Multivariate functional principal component analysis and k-means clustering to identify kinematic foot types during gait in children with cerebral palsy.

BACKGROUND: Children with neuromuscular disorders, such as cerebral palsy, frequently develop foot deformities, such as equinopronovalgus and equinosupovarus, leading to walking difficulties and discomfort. Traditional assessment methods, including clinical measures and radiographs, often fail to capture the dynamic nature of these deformities, resulting in suboptimal treatment. 3D gait analysis using multisegment foot models offers a more detailed understanding of these deformities. RESEARCH QUESTION: To determine whether the combination of multisegment foot models, multivariate functional principal component analysis, and k-means cluster analyses could identify distinct, clinically relevant foot types in a large pediatric cohort with cerebral palsy. METHODS: This was a retrospective analysis of 3D gait data from 197 patients with cerebral palsy collected using a multisegment foot model. Multivariate functional principal component analysis was used to reduce these data prior to using k-means clustering to identify foot posture clusters. Further analyses, including ANOVA and Fisher's Exact tests, were used to evaluate demographic, radiographic, and gait characteristics to explain the clinical relevance of each cluster. RESULTS: Analysis of kinematic data from 371 feet revealed six clinically significant clusters, with a low misclassification rate of 2 %. One-factor ANOVAs demonstrated significant differences across clusters for all MPCs, whereas no significant differences were noted in basic anthropometric variables. Significant variations were observed in radiographic and gait function variables, and a strong association between GMFCS levels and cluster categorization was identified. SIGNIFICANCE: The novel approach of integrating multivariate functional principal component analysis and k-means clustering identified a spectrum of foot deformities in children with CP, ranging from equinosupovarus to marked equinopronovalgus. This methodology provides an objective classification based on kinematic data and can facilitate improved diagnosis and treatment of cerebral palsy-related foot deformities.

Diagnosis of neurodegenerative diseases with a refined Lempel-Ziv complexity.

The investigation into the distinctive difference of gait is of significance for the clinical diagnosis of neurodegenerative diseases. However, human gait is affected by many factors like behavior, occupation and so on, and they may confuse the gait differences among Parkinson's disease, amyotrophic lateral sclerosis, and Huntington's disease. For the purpose of examining distinctive gait differences of neurodegenerative diseases, this study extracts various features from both vertical ground reaction force and time intervals. Moreover, refined Lempel-Ziv complexity is proposed considering the detailed distribution of signals based on the median and quartiles. Basic features (mean, coefficient of variance, and the asymmetry index), nonlinear dynamic features (Hurst exponent, correlation dimension, largest Lyapunov exponent), and refined Lempel-Ziv complexity of different neurodegenerative diseases are compared statistically by violin plot and Kruskal-Wallis test to reveal distinction and regularities. The comparative analysis results illustrate the gait differences across these neurodegenerative diseases by basic features and nonlinear dynamic features. Classification results by random forest indicate that the refined Lempel-Ziv complexity can robustly enhance the diagnosis accuracy when combined with basic features.

Changes in walking function and neural control following pelvic cancer surgery with reconstruction.

Introduction: Surgical planning and custom prosthesis design for pelvic cancer patients are challenging due to the unique clinical characteristics of each patient and the significant amount of pelvic bone and hip musculature often removed. Limb-sparing internal hemipelvectomy surgery with custom prosthesis reconstruction has become a viable option for this patient population. However, little is known about how post-surgery walking function and neural control change from pre-surgery conditions. Methods: This case study combined comprehensive walking data (video motion capture, ground reaction, and electromyography) with personalized neuromusculoskeletal computer models to provide a thorough assessment of pre- to post-surgery changes in walking function (ground reactions, joint motions, and joint moments) and neural control (muscle synergies) for a single pelvic sarcoma patient who received internal hemipelvectomy surgery with custom prosthesis reconstruction. Pre- and post-surgery walking function and neural control were quantified using pre- and post-surgery neuromusculoskeletal models, respectively, whose pelvic anatomy, joint functional axes, muscle-tendon properties, and muscle synergy controls were personalized using the participant's pre-and post-surgery walking and imaging data. For the post-surgery model, virtual surgery was performed to emulate the implemented surgical decisions, including removal of hip muscles and implantation of a custom prosthesis with total hip replacement. Results: The participant's post-surgery walking function was marked by a slower self-selected walking speed coupled with several compensatory mechanisms necessitated by lost or impaired hip muscle function, while the participant's post-surgery neural control demonstrated a dramatic change in coordination strategy (as evidenced by modified time-invariant synergy vectors) with little change in recruitment timing (as evidenced by conserved time-varying synergy activations). Furthermore, the participant's post-surgery muscle activations were fitted accurately using his pre-surgery synergy activations but fitted poorly using his pre-surgery synergy vectors. Discussion: These results provide valuable information about which aspects of post-surgery walking function could potentially be improved through modifications to surgical decisions, custom prosthesis design, or rehabilitation protocol, as well as how computational simulations could be formulated to predict post-surgery walking function reliably given a patient's pre-surgery walking data and the planned surgical decisions and custom prosthesis design.

Clinical Feasibility of a Markerless Gait Analysis System.

Background: The gait analysis method that has been used in clinical practice to date is an optical tracking system (OTS) using a marker, but a markerless gait analysis (MGA) system is being developed because of the expensive cost and complicated examination of the OTS. To apply this MGA clinically, a comparative study of the MGA and OTS methods is necessary. The purpose of this study was to evaluate the compatibility between the OTS and the MGA methods and to evaluate the usefulness of the MGA system in actual clinical settings. Methods: From March 2021 to August 2021, 14 patients underwent gait analysis using the OTS and MGA system, and the spatiotemporal parameters and kinematic results obtained by the 2 methods were compared. To evaluate the practicality of the MGA system in an actual clinical setting, MGA was performed on 14 symptomatic children with idiopathic toe walking, who had been treated with a corrective cast, and the pre-cast and post-cast results were compared. For the OTS, the Motion Analysis Eagle system was used, and for MGA, DH Walk was used. Results: The spatiotemporal parameters showed no significant difference between the OTS and MGA system. The joint angle graphs of the kinematics along the sagittal plane showed similar shapes as a whole, with particularly high correlations in the hip and knee (pelvis: 29.4%, hip joint: 96.7%, knee joint: 94.9%, and ankle joint: 68.5%). A quantified comparison using the CORrelation and Analysis (CORA) score also showed high similarity between the 2 methods. The MGA results of pre-cast application and post-cast removal for children with idiopathic toe walking showed a statistically significant improvement in ankle dorsiflexion after treatment (p < 0.001). Conclusions: MGA showed a good correlation with the conventional OTS in terms of spatiotemporal parameters and kinematics. We demonstrated that ankle sagittal kinematics improved after treatment by corrective cast in children with idiopathic toe walking using the MGA method. Thus, after the improvement of a few limitations, the MGA system may soon be able to be clinically applied.

Association between three-dimensional gait kinematics and joint-line inclination in osteoarthritic knees compared with normal knees: An epidemiological study.

Purpose: No report has proven how tibial and femoral joint-line inclinations affect thigh and shank motion, respectively, according to Kellgren-Lawrence grade in motion analysis with a sufficient sample size. Therefore, this study aimed to evaluate the motion of the thigh and shank individually from the ground and the relative motion between bones in a large-sample motion analysis to determine the differences between normal and osteoarthritic knees and examine the effects of tibial and femoral joint-line inclination on motion according to osteoarthritis (OA) grade. Methods: Of 459 participants with healthy knees and varus knee OA undergoing three-dimensional gait analysis, 383 (218 females and 165 males) with an average age of 68 ± 13 years were selected. Gait analysis was performed using a motion-capture system. The six degrees of freedom motion parameters of the knee in the Grood and world coordinate systems and the joint-line inclination in the standing radiographs were measured. Results: Osteoarthritic knees demonstrated a relative motion different from that of normal knees, with responsibility for the thigh in the sagittal and rotational planes and the thigh and shank in the coronal plane. The involvement of joint-line inclination in motion was mainly on the tibial side, and the effect was minimal in normal knees. Conclusions: The details of the relative motion of both the thigh and shank can be clarified by analysing individual motions to determine the responsible part. The tibial joint-line affected knee motion: however, the effect was minimal in normal knees. This finding implies that if physical ability can be improved, the negative effects of deformity in osteoarthritic knees may be compensated for. Level of Evidence: Level Ⅱ.

Effects of foot exercises and customized arch support insoles on foot posture, plantar force distribution, and balance in people with flexible flatfoot: A randomized controlled trial.

BACKGROUND: Exercises strengthening foot muscles and customized arch support insoles are recommended for improving foot posture in flexible flatfoot. However, it is not known what the effects of exercises and insoles on plantar force distribution obtained during walking at different speeds. Also, randomized controlled trials comparing the effects of exercises and insoles are limited. RESEARCH QUESTION: What are the effects of foot exercises, customized arch support insoles, and exercises plus insoles on foot posture, plantar force distribution, and balance in people with flexible flatfoot? Do exercises, insoles, and exercises plus insoles affect outcome measures differently? METHODS: Forty-five people with flexible flatfoot were randomly divided into three groups and 40 of those completed the study. The exercise group performed tibialis posterior strengthening and short foot exercises three days a week for six weeks. The insole group used their customized arch support insoles for six weeks. The exercise plus insole group received both interventions for six weeks. The assessments were performed three times: before the interventions and at the 6th and 12th weeks. Outcome measures were (1) foot posture, (2) plantar force distribution in the following conditions: static standing, barefoot walking at different speeds, and walking immediately after the heel-rise test, and (3) balance. RESULTS: Foot posture improved in all groups, but insole was less effective than exercise and exercise plus insole (p<0.05). Plantar force variables obtained during standing and walking changed in all groups (p<0.05). The superiority of the interventions differed according to the plantar regions and walking speed conditions (p<0.05). Static balance improved in all groups, but limits of stability improved in the exercise plus insole and exercise groups (p<0.05). SIGNIFICANCE: The superiority of the interventions differed according to the assessed parameter. The management of flexible flatfoot should be tailored based on the assessment results of each individual.

Spatiotemporal Gait Analysis of Patients with Spinocerebellar Ataxia Types 3 and 10 Using Inertial Measurement Units: A Comparative Study.

Given the high morbidity related to the progression of gait deficits in spinocerebellar ataxias (SCA), there is a growing interest in identifying biomarkers that can guide early diagnosis and rehabilitation. Spatiotemporal parameter (STP) gait analysis using inertial measurement units (IMUs) has been increasingly studied in this context. This study evaluated STP profiles in SCA types 3 and 10, compared them to controls, and correlated them with clinical scales. IMU portable sensors were used to measure STPs under four gait conditions: self-selected pace (SSP), fast pace (FP), fast pace checking-boxes (FPCB), and fast pace with serial seven subtractions (FPS7). Compared to healthy subjects, both SCA groups had higher values for step time, variability, and swing time, with lower values for gait speed, cadence, and step length. We also found a reduction in speed gain capacity in both SCA groups compared to controls and an increase in speed dual-task cost in the SCA10 group. However, there were no significant differences between the SCA groups. Swing time, mean speed, and step length were correlated with disease severity, risk of falling and functionality in both clinical groups. In the SCA3 group, fear of falling was correlated with cadence. In the SCA10 group, results of the Montreal cognitive assessment test were correlated with step time, mean speed, and step length. These results show that individuals with SCA3 and SCA10 present a highly variable, short-stepped, slow gait pattern compared to healthy subjects, and their gait quality worsened with a fast pace and dual-task involvement.

Machine Learning Approaches for Dementia Detection Through Speech and Gait Analysis: A Systematic Literature Review.

Background: Dementia is a general term for several progressive neurodegenerative disorders including Alzheimer's disease. Timely and accurate detection is crucial for early intervention. Advancements in artificial intelligence present significant potential for using machine learning to aid in early detection. Objective: Summarize the state-of-the-art machine learning-based approaches for dementia prediction, focusing on non-invasive methods, as the burden on the patients is lower. Specifically, the analysis of gait and speech performance can offer insights into cognitive health through clinically cost-effective screening methods. Methods: A systematic literature review was conducted following the PRISMA protocol (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). The search was performed on three electronic databases (Scopus, Web of Science, and PubMed) to identify the relevant studies published between 2017 to 2022. A total of 40 papers were selected for review. Results: The most common machine learning methods employed were support vector machine followed by deep learning. Studies suggested the use of multimodal approaches as they can provide comprehensive and better prediction performance. Deep learning application in gait studies is still in the early stages as few studies have applied it. Moreover, including features of whole body movement contribute to better classification accuracy. Regarding speech studies, the combination of different parameters (acoustic, linguistic, cognitive testing) produced better results. Conclusions: The review highlights the potential of machine learning, particularly non-invasive approaches, in the early prediction of dementia. The comparable prediction accuracies of manual and automatic speech analysis indicate an imminent fully automated approach for dementia detection.

Gait Analysis with Wearable Sensors in Isolated REM Sleep Behavior Disorder Associated with Phenoconversion: An Explorative Study.

Background: Gait disturbance is a vital characteristic of motor manifestation in α- synucleinopathies, especially Parkinson's disease. Subtle gait alterations are present in isolated rapid eye movement sleep behavior disorder (iRBD) patients before phenoconversion; it is yet unclear, if gait analysis may predict phenoconversion. Objective: To investigate subtle gait alterations and explore whether gait analysis using wearable sensors is associated with phenoconversion of iRBD to α-synucleinopathies. Methods: Thirty-one polysomnography-confirmed iRBD patients and 33 healthy controls (HCs) were enrolled at baseline. All participants walked for a minute while wearing 6 inertial sensors on bilateral wrists, ankles, and the trunk (sternal and lumbar region). Three conditions were tested: (i) normal walking, (ii) fast walking, and (iii) dual-task walking. Results: Decreased arm range of motion and increased gait variation (stride length, stride time and stride velocity) discriminate converters from HCs at baseline. After an average of 5.40 years of follow-up, 10 patients converted to neurodegenerative diseases (converters). Cox regression analysis showed higher value of stride length asymmetry under normal walking condition to be associated with an early conversion of iRBD to α- synucleinopathies (adjusted HR 4.468, 95% CI 1.088- 18.349, p = 0.038). Conclusions: Stride length asymmetry is associated with progression to α- synucleinopathies in patients with iRBD. Gait analysis with wearable sensors may be useful for screening, monitoring, and risk stratification for disease-modifying therapy trials in patients with iRBD.

Biomechanical gait analysis in sheep: kinematic parameters.

Animals have been used as models to help to better understand biological and anatomical systems, and pathologies in both humans and non-human species, and sheep are often used as an in vivo experimental model for orthopedic research. Gait analysis has been shown to be an important tool in biomechanics research with clinical applications. The purpose of this study was to perform a kinematic analysis using a tridimensional (3D) reconstruction of the sheep hindlimb. Seven healthy sheep were evaluated for natural overground walking, and motion capture of the right hindlimb was collected with an optoelectronic system while the animals walked in a track. The analysis addressed gait spatiotemporal variables, hip, knee and ankle angle and intralimb joint angle coordination measures during the entire walking cycle. This study is the first that describes the spatiotemporal parameters from the hip, knee and ankle joints in a tridimensional way: flexion/extension; abduction/adduction and inter/external rotation. The results of this assessment can be used as an outcome indicator to guide treatment and the efficacy of different therapies for orthopedic and neurological conditions involving the locomotor system of the sheep animal model.

Long-term gait analysis in patients after total knee arthroplasty: A systematic review and meta-analysis.

BACKGROUND: Gait abnormalities have been described in patients after total knee arthroplasty (TKA), leading to the development of inter-joint coordination abnormalities and increased risk of falling. Such impairments have been reported to persist in the long-term, although the majority of studies assessed gait pattern especially in the first months after TKA. RESEARCH QUESTION: What are the long-term gait impairments in patients after TKA compared to healthy age-matched subjects? METHODS: A systematic search was conducted on MEDLINE/PubMed, EMBASE, CENTRAL and Scopus databases. Observational studies or randomized controlled trials investigating gait spatial-temporal, kinematic and kinetics parameters in a time-window longer than 6 months in patients with TKA compared to healthy age-matched subjects were included. Methodological quality was assessed using the modified Downs and Black (D&B) checklist and participants' characteristics, surgical procedures details and outcome measures were extracted. Pooled or un-pooled findings were categorized into "6 months - 1 year" and "more than 1 year" timepoint categories. RESULTS: Twenty-eight studies (976 patients) were included. Overall quality was fair with a mean modified D&B score of 63.5 %. Reduced speed, stride length, cadence and longer stance phase were found in patients when compared to healthy individuals at "6 months - 1 year" follow-up. Spatial-temporal parameters deficits were also found at more than 1 year after TKA, where lower single-limb support and longer double-limb support durations were detected. These impairments occurred in concomitance with decreased knee range of motion along the sagittal and frontal planes and altered kinetic parameters. Hip kinematic and kinetic long-term impairments were also detected after TKA. SIGNIFICANCE: These findings highlighted long-term gait pattern alterations in patients with TKA compared to age-matched healthy subjects. Future studies should identify interventions able to reduce long-term gait pattern alterations and improve function in patients after TKA.

Gait characterization in rare bone diseases in a real-world environment - A comparative controlled study.

BACKGROUND: Rare bone diseases (RBD) cause physical and sensory disability that affects quality of life. Mobility challenges are common for people with RBDs, and travelling to gait analysis labs can be very complex. Smartphone sensors could provide remote monitoring. RESEARCH QUESTION: This study aimed to search for and identify variables that can be used to discriminate between people with RBD and healthy people by using built-in smartphone sensors in a real-world setting. METHODS: In total, 18 participants (healthy: n=9; RBD: n=9), controlled by age and sex, were included in this cross-sectional study. A freely available App (Phyphox) was used to gather data from built-in smartphone sensors (accelerometer & gyroscope) at 60 Hz during a 15-min walk on a level surface without turns or stops. Temporal gait parameters like cadence, mean stride time and, coefficient variance (CoVSt) and nonlinear analyses, as the largest Lyapunov exponent (LLE) & sample entropy (SE) in the three accelerometer axes were used to distinguish between the groups and describe gait patterns. RESULTS: The LLE (p=0.04) and the SE of the z-axis (p=0.01), which are correlated with balance control during walking and regularity of the gait, are sufficiently sensitive to distinguish between RBD and controls. SIGNIFICANCE: The use of smartphone sensors to monitor gait in people with RBD allows for the identification of subtle changes in gait patterns, which can be used to inform assessment and management strategies in larger cohorts.

Mobile digital gait analysis captures effects of botulinum toxin in hereditary spastic paraplegia.

BACKGROUND AND PURPOSE: Hereditary spastic paraplegias (HSPs) comprise a group of inherited neurodegenerative disorders characterized by progressive spasticity and weakness. Botulinum toxin has been approved for lower limb spasticity following stroke and cerebral palsy, but its effects in HSPs remain underexplored. We aimed to characterize the effects of botulinum toxin on clinical, gait, and patient-reported outcomes in HSP patients and explore the potential of mobile digital gait analysis to monitor treatment effects and predict treatment response. METHODS: We conducted a prospective, observational, multicenter study involving ambulatory HSP patients treated with botulinum toxin tailored to individual goals. Comparing data at baseline, after 1 month, and after 3 months, treatment response was assessed using clinical parameters, goal attainment scaling, and mobile digital gait analysis. Machine learning algorithms were used for predicting individual goal attainment based on baseline parameters. RESULTS: A total of 56 patients were enrolled. Despite the heterogeneity of treatment goals and targeted muscles, botulinum toxin led to a significant improvement in specific clinical parameters and an improvement in specific gait characteristics, peaking at the 1-month and declining by the 3-month follow-up. Significant correlations were identified between gait parameters and clinical scores. With a mean balanced accuracy of 66%, machine learning algorithms identified important denominators to predict treatment response. CONCLUSIONS: Our study provides evidence supporting the beneficial effects of botulinum toxin in HSP when applied according to individual treatment goals. The use of mobile digital gait analysis and machine learning represents a novel approach for monitoring treatment effects and predicting treatment response.

The use of digital tools in rare neurological diseases towards a new care model: a narrative review.

Rare neurological diseases as a whole share peculiar features as motor and/or cognitive impairment, an elevated disability burden, a frequently chronic course and, in present times, scarcity of therapeutic options. The rarity of those conditions hampers both the identification of significant prognostic outcome measures, and the development of novel therapeutic approaches and clinical trials. Collection of objective clinical data through digital devices can support diagnosis, care, and therapeutic research. We provide an overview on recent developments in the field of digital tools applied to rare neurological diseases, both in the care setting and as providers of outcome measures in clinical trials in a representative subgroup of conditions, including ataxias, hereditary spastic paraplegias, motoneuron diseases and myopathies.

Model-based cueing-as-needed for walking in Parkinson's disease: A randomized cross-over study.

BACKGROUND: Correcting of the lack of regularity in steps is a key component of gait rehabilitation in Parkinson's disease. We proposed to introduce adaptive spatial auditory cueing (ASAC) based on verbal instruction "lengthen the step" automatically delivered when the stride length decreased below a predetermined threshold. OBJECTIVES: The present study compared the effect of usual rhythmic auditory cueing versus ASAC used during a walking training in Parkinson's disease. METHODS: Fifteen patients with Parkinson's disease performed both interventions in randomized order, one week apart: a 20-minute walking training with rhythmic auditory cueing, in form of a metronome adjusted on 110% of the patient's own cadence, or ASAC delivered when the stride length is less than 110% of the patient's own stride length. Assessment criteria were walking distance covered during the intervention, speed, step length, cadence, coefficients of variation of step length and step duration, and indexes of spatial and temporal asymmetry during a walking test before and just after the intervention. RESULTS: The walking distance is higher with ASAC compared with rhythmic auditory cueing (rhythmic auditory cueing, 905 (203) m, mean (standard deviation); ASAC, 1043 (212) m; P=0.002). Between-intervention comparison showed some similar effects on walking after the intervention including free speed and step length increases (P<0.05). CONCLUSION: The distance covered during 20-minute walking with ASAC increases by 15% compared to the use of classical rhythmic auditory cueing, while the immediate therapeutic effects show similar spatial-temporal benefits on short-distance walking. Auditory biofeedback cueing promoting the increase in step length might improve gait relearning in Parkinson's disease.

Automatic gait events detection with inertial measurement units: healthy subjects and moderate to severe impaired patients.

BACKGROUND: Recently, the use of inertial measurement units (IMUs) in quantitative gait analysis has been widely developed in clinical practice. Numerous methods have been developed for the automatic detection of gait events (GEs). While many of them have achieved high levels of efficiency in healthy subjects, detecting GEs in highly degraded gait from moderate to severely impaired patients remains a challenge. In this paper, we aim to present a method for improving GE detection from IMU recordings in such cases. METHODS: We recorded 10-meter gait IMU signals from 13 healthy subjects, 29 patients with multiple sclerosis, and 21 patients with post-stroke equino varus foot. An instrumented mat was used as the gold standard. Our method detects GEs from filtered acceleration free from gravity and gyration signals. Firstly, we use autocorrelation and pattern detection techniques to identify a reference stride pattern. Next, we apply multiparametric Dynamic Time Warping to annotate this pattern from a model stride, in order to detect all GEs in the signal. RESULTS: We analyzed 16,819 GEs recorded from healthy subjects and achieved an F1-score of 100%, with a median absolute error of 8 ms (IQR [3-13] ms). In multiple sclerosis and equino varus foot cohorts, we analyzed 6067 and 8951 GEs, respectively, with F1-scores of 99.4% and 96.3%, and median absolute errors of 18 ms (IQR [8-39] ms) and 26 ms (IQR [12-50] ms). CONCLUSIONS: Our results are consistent with the state of the art for healthy subjects and demonstrate a good accuracy in GEs detection for pathological patients. Therefore, our proposed method provides an efficient way to detect GEs from IMU signals, even in degraded gaits. However, it should be evaluated in each cohort before being used to ensure its reliability.

FP-GCN: Frequency Pyramid Graph Convolutional Network for Enhancing Pathological Gait Classification.

Gait, a manifestation of one's walking pattern, intricately reflects the harmonious interplay of various bodily systems, offering valuable insights into an individual's health status. However, the current study has shortcomings in the extraction of temporal and spatial dependencies in joint motion, resulting in inefficiencies in pathological gait classification. In this paper, we propose a Frequency Pyramid Graph Convolutional Network (FP-GCN), advocating to complement temporal analysis and further enhance spatial feature extraction. specifically, a spectral decomposition component is adopted to extract gait data with different time frames, which can enhance the detection of rhythmic patterns and velocity variations in human gait and allow a detailed analysis of the temporal features. Furthermore, a novel pyramidal feature extraction approach is developed to analyze the inter-sensor dependencies, which can integrate features from different pathways, enhancing both temporal and spatial feature extraction. Our experimentation on diverse datasets demonstrates the effectiveness of our approach. Notably, FP-GCN achieves an impressive accuracy of 98.78% on public datasets and 96.54% on proprietary data, surpassing existing methodologies and underscoring its potential for advancing pathological gait classification. In summary, our innovative FP-GCN contributes to advancing feature extraction and pathological gait recognition, which may offer potential advancements in healthcare provisions, especially in regions with limited access to medical resources and in home-care environments. This work lays the foundation for further exploration and underscores the importance of remote health monitoring, diagnosis, and personalized interventions.

Assessment of Gait Patterns during Crutch Assisted Gait through Spatial and Temporal Analysis.

The use of crutches is a common method of assisting people during recovery from musculoskeletal injuries in the lower limbs. There are several different ways to walk with crutches depending on the patient's needs. The structure of crutch gaits or crutch gait patterns varies based on the delay between the aid and foot placement, the number of concurrent points of contact, and laterality. In a rehabilitation process, the prescribed pattern may differ according to the injury, the treatment and the individual's condition. Clinicians may improve diagnosis, assessment, training, and treatment by monitoring and analyzing gait patterns. This study aimed to assess and characterize four crutch walking patterns using spatial and temporal parameters obtained from the instrumented crutches. For this purpose, 27 healthy users performed four different gait patterns over multiple trials. Each trial was recorded using a portable system integrated into the crutches, which measured force, position, and acceleration. Based on the data angle, an algorithm was developed to segment the trials into gait cycles and identify gait phases. The next step was to determine the most appropriate metrics to describe each gait pattern. Several metrics were used to analyze the collected data, including force, acceleration, angle, and stride time. Among 27 participants, significant differences were found between crutch gait patterns. Through the use of these spatial and temporal parameters, promising results were obtained for monitoring assisted gait with crutches. Furthermore, the results demonstrated the possibility of using instrumented crutches as a clinical tool.

The Reliability and Validity of the OneStep Smartphone Application for Gait Analysis among Patients Undergoing Rehabilitation for Unilateral Lower Limb Disability.

An easy-to-use and reliable tool is essential for gait assessment of people with gait pathologies. This study aimed to assess the reliability and validity of the OneStep smartphone application compared to the C-Mill-VR+ treadmill (Motek, Nederlands), among patients undergoing rehabilitation for unilateral lower extremity disability. Spatiotemporal gait parameters were extracted from the treadmill and from two smartphones, one on each leg. Inter-device reliability was evaluated using Pearson correlation, intra-cluster correlation coefficient (ICC), and Cohen's d, comparing the application's readings from the two phones. Validity was assessed by comparing readings from each phone to the treadmill. Twenty-eight patients completed the study; the median age was 45.5 years, and 61% were males. The ICC between the phones showed a high correlation (r = 0.89-1) and good-to-excellent reliability (ICC range, 0.77-1) for all the gait parameters examined. The correlations between the phones and the treadmill were mostly above 0.8. The ICC between each phone and the treadmill demonstrated moderate-to-excellent validity for all the gait parameters (range, 0.58-1). Only 'step length of the impaired leg' showed poor-to-good validity (range, 0.37-0.84). Cohen's d effect size was small (d < 0.5) for all the parameters. The studied application demonstrated good reliability and validity for spatiotemporal gait assessment in patients with unilateral lower limb disability.

Optimizing Rare Disease Gait Classification through Data Balancing and Generative AI: Insights from Hereditary Cerebellar Ataxia.

The interpretability of gait analysis studies in people with rare diseases, such as those with primary hereditary cerebellar ataxia (pwCA), is frequently limited by the small sample sizes and unbalanced datasets. The purpose of this study was to assess the effectiveness of data balancing and generative artificial intelligence (AI) algorithms in generating synthetic data reflecting the actual gait abnormalities of pwCA. Gait data of 30 pwCA (age: 51.6 ± 12.2 years; 13 females, 17 males) and 100 healthy subjects (age: 57.1 ± 10.4; 60 females, 40 males) were collected at the lumbar level with an inertial measurement unit. Subsampling, oversampling, synthetic minority oversampling, generative adversarial networks, and conditional tabular generative adversarial networks (ctGAN) were applied to generate datasets to be input to a random forest classifier. Consistency and explainability metrics were also calculated to assess the coherence of the generated dataset with known gait abnormalities of pwCA. ctGAN significantly improved the classification performance compared with the original dataset and traditional data augmentation methods. ctGAN are effective methods for balancing tabular datasets from populations with rare diseases, owing to their ability to improve diagnostic models with consistent explainability.