Instrumented gait analysis for management of gait disorders in children with cerebral palsy: A scoping review

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.

Research on Monitoring Assistive Devices for Rehabilitation of Movement Disorders through Multi-Sensor Analysis Combined with Deep Learning

This study aims to integrate a convolutional neural network (CNN) and the Random Forest Model into a rehabilitation assessment device to provide a comprehensive gait analysis in the evaluation of movement disorders to help physicians evaluate rehabilitation progress by distinguishing gait characteristics under different walking modes. Equipped with accelerometers and six-axis force sensors, the device monitors body symmetry and upper limb strength during rehabilitation. Data were collected from normal and abnormal walking groups. A knee joint limiter was applied to subjects to simulate different levels of movement disorders. Features were extracted from the collected data and analyzed using a CNN. The overall performance was scored with Random Forest Model weights. Significant differences in average acceleration values between the moderately abnormal (MA) and severely abnormal (SA) groups (without vehicle assistance) were observed (p < 0.05), whereas no significant differences were found between the MA with vehicle assistance (MA-V) and SA with vehicle assistance (SA-V) groups (p > 0.05). Force sensor data showed good concentration in the normal walking group and more scatter in the SA-V group. The CNN and Random Forest Model accurately recognized gait conditions, achieving average accuracies of 88.4% and 92.3%, respectively, proving that the method mentioned above provides more accurate gait evaluations for patients with movement disorders.

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.

Distal femoral osteotomy and patellar tendon advancement for the treatment of crouch gait in patients with bilateral spastic cerebral palsy

BACKGROUND

Crouch gait, or flexed knee gait, represents a common gait pattern in patients with spastic bilateral cerebral palsy (CP). Distal femoral extension and/or shortening osteotomy (DFEO/DFSO) and patellar tendon advancement (PTA) can be considered as viable options when knee flexion contractures are involved. Better outcomes have been reported after a combination of both, independently of the presence of knee extensor lag. In this study, we evaluated the clinical and kinematic outcomes of these procedures.

PATIENTS AND METHODS

We reviewed a cohort of 52 limbs (28 patients) who were treated for crouch gait by DFEO/DFSO alone (group 1, n = 15) or DFEO/DFSO + PTA (group 2, n = 37) as a part of single event multilevel surgery (SEMLS). The mean age at surgery was 14 years, and the mean follow-up time was 18 months. The physical examination data and three-dimensional standardized gait analysis were collected and analyzed before the surgery and postoperatively.

RESULTS

Overall knee range of motion improved in all limbs. The knee flexion decreased significantly in both groups at initial, mid, and terminal stance. Hip flexion significantly decreased in mid-stance for limbs in group 2. Both clinical and gait parameters were most improved in limbs who underwent DFEO/DFSO + PTA. Increased pelvic tilt was observed in both groups after surgery.

CONCLUSION

Although DFEO/DFSO alone was successful in correcting knee flexion contractures, PTA has helped to improve knee extensor lag and knee extension during gait.

LEVEL OF EVIDENCE

Therapeutic level IV.

The effect of time normalization and biomechanical signal processing techniques of ground reaction force curves on deep-learning model performance

Time-series data are common in biomechanical studies. These data often undergo pre-processing steps such as time normalization or filtering prior to use in further analyses, including deep-learning classification. In this context, it remains unclear how these preprocessing steps affect deep-learning model performance. Thus, the aim of this study is to assess the effect of time-normalization and filtering on the performance of deep-learning classification models. We also investigated the effect of amplitude scaling. Using a public dataset (Gutenburg Gait Database, a ground reaction force database of level overground walking at self-selected walking speed involving 350 healthy individuals), we trained convolutional neural network (CNN) and long short-term memory (LSTM) models to predict binary sex (male, female) using three-dimensional ground-reaction forces to which we applied different processing approaches: zero padding, interpolation to 100% of signal, filtering, and scaling (min-max, body mass). The results show that transformations resulted in differences in model performances. Highest performance was obtained using unfiltered data, zero-padding, and min-max amplitude scaling (F1-score of 91 and 87% for CNN and LSTM, respectively). Not filtering data and using min-max scaling generally improve performance for both model architectures. For interpolation, results are not consistent across model architectures. This study suggests that processing steps must be considered in applications where deep-learning classification performance is relevant.

Three-Dimensional Instrumented Gait Analysis for Children With Cerebral Palsy: An Evidence-Based Clinical Practice Guideline

BACKGROUND

Children with cerebral palsy (CP) who walk have complex gait patterns and deviations often requiring physical therapy (PT)/medical/surgical interventions. Walking in children with CP can be assessed with 3-dimensional instrumented gait analysis (3D-IGA) providing kinematics (joint angles), kinetics (joint moments/powers), and muscle activity.

PURPOSE

This clinical practice guideline provides PTs, physicians, and associated clinicians involved in the care of children with CP, with 7 action statements on when and how 3D-IGA can inform clinical assessments and potential interventions. It links the action statement grades with specific levels of evidence based on a critical appraisal of the literature.

CONCLUSIONS

This clinical practice guideline addresses 3D-IGA's utility to inform surgical and non-surgical interventions, to identify gait deviations among segments/joints and planes and to evaluate the effectiveness of interventions. Best practice statements provide guidance for clinicians about the preferred characteristics of 3D-IGA laboratories including instrumentation, staffing, and reporting practices.Video Abstract: Supplemental digital content available at http://links.lww.com/PPT/A524.

The Traffic Light System: A user-friendly alternative for gait data representation

BACKGROUND

Instrumented gait analysis is an established procedure in biomechanical assessment, requiring specially-trained analysts to interpret the complex graphical output generated.

RESEARCH QUESTION

Does a new method of visual representation of lower limb kinematic gait analysis data provide a reliable and valid method of interpretation of biomechanical data for healthcare professionals?

METHODS

An innovative system based on the Traffic Lights System (TLS) was developed. Simulated abnormal gait was captured using a 16-camera optoelectronic motion capture system, and the results were presented in both the Traditional Graphical System (TGS) format and the new TLS. An online form was filled by health professionals who attempted to interpret normal and abnormal motion in the joints presented in the 2 output formats.

RESULTS

Out of 26 raters, 18 preferred the new system because of its user-friendliness and its ease of interpretation. 2 raters preferred the TGS, with one of these raters clarifying that the preference is due to colour blindness. For intra-rater reliability, 2 trained raters provided a second response for the TGS (Cronbach's Alpha ranging between 0.733 and 0.918), whilst the TLS resulted in Cronbach's Alpha between 0.817 and 1.00 amongst 3 untrained raters. The Fleiss Multi-rater Kappa Test demonstrated low inter-rater reliability amongst raters in the TGS, whereas the overall Fleiss Multi-rater Kappa values of the TLS surpassed the TGS in all 3 studies.

SIGNIFICANCE

This study showed that whilst trained health professionals have high intra-rater reliability in interpreting traditional gait analysis results, those professionals inexperienced in the system, do not always comprehend the complex graphs generated by the system when presenting gait analysis data. When these graphs are transformed into coloured outputs representing the extent of the movement, the TLS has demonstrated high validity and high intra- and inter-rater reliability, significantly exceeding those of the TGS, especially in untrained health professionals.

Consequences of Virtual Reality Experience on Biomechanical Gait Parameters in Children with Cerebral Palsy: A Scoping Review

Virtual reality (VR), coupled with motion tracking, can investigate walking in a controlled setting while applying various walking challenges. The purpose of this review was to summarize the evidence on consequences of VR on biomechanical gait parameters in children with cerebral palsy. MEDLINE, Embase and Web of Science were searched. Among 7.574 studies, screened by two independent reviewers, seven studies were included, analyzing treadmill (n = 6) or overground walking (n = 1) under VR. Most frequently reported were the spatiotemporal parameters walking speed, stride length, step width, stance phase, and the kinematic parameters range of knee flexion and peak ankle dorsiflexion. However, methodological approaches and reporting of the results were inconsistent among studies. This review reveals that VR can complement information gained from clinical gait analysis. However, this is still an emerging field of research and there is limited knowledge on the effect of VR on gait parameters, notably during overground walking.

Automated Implementation of the Edinburgh Visual Gait Score (EVGS) Using OpenPose and Handheld Smartphone Video

Recent advancements in computing and artificial intelligence (AI) make it possible to quantitatively evaluate human movement using digital video, thereby opening the possibility of more accessible gait analysis. The Edinburgh Visual Gait Score (EVGS) is an effective tool for observational gait analysis, but human scoring of videos can take over 20 min and requires experienced observers. This research developed an algorithmic implementation of the EVGS from handheld smartphone video to enable automatic scoring. Participant walking was video recorded at 60 Hz using a smartphone, and body keypoints were identified using the OpenPose BODY25 pose estimation model. An algorithm was developed to identify foot events and strides, and EVGS parameters were determined at relevant gait events. Stride detection was accurate within two to five frames. The level of agreement between the algorithmic and human reviewer EVGS results was strong for 14 of 17 parameters, and the algorithmic EVGS results were highly correlated (r > 0.80, "r" represents the Pearson correlation coefficient) to the ground truth values for 8 of the 17 parameters. This approach could make gait analysis more accessible and cost-effective, particularly in areas without gait assessment expertise. These findings pave the way for future studies to explore the use of smartphone video and AI algorithms in remote gait analysis.

Combined gait analysis and radiologic examination in children with X-linked hypophosphatemia

BACKGROUND

X-linked hypophosphataemia causes bone deformities and gait abnormalities that tend to worsen with age in the absence of appropriate treatment. However, doctors do not currently use quantitative tools to characterize these symptoms and their possible interactions.

METHODS

Radiographs and 3D gait data from 43 non-surgical growing children with X-linked hypophosphataemia were acquired prospectively. Data from age-matched typically developing children were used to form the reference group. Subgroups based on radiological parameters were compared with each other and with the reference population. Linear correlations between radiographic parameters and gait variables were examined.

FINDING

X-linked hypophosphatemic patients differed from the control group in pelvic tilt, ankle plantarflexion, knee flexion moment and power. High correlations with tibiofemoral angle were found for trunk lean, knee and hip adduction, and knee abduction moment. The Gait Deviation Index was below 80 for 88% of the patients with a high tibiofemoral angle (varus). Compared to other subgroups, varus patients had augmented trunk lean (+3°) and knee adduction (+10°) and decreased hip adduction (-5°) and ankle plantarflexion (-6°). Femoral torsion was associated with alterations in rotation at the knee, and hip.

INTERPRETATION

Gait abnormalities induced in X-linked hypophosphataemia have been described in a large cohort of children. Links between gait alterations and lower limb deformities were found, with varus deformities standing out. Since bony deformities appear when X-linked hypophosphatemic children start walking and have been found to alter gait patterns, we suggest that combining radiology with gait analysis may improve the clinical management of X-linked hypophosphataemia.

Relationship between kinematic gait quality and caregiver-reported everyday mobility in children and youth with spastic Cerebral Palsy

BACKGROUND

3D gait analysis (3DGA) is a common assessment in Cerebral Palsy (CP) to quantify the extent of movement abnormalities. Yet, 3DGA is performed in laboratories and may thus be of debatable significance to everyday life.

AIM

The aim was to assess the relationship between kinematic gait abnormality and everyday mobility in ambulatory children and youth with spastic CP.

METHODS

73 paediatric and juvenile patients with uni- or bilateral spastic CP (N = 21 USCP, N = 52, BSCP, age: 4-20 y, GMFCS I-III) underwent a 3DGA, while the MobQues47 Questionnaire quantified caregiver-reported mobility. We calculated the Gait Profile Score (GPS), a metric that summarizes how far the lower limb joint angles during walking deviate from those of matched controls.

RESULTS

The GPS correlated well with indoor and outdoor mobility (rho = -0.69 and -0.70, both p < 0.001) and the relationships were not significantly different for USCP and BSCP. Still, mobility was lower in BSCP (p < 0.001) and more compromised outdoors (p = 0.002). Indoor mobility could be predicted by walking speed, GPS and age (adj. R² = 0.62). Outdoor mobility was best predicted by walking speed and GPS (adj. R² = 0.60). The additive explained variance by the GPS was even higher outdoors than indoors (17.1% vs. 11.4%).

CONCLUSIONS

Measuring movement deviations with 3DGA seems equally meaningful in uni- and bilaterally affected children and has considerable relevance for real-life ambulation, particurlarly outdoors, where children with spastic CP typically face greater difficulties. Therapeutic strategies that achieve faster walking and reduction of kinematic deviations may increase outdoor mobility.

Reliability and validity of the gait classification system in children with cerebral palsy (GCS-CP)

BACKGROUND

Gait classification systems (GCS) may enable clinicians to differentiate gait patterns into clinically significant categories that assist in clinical decision-making and assessment of outcomes. Davids and Bagley in 2014 [1] described a GCS for children with cerebral palsy (GCS-CP). The purpose of our study was to use the GCS-CP for the first time on a sample of patients with CP and to evaluate the reliability and utility of the classification system.

METHODS

The gait of 131 children with CP was retrospectively reviewed and classified according to Davids and Bagley's classification using two-dimensional (2D) video and three-dimensional (3D) lower limb kinematics and kinetics. Gross Motor Function Classification System (GMFCS) levels were determined, and the Gait Profile Scores (GPS) calculated to characterize the sample concerning gait classification. The comparison between the groups was performed using the Kruskal-Wallis test with respect to the non-normal distribution of the data. The intrarater and interrater reliability was determined using the Kappa index (k) statistics with 95% CI.

RESULTS

All GCS-CP groups were represented within the evaluated sample. Of the 131 cases evaluated, 127 (96.95%) were able to be classified with respect to sagittal plane stance phase gait deviations. All patients in the sample were able to be classified with respect to sagittal plane swing phase and transverse plane gait deviations. The interrater reliability was 0.596 and 0.485 for the first and second levels of the classification, respectively, according to the Fleiss's Kappa statistics. Intrarater reliability was 0.776 and 0.714 for the raters one and two, respectively, according to the Cohen's Kappa statistics.

SIGNIFICANCE

The GCS-CP exhibited clinical utility, successfully classifying almost all subjects with CP in two planes, based upon kinematic and kinetic data. The classification is valid and has moderate interrater and moderate to substantial intrarater reliability.

Accuracy of a 3D temporal scanning system for gait analysis: Comparative with a marker-based photogrammetry system

BACKGROUND

Combining the accuracy of marker-based stereophotogrammetry and the usability and comfort of markerless human movement analysis is a difficult challenge. 3D temporal scanners are a promising solution, since they provide moving meshes with thousands of vertices that can be used to analyze human movements.

RESEARCH QUESTION

Can a 3D temporal scanner be used as a markerless system for gait analysis with the same accuracy as traditional, marker-based stereophotogrammetry systems?

METHODS

A comparative study was carried out using a 3D temporal scanner synchronized with a marker-based stereophotogrammetry system. Two gait cycles of twelve healthy adults were measured simultaneously, extracting the positions of key anatomical points from both systems, and using them to analyze the 3D kinematics of the pelvis, right hip and knee joints. Measurement differences of marker positions and joint angles were described by their root mean square. A t-test was performed to rule out instrumental errors, and an F-test to evaluate the amplifications of marker position errors in dynamic conditions.

RESULTS

The differences in 3D landmark positions were between 1.9 and 2.4 mm in the reference pose. Marker position errors were significantly increased during motion in the medial-lateral and vertical directions. The angle relative errors were between 3% and 43% of the range of motion, with the greatest difference being observed in hip axial rotation.

SIGNIFICANCE

The differences in the results obtained between the 3D temporal scanner and the marker-based system were smaller than the usual errors due to lack of accuracy in the manual positioning of markers on anatomical landmarks and to soft-tissue artefacts. That level of accuracy is greater than other markerless systems, and proves that such technology is a good alternative to traditional, marker-based motion capture.

Home-Based Measurements of Dystonia in Cerebral Palsy Using Smartphone-Coupled Inertial Sensor Technology and Machine Learning: A Proof-of-Concept Study

Accurate and reliable measurement of the severity of dystonia is essential for the indication, evaluation, monitoring and fine-tuning of treatments. Assessment of dystonia in children and adolescents with dyskinetic cerebral palsy (CP) is now commonly performed by visual evaluation either directly in the doctor's office or from video recordings using standardized scales. Both methods lack objectivity and require much time and effort of clinical experts. Only a snapshot of the severity of dyskinetic movements (i.e., choreoathetosis and dystonia) is captured, and they are known to fluctuate over time and can increase with fatigue, pain, stress or emotions, which likely happens in a clinical environment. The goal of this study was to investigate whether it is feasible to use home-based measurements to assess and evaluate the severity of dystonia using smartphone-coupled inertial sensors and machine learning. Video and sensor data during both active and rest situations from 12 patients were collected outside a clinical setting. Three clinicians analyzed the videos and clinically scored the dystonia of the extremities on a 0-4 scale, following the definition of amplitude of the Dyskinesia Impairment Scale. The clinical scores and the sensor data were coupled to train different machine learning models using cross-validation. The average F1 scores (0.67 ± 0.19 for lower extremities and 0.68 ± 0.14 for upper extremities) in independent test datasets indicate that it is possible to detected dystonia automatically using individually trained models. The predictions could complement standard dyskinetic CP measures by providing frequent, objective, real-world assessments that could enhance clinical care. A generalized model, trained with data from other subjects, shows lower F1 scores (0.45 for lower extremities and 0.34 for upper extremities), likely due to a lack of training data and dissimilarities between subjects. However, the generalized model is reasonably able to distinguish between high and lower scores. Future research should focus on gathering more high-quality data and study how the models perform over the whole day.

A Quality Control Check to Ensure Comparability of Stereophotogrammetric Data between Sessions and Systems

Optoelectronic stereophotogrammetric (SP) systems are widely used in human movement research for clinical diagnostics, interventional applications, and as a reference system for validating alternative technologies. Regardless of the application, SP systems exhibit different random and systematic errors depending on camera specifications, system setup and laboratory environment, which hinders comparing SP data between sessions and across different systems. While many methods have been proposed to quantify and report the errors of SP systems, they are rarely utilized due to their complexity and need for additional equipment. In response, an easy-to-use quality control (QC) check has been designed that can be completed immediately prior to a data collection. This QC check requires minimal training for the operator and no additional equipment. In addition, a custom graphical user interface ensures automatic processing of the errors in an easy-to-read format for immediate interpretation. On initial deployment in a multicentric study, the check (i) proved to be feasible to perform in a short timeframe with minimal burden to the operator, and (ii) quantified the level of random and systematic errors between sessions and systems, ensuring comparability of data in a variety of protocol setups, including repeated measures, longitudinal studies and multicentric studies.