

In total, 19 randomized controlled trials with a total of 2626 participants, were included. The results of the meta-analysis showed that inertial measurement units (IMUs), motion sensors, 3D motion capture systems, and observational gait analysis had statistical significance in evaluating the changes in step velocity and step length of lower extremity movement in elderly individuals (P < 0.00001), which can be used as a standardized basis for the assessment of motor function in elderly individuals. Subgroup analysis showed that there was significant heterogeneity in the assessment of step velocity [SMD=-0.98, 95%CI(-1.23, -0.72), I2 = 91.3%, P < 0.00001] and step length [SMD=-1.40, 95%CI(-1.77, -1.02), I2 = 86.4%, P < 0.00001] in elderly individuals. However, the sensors (I2 = 9%, I2 = 0%) and 3D motion capture systems (I2 = 0%) showed low heterogeneity in terms of step velocity and step length. The sensitivity analysis and publication bias test demonstrated that the results were stable and reliable.

CONCLUSION

observational gait analysis, motion sensors, 3D motion capture systems, and IMUs, as evaluation means, play a certain role in evaluating the characteristic parameters of step velocity and step length in lower extremity motor function of elderly individuals, which has good accuracy and clinical value in preventing motor injury. However, the high heterogeneity of observational gait analysis and IMUs suggested that different evaluation methods use different calculation formulas and indicators, resulting in the failure to obtain standardized indicators in clinical applications. Thus, multimodal quantitative evaluation should be integrated.

AI in evaluating ambulation of stroke patients: severity classification with video and functional ambulation category scale

BACKGROUND

The evaluation of gait function and severity classification of stroke patients are important to determine the rehabilitation goal and the level of exercise. Physicians often qualitatively evaluate patients' walking ability through visual gait analysis using naked eye, video images, or standardized assessment tools. Gait evaluation through observation relies on the doctor's empirical judgment, potentially introducing subjective opinions. Therefore, conducting research to establish a basis for more objective judgment is crucial.

OBJECTIVE

To verify a deep learning model that classifies gait image data of stroke patients according to Functional Ambulation Category (FAC) scale.

METHODS

Gait vision data from 203 stroke patients and 182 healthy individuals recruited from six medical institutions were collected to train a deep learning model for classifying gait severity in stroke patients. The recorded videos were processed using OpenPose. The dataset was randomly split into 80% for training and 20% for testing.

RESULTS

The deep learning model attained a training accuracy of 0.981 and test accuracy of 0.903. Area Under the Curve(AUC) values of 0.93, 0.95, and 0.96 for discriminating among the mild, moderate, and severe stroke groups, respectively.

CONCLUSION

This confirms the potential of utilizing human posture estimation based on vision data not only to develop gait parameter models but also to develop models to classify severity according to the FAC criteria used by physicians. To develop an AI-based severity classification model, a large amount and variety of data is necessary and data collected in non-standardized real environments, not in laboratories, can also be used meaningfully.

Application of the participatory design in the testing of a baropodometric insole prototype for weight-bearing asymmetry after a stroke: A qualitative study

Introduction

Currently studies indicate the need to incorporate the user`s perspective in the testing of new assistive technologies. The objective of this paper is to test a baropodometric insole prototype for monitoring and treatment weight-bearing asymmetry, according to the Participatory Design.

Methods

We used a qualitative case study approach during the testing phase of the baropodometric insole prototype. The focus group approach addressed topics related to the experience and accessibility of the potential user in conjunction with professionals, researchers, and physiotherapy students. Facilitators, barriers, and requirements for the device were collected through audio recordings of the discussions during and after prototype testing.

Results

Key steps in the prototype testing process were divided into (1) Test of the prototype according to the Participatory Design, divided into Who, When, How, and Why the potential user was involved in the study; and (2) Facilitators, barriers and requirements to improve the prototype.

Conclusions

The baropodometric insole prototype can be seen as a promising device for monitoring and treating weight-bearing asymmetry.

Can We Target Close Therapeutic Goals in the Gait Re-Education Algorithm for Stroke Patients at the Beginning of the Rehabilitation Process?

(1) Background: The study aimed to determine the most important activities of the knee joints related to gait re-education in patients in the subacute period after a stroke. We focused on the tests that a physiotherapist could perform in daily clinical practice. (2) Methods: Twenty-nine stroke patients (SG) and 29 healthy volunteers (CG) were included in the study. The patients underwent the 5-meter walk test (5mWT) and the Timed Up and Go test (TUG). Tests such as step up, step down, squat, step forward, and joint position sense test (JPS) were also performed, and the subjects were assessed using wireless motion sensors. (3) Results: We observed significant differences in the time needed to complete the 5mWT and TUG tests between groups. The results obtained in the JPS show a significant difference between the paretic and the non-paretic limbs compared to the CG group. A significantly smaller range of knee joint flexion (ROM) was observed in the paretic limb compared to the non-paretic and control limbs in the step down test and between the paretic and non-paretic limbs in the step forward test. (4) Conclusions: The described functional tests are useful in assessing a stroke patient's motor skills and can be performed in daily clinical practice.

Devices for Gait and Balance Rehabilitation: General Classification and a Narrative Review of End Effector-Based Manipulators

Gait and balance have a direct impact on patients’ independence and quality of life. Due to a higher life expectancy, the number of patients suffering neurological disorders has increased exponentially, with gait and balance impairments being the main side effects. In this context, the use of rehabilitation robotic devices arises as an effective and complementary tool to recover gait and balance functions. Among rehabilitation devices, end effectors present some advantages and have shown encouraging outcomes. The objective of this study is twofold: to propose a general classification of devices for gait and balance rehabilitation and to provide a review of the existing end effectors for such purposes. We classified the devices into five groups: treadmills, exoskeletons, patient-guided systems, perturbation platforms, and end effectors. Overall, 55 end effectors were identified in the literature, of which 16 were commercialized. We found a disproportionate number of end effectors capable of providing both types of rehabilitation (2/55) and those focused on either balance (21/55) or gait (32/55). The analysis of their features from a mechanical standpoint (degrees of freedom, topology, and training mode) allowed us to identify the potential of parallel manipulators as driving mechanisms of end effector devices and to suggest several future research directions.

Gait Impairment Analysis Using Silhouette Sinogram Signals and Assisted Knowledge Learning

The analysis of body motion is a valuable tool in the assessment and diagnosis of gait impairments, particularly those related to neurological disorders. In this study, we propose a novel automated system leveraging artificial intelligence for efficiently analyzing gait impairment from video-recorded images. The proposed methodology encompasses three key aspects. First, we generate a novel one-dimensional representation of each silhouette image, termed a silhouette sinogram, by computing the distance and angle between the centroid and each detected boundary points. This process enables us to effectively utilize relative variations in motion at different angles to detect gait patterns. Second, a one-dimensional convolutional neural network (1D CNN) model is developed and trained by incorporating the consecutive silhouette sinogram signals of silhouette frames to capture spatiotemporal information via assisted knowledge learning. This process allows the network to capture a broader context and temporal dependencies within the gait cycle, enabling a more accurate diagnosis of gait abnormalities. This study conducts training and an evaluation utilizing the publicly accessible INIT GAIT database. Finally, two evaluation schemes are employed: one leveraging individual silhouette frames and the other operating at the subject level, utilizing a majority voting technique. The outcomes of the proposed method showed superior enhancements in gait impairment recognition, with overall F1-scores of 100%, 90.62%, and 77.32% when evaluated based on sinogram signals, and 100%, 100%, and 83.33% when evaluated based on the subject level, for cases involving two, four, and six gait abnormalities, respectively. In conclusion, by comparing the observed locomotor function to a conventional gait pattern often seen in healthy individuals, the recommended approach allows for a quantitative and non-invasive evaluation of locomotion.

Dual Tasking Affects the Outcomes of Instrumented Timed up and Go, Sit-to-Stand, Balance, and 10-Meter Walk Tests in Stroke Survivors

Stroke can impair mobility, with deficits more pronounced while simultaneously performing multiple activities. In this study, common clinical tests were instrumented with wearable motion sensors to study motor-cognitive interference effects in stroke survivors (SS). A total of 21 SS and 20 healthy controls performed the Timed Up and Go (TUG), Sit-to-Stand (STS), balance, and 10-Meter Walk (10MWT) tests under single and dual-task (counting backward) conditions. Calculated measures included total time and gait measures for TUG, STS, and 10MWT. Balance tests for both open and closed eyes conditions were assessed using sway, measured using the linear acceleration of the thorax, pelvis, and thighs. SS exhibited poorer performance with slower TUG (16.15 s vs. 13.34 s, single-task p < 0.001), greater sway in the eyes open balance test (0.1 m/s2 vs. 0.08 m/s2, p = 0.035), and slower 10MWT (12.94 s vs. 10.98 s p = 0.01) compared to the controls. Dual tasking increased the TUG time (~14%, p < 0.001), balance thorax sway (~64%, p < 0.001), and 10MWT time (~17%, p < 0.001) in the SS group. Interaction effects were minimal, suggesting similar dual-task costs. The findings demonstrate exaggerated mobility deficits in SS during dual-task clinical testing. Dual-task assessments may be more effective in revealing impairments. Integrating cognitive challenges into evaluation can optimize the identification of fall risks and personalize interventions targeting identified cognitive-motor limitations post stroke.

The Artificial Intelligence Revolution in Stroke Care: A Decade of Scientific Evidence in Review

BACKGROUND

The emergence of artificial intelligence (AI) has significantly influenced the diagnostic evaluation of stroke and has revolutionized acute stroke care delivery. The scientific evidence evaluating the role of AI, especially in areas of stroke treatment and rehabilitation is limited but continues to accumulate. We performed a systemic review of current scientific evidence evaluating the use of AI in stroke evaluation and care and examined the publication trends during the past decade.

METHODS

A systematic search of electronic databases was conducted to identify all studies published from 2012 to 2022 that incorporated AI in any aspect of stroke care. Studies not directly relevant to stroke care in the context of AI and duplicate studies were excluded. The level of evidence and publication trends were examined.

RESULTS

A total of 623 studies were examined, including 101 reviews (16.2%), 9 meta-analyses (1.4%), 140 original articles on AI methodology (22.5%), 2 case reports (0.3%), 2 case series (0.3%), 31 case-control studies (5%), 277 cohort studies (44.5%), 16 cross-sectional studies (2.6%), and 45 experimental studies (7.2%). The highest published area of AI in stroke was diagnosis (44.1%) and the lowest was rehabilitation (12%). A 10-year trend analysis revealed a significant increase in AI literature in stroke care.

CONCLUSIONS

Most research on AI is in the diagnostic area of stroke care, with a recent noteworthy trend of increased research focus on stroke treatment and rehabilitation.

Extracorporeal Shock Wave Therapy with Low-Energy Flux Density Treatment Applied to Hemiplegia Patients on Somatosensory Functions and Spatiotemporal Parameters

We aimed to investigate the efect of Extracorporeal Shock Wave Therapy (ESWT) applied to patients with hemiplegia on somatosensory data, spatiotemporal parameters, posture, and muscle tone. This was a double-blind, randomised, controlled trial. Patients were randomised within pairs to either the experimental (ESWT) group (n=20) or the control group (n=20). All patients participated in the same conventional stroke rehabilitation program for 60 minutes of treatment a day, 5 times a week for 6 weeks (30 sessions). Patients assigned to the ESWT group received additional ESWT over the plantar fascia 3 days/week for 6 weeks. Timed Up and Go (TUG) test, Modified Ashworth Scale (MAS) score, Posture Assessment Scale for Stroke Patients (PASS), spatiotemporal parameters, Semmes-Weinstein monofilament (SWM) test, and vibration sensation test (VST) were performed in all participant before and after treatment. In the ESWT and control groups, statistically, significant diferences were obtained in the posttreatment analysis than pre-treatment. Significant diferences were found in foot angle, step cycle duration, swing phase, cadence, gait cycle distance, and VST values after ESWT treatment (P < .01). When combined with a neurological rehabilitation program, it was determined that ESWT applied to the plantar face of the foot in individuals with hemiplegia increased somatosensory functions and was more successful in developing postural control and balance.

Systematic review of automatic post-stroke gait classification systems

BACKGROUND

Gait classification is a clinically helpful task performed after a stroke in order to guide rehabilitation therapy. Gait disorders are commonly identified using observational gait analysis in clinical settings, but this approach is limited due to low reliability and accuracy. Data-driven gait classification can quantify gait deviations and categorise gait patterns automatically possibly improving reliability and accuracy; however, the development and clinical utility of current data driven systems has not been reviewed previously.

RESEARCH QUESTION

The purpose of this systematic review is to evaluate the literature surrounding the methodology used to develop automatic gait classification systems, and their potential effectiveness in the clinical management of stroke-affected gait.

METHOD

The database search included PubMed, IEEE Xplore, and Scopus. Twenty-one studies were identified through inclusion and exclusion criteria from 407 available studies published between 2015 and 2022. Development methodology, classification performance, and clinical utility information were extracted for review.

RESULTS AND SIGNIFICANCE

Most of gait classification systems reported a classification accuracy between 80%-100%. However, collated studies presented methodological errors in machine learning (ML) model development. Further, many studies neglected model components such as clinical utility (e.g., predictions don't assist clinicians or therapists in making decisions, interpretability, and generalisability). We provided recommendations to guide development of future post-stroke automatic gait classification systems to better assist clinicians and therapists. Future automatic gait classification systems should emphasise the clinical significance and adopt a standardised development methodology of ML model.

Clustering Approaches for Gait Analysis within Neurological Disorders: A Narrative Review

Background

The prevalence of neurological disorders is increasing, underscoring the importance of objective gait analysis to help clinicians identify specific deficits. Nevertheless, existing technological solutions for gait analysis often suffer from impracticality in daily clinical use, including excessive cost, time constraints, and limited processing capabilities.

Summary

This review aims to evaluate existing techniques for clustering patients with the same neurological disorder to assist clinicians in optimizing treatment options. A narrative review of thirteen relevant studies was conducted, characterizing their methods, and evaluating them against seven criteria. Additionally, the results are summarized in two comprehensive tables. Recent approaches show promise; however, our results indicate that, overall, only three approaches display medium or high process maturity, and only two show high clinical applicability.

Key Messages

Our findings highlight the necessity for advancements, specifically regarding the use of markerless optical tracking systems, the optimization of experimental plans, and the external validation of results. This narrative review provides a comprehensive overview of existing clustering techniques, bridging the gap between instrumented gait analysis and its real-world clinical utility. We encourage researchers to use our findings and those from other medical fields to enhance clustering techniques for patients with neurological disorders, facilitating the identification of disparities within groups and their extent, ultimately improving patient outcomes.

Rehabilitative effects of electrical stimulation on gait performance in stroke patients: A systematic review with meta-analysis

BACKGROUND

Electrical stimulation techniques are widely utilized for rehabilitation management in individuals with stroke patients.

OBJECTIVES

This review aims to summarize the rehabilitative effects of electrical stimulation therapy on gait performance in stroke patients.

METHODS

This review included randomized controlled trials (RCT) investigating the therapeutic effects of electrical stimulation in stroke patients throughout five databases. This review qualitatively synthesized 20 studies and quantitatively analyzed 11 RCTs.

RESULTS

Functional electrical stimulation (FES) was the most commonly used electrical stimulation type to improve postural stability and gait performance in stroke patients. The clinical measurement tools commonly used in the three studies to assess the therapeutic effects of FES were Berg balance scale (BBS), 10-meter walk test (10MWT), 6-minute walk test (6mWT), and gait velocity. The BBS score and gait velocity had positive effects in the FES group compared with the control group, but the 10MWT and 6mWT showed the same effects between the two groups. The heterogeneity of BBS scores was also high.

CONCLUSION

The results of this review suggest that electrical stimulation shows little evidence of postural stability and gait performance in stroke patients, although some electrical stimulations showed positive effects on postural stability and gait performance.

Validation of an algorithm to assess regular and irregular gait using inertial sensors in healthy and stroke individuals

Background

Studies using inertial measurement units (IMUs) for gait assessment have shown promising results regarding accuracy of gait event detection and spatiotemporal parameters. However, performance of such algorithms is challenged in irregular walking patterns, such as in individuals with gait deficits. Based on the literature, we developed an algorithm to detect initial contact (IC) and terminal contact (TC) and calculate spatiotemporal gait parameters. We evaluated the validity of this algorithm for regular and irregular gait patterns against a 3D optical motion capture system (OMCS).

Methods

Twenty healthy participants (aged 59 ± 12 years) and 10 people in the chronic phase after stroke (aged 61 ± 11 years) were equipped with 4 IMUs: on both feet, sternum and lower back (MTw Awinda, Xsens) and 26 reflective makers. Participants walked on an instrumented treadmill for 2 minutes (i) with their preferred stride lengths and (ii) once with irregular stride lengths (±20% deviation) induced by light projected stepping stones. Accuracy of the algorithm was evaluated on stride-by-stride agreement of IC, TC, stride time, length and velocity with OMCS. Bland-Altman-like plots were made for the spatiotemporal parameters, while differences in detection of IC and TC time instances were shown in histogram plots. Performance of the algorithm was compared between regular and irregular gait with a linear mixed model. This was done by comparing the performance in healthy participants in the regular vs irregular walking condition, and by comparing the agreement in healthy participants with stroke participants in the regular walking condition.

Results

For each condition at least 1,500 strides were included for analysis. Compared to OMCS, IMU-based IC detection in both groups and condition was on average 9-17 (SD ranging from 7 to 35) ms, while IMU-based TC was on average 15-24 (SD ranging from 12 to 35) ms earlier. When comparing regular and irregular gait in healthy participants, the difference between methods was 2.5 ms higher for IC, 3.4 ms lower for TC, 0.3 cm lower for stride length, and 0.4 cm/s higher for stride velocity in the irregular walking condition. No difference was found on stride time. When comparing the differences between methods between healthy and stroke participants, the difference between methods was 7.6 ms lower for IC, 3.8 cm lower for stride length, and 3.4 cm/s lower for stride velocity in stroke participants. No differences were found on differences between methods on TC detection and stride time between stroke and healthy participants.

Conclusions

Small irrelevant differences were found on gait event detection and spatiotemporal parameters due to irregular walking by imposing irregular stride lengths or pathological (stroke) gait. Furthermore, IMUs seem equally good compared to OMCS to assess gait variability based on stride time, but less accurate based on stride length.

Single-Belt Versus Split-Belt: Intelligent Treadmill Control via Microphase Gait Capture for Poststroke Rehabilitation

Stroke is the leading long-term disability and causes a significant financial burden associated with rehabilitation. In poststroke rehabilitation, individuals with hemiparesis have a specialized demand for coordinated movement between the paretic and the nonparetic legs. The split-belt treadmill can effectively facilitate the paretic leg by slowing down the belt speed for that leg while the patient is walking on a split-belt treadmill. Although studies have found that split-belt treadmills can produce better gait recovery outcomes than traditional single-belt treadmills, the high cost of split-belt treadmills is a significant barrier to stroke rehabilitation in clinics. In this article, we design an AI-based system for the single-belt treadmill to make it act like a split-belt by adjusting the belt speed instantaneously according to the patient's microgait phases. This system only requires a low-cost RGB camera to capture human gait patterns. A novel microgait classification pipeline model is used to detect gait phases in real time. The pipeline is based on self-supervised learning that can calibrate the anchor video with the real-time video. We then use a ResNet-LSTM module to handle temporal information and increase accuracy. A real-time filtering algorithm is used to smoothen the treadmill control. We have tested the developed system with 34 healthy individuals and four stroke patients. The results show that our system is able to detect the gait microphase accurately and requires less human annotation in training, compared to the ResNet50 classifier. Our system "Splicer" is boosted by AI modules and performs comparably as a split-belt system, in terms of timely varying left/right foot speed, creating a hemiparetic gait in healthy individuals, and promoting paretic side symmetry in force exertion for stroke patients. This innovative design can potentially provide cost-effective rehabilitation treatment for hemiparetic patients.

Minimal detectable change in inertial measurement unit-based trunk acceleration indices during gait in inpatients with subacute stroke

Gait analysis using inertial measurement units (IMU) provides a multifaceted assessment of gait characteristics, but minimal detectable changes (MDC), the true change beyond measurement error, during gait in patients hospitalized with subacute stroke has not been clarified. This study aimed to determine the MDC in IMU-based trunk acceleration indices during gait in patients hospitalized with subacute stroke. Nineteen patients with subacute stroke (mean ± SD, 75.4 ± 10.9 years; 13 males) who could understand instructions, had a pre-morbid modified Rankin Scale < 3 and could walk straight for 16 m under supervision were included. As trunk acceleration indices, Stride regularity, harmonic ratio (HR), and normalized root mean square (RMS) during gait were calculated on three axes: mediolateral (ML), vertical (VT), and anterior-posterior (AP). MDC was calculated from two measurements taken on the same day according to the following formula: MDC = standard error of measurement × 1.96 × 2. The MDCs for each trunk acceleration index were, in order of ML, VT, and AP: 0.175, 0.179, and 0.149 for stride regularity; 0.666, 0.741, and 0.864 for HR; 4.511, 2.288, and 2.680 for normalized RMS. This finding helps determine the effectiveness of rehabilitation interventions in the gait assessment of patients with stroke.

Ecological validity of a deep learning algorithm to detect gait events from real-life walking bouts in mobility-limiting diseases

Introduction

The clinical assessment of mobility, and walking specifically, is still mainly based on functional tests that lack ecological validity. Thanks to inertial measurement units (IMUs), gait analysis is shifting to unsupervised monitoring in naturalistic and unconstrained settings. However, the extraction of clinically relevant gait parameters from IMU data often depends on heuristics-based algorithms that rely on empirically determined thresholds. These were mainly validated on small cohorts in supervised settings.

Methods

Here, a deep learning (DL) algorithm was developed and validated for gait event detection in a heterogeneous population of different mobility-limiting disease cohorts and a cohort of healthy adults. Participants wore pressure insoles and IMUs on both feet for 2.5 h in their habitual environment. The raw accelerometer and gyroscope data from both feet were used as input to a deep convolutional neural network, while reference timings for gait events were based on the combined IMU and pressure insoles data.

Results and discussion

The results showed a high-detection performance for initial contacts (ICs) (recall: 98%, precision: 96%) and final contacts (FCs) (recall: 99%, precision: 94%) and a maximum median time error of -0.02 s for ICs and 0.03 s for FCs. Subsequently derived temporal gait parameters were in good agreement with a pressure insoles-based reference with a maximum mean difference of 0.07, -0.07, and <0.01 s for stance, swing, and stride time, respectively. Thus, the DL algorithm is considered successful in detecting gait events in ecologically valid environments across different mobility-limiting diseases.

Overground Robotic Exoskeleton Training for Patients With Stroke on Walking-Related Outcomes: A Systematic Review and Meta-analysis of Randomized Controlled Trials

OBJECTIVE

This review aims to evaluate the effectiveness of solely overground robotic exoskeleton (RE) training or overground RE training with conventional rehabilitation in improving walking ability, speed, and endurance among patients with stroke.

DATA SOURCES

Nine databases, 5 trial registries, gray literature, specified journals, and reference lists from inception until December 27, 2021.

STUDY SELECTION

Randomized controlled trials adopting overground robotic exoskeleton training for patients with any phases of stroke on walking-related outcomes were included.

DATA EXTRACTION

Two independent reviewers extracted items and performed risk of bias using the Cochrane Risk of Bias tool 1 and certainty of evidence using the Grades of Recommendation Assessment, Development, and Evaluation.

DATA SYNTHESIS

Twenty trials involving 758 participants across 11 countries were included in this review. The overall effect of overground robotic exoskeletons on walking ability at postintervention (d=0.21; 95% confidence interval [CI], 0.01, 0.42; Z=2.02; P=.04) and follow-up (d=0.37; 95% CI, 0.03, 0.71; Z=2.12; P=.03) and walking speed at postintervention (d=0.23; 95% CI, 0.01, 0.46; Z=2.01; P=.04) showed significant improvement compared with conventional rehabilitation. Subgroup analyses suggested that RE training should combine with conventional rehabilitation. A preferable gait training regime is <4 times per week over ≥6 weeks for ≤30 minutes per session among patients with chronic stroke and ambulatory status of independent walkers before training. Meta-regression did not identify any effect of the covariates on the treatment effect. The majority of randomized controlled trials had small sample sizes, and the certainty of the evidence was very low.

CONCLUSION

Overground RE training may have a beneficial effect on walking ability and walking speed to complement conventional rehabilitation. Further large-scale and long-term, high-quality trials are recommended to enhance the quality of overground RE training and confirm its sustainability.

A comparison of three-dimensional kinematics between markerless and marker-based motion capture in overground gait

Vision-based methods using RGB inputs for human pose estimation have grown in recent years but have undergone limited testing in clinical and biomechanics research areas like gait analysis. The purpose of the present study was to compare lower extremity kinematics during overground gait between a traditional marker-based approach and a commercial multi-view markerless system in a sample of subjects including young adults, older adults, and adults diagnosed with Parkinson's disease. A convenience sample of 35 adults between the age of 18-85 years were included in this study, yielding a total of 114 trials and 228 gait cycles that were compared between systems. A total of 30 time normalized waveforms, including three-dimensional joint centers, segment angles, and joint angles were compared between systems using root mean-squared error (RMSE), range of motion difference (ΔROM), Pearson correlation coefficients (r), and interclass correlation coefficients (ICC). RMSEs for joint center positions were less than 28 mm in all joints with correlations indicating good to excellent agreement. RMSEs for segment and joint angles were in range of previous results, with highest agreement between systems in the sagittal plane. ΔROM differences were within reference values that characterize clinical groups like Parkinson's disease, stroke, or knee osteoarthritis. Further improvements in pelvis tracking, markerless keypoint model definitions, and standardization of comparison study protocols are needed. Nevertheless, markerless solutions seem promising toward unrestricted motion analysis in biomechanics research and clinical settings.

Spatiotemporal gait parameter fluctuations in older adults affected by mild cognitive impairment: comparisons among three cognitive dual-task tests

BACKGROUNDS

Gait disorder is associated with cognitive functional impairment, and this disturbance is more pronouncedly when performing additional cognitive tasks. Our study aimed to characterize gait disorders in mild cognitive impairment (MCI) under three dual tasks and determine the association between gait performance and cognitive function.

METHODS

A total of 260 participants were enrolled in this cross-sectional study and divided into MCI and cognitively normal control. Spatiotemporal and kinematic gait parameters (31 items) in single task and three dual tasks (serial 100-7, naming animals and words recall) were measured using a wearable sensor. Baseline characteristics of the two groups were balanced using propensity score matching. Important gait features were filtered using random forest method and LASSO regression and further described using logistic analysis.

RESULTS

After matching, 106 participants with MCI and 106 normal controls were recruited. Top 5 gait features in random forest and 4 ~ 6 important features in LASSO regression were selected. Robust variables associating with cognitive function were temporal gait parameters. Participants with MCI exhibited decreased swing time and terminal swing, increased mid stance and variability of stride length compared with normal control. Subjects walked slower when performing an extra dual cognitive task. In the three dual tasks, words recall test exhibited more pronounced impact on gait regularity, velocity, and dual task cost than the other two cognitive tests.

CONCLUSION

Gait assessment under dual task conditions, particularly in words recall test, using portable sensors could be useful as a complementary strategy for early detection of MCI.

Conventional physical therapy combined with extracorporeal shock wave leads to positive effects on spasticity in stroke survivors: a prospective observational study

The study aimed to evaluate the effectiveness of radial extracorporeal shock wave therapy (rESWT) and conventional physical therapy (CPT) protocol on the gait pattern in stroke survivors through a new gait analysis technology. Fifteen (n=15) stroke survivors took part in this prospective, observational study and were assessed clinically and through an instrumented treadmill before and after rESWT and CPT. Spasticity grade 95% CI 0.93 (0.79 +/- 1.08), pain intensity 95% CI 1.60 (1.19 +/- 2.01), and clonus score decreased significantly 95% CI 1.13 (0.72 +/- 1.54). The sensorimotor function 95% CI -2.53 (-3.42 +/- 1.65), balance 95% CI -5.67 (-6.64 +/- - 4.69), and gait parameters were enhanced at the end of the program. Step length 95% CI -3.47 (-6.48 +/- 0.46) and step cycle were improved 95% CI -0.09 (-0.17 +/- -0.01), and hip 95% CI -3.90 (-6.92 +/- -0.88), knee 95% CI -2.08 (-3.84 +/- -0.32) and ankle flexion-extension 95% CI -2.08 (-6.64 +/- -4.69) were augmented. Adding the quantitative analysis to the clinical assessment, we gained easy access to track progress and obtained an individualized therapeutic approach for stroke survivors.

Immediate Effect of Ankle Exoskeleton on Spatiotemporal Parameters and Center of Pressure Trajectory After Stroke

Gait impairments is a common condition in post-stroke subjects. We recently presented a wearable ankle exoskeleton called G-Exos, which showed that the device assisted in the ankle's dorsiflexion and inversion/reversion movements. The aim of the current pilot study was to explore spatiotemporal gait parameters and center of pressure trajectories associated with the use of the G-Exos in stroke participants. Three post-stroke subjects (52-63 years, 2 female/1 male) walked 160-meter using the G-Exos on the affected limb, on a protocol divided into 4 blocks of 40-meters: (I) without the exoskeleton, (II) with systems hybrid system, (III) active only and (IV) passive only. The results showed that the use of the exoskeleton improved swing and stance phases on both limbs, reduced stride width on the paretic limb, increased stance COP distances, and made single support COP distances more similar between the paretic and non-paretic limb. This suggests that all G-Exos systems contributed to improving body weight bearing on the paretic limb and symmetry in the gait cycle.

Assistive Technology Involving Postural Control and Gait Performance for Adults with Stroke: A Systematic Review and Meta-Analysis

This study aimed to comprehensively summarize assistive technology devices for postural control and gait performance in stroke patients. In the study, we searched for randomized controlled trials (RCTs) published until 31 December 2022 in four electrical databases. The most frequently applied assistive technology devices involving postural stability and gait function for stroke patients were robot-assistive technology devices. Out of 1065 initially retrieved citations that met the inclusion criteria, 30 RCTs (12 studies for subacute patients and 18 studies for chronic patients) were included in this review based on eligibility criteria. The meta-analysis included ten RCTs (five studies for subacute patients and five for chronic patients) based on the inclusion criteria of the data analysis. After analyzing, the variables, only two parameters, the Berg balance scale (BBS) and the functional ambulation category (FAC), which had relevant data from at least three studies measuring postural control and gait function, were selected for the meta-analysis. The meta-analysis revealed significant differences in the experimental group compared to the control group for BBS in both subacute and chronic stroke patients and for the FAC in chronic stroke patients. Robot-assistive training was found to be superior to regular therapy in improving postural stability for subacute and chronic stroke patients but not gait function. This review suggests that robot-assistive technology devices should be considered in rehabilitative approaches for postural stability and gait function for subacute and chronic stroke patients.

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.