Search Results (225)

Background: Charcot–Marie–Tooth disease (CMT) is a genetically and phenotypically heterogeneous hereditary neuropathy. Axonal CMT type 2 (CMT2) subtypes often exhibit overlapping clinical features, which makes molecular genetic analysis essential for accurate diagnosis and subtype differentiation. Methods: This retrospective study included five pediatric patients who presented with gait disturbance, muscle weakness, and foot deformities and were subsequently diagnosed with axonal forms of CMT. Clinical data, electrophysiological studies, neuroimaging, and genetic analyses were evaluated. Whole exome sequencing (WES) was performed in three sporadic cases, while targeted CMT gene panel testing was used for two siblings. Variants were interpreted using ACMG guidelines, supported by public databases (ClinVar, HGMD, and VarSome), and confirmed by Sanger sequencing when available. Results: All had absent deep tendon reflexes and distal muscle weakness; three had intellectual disability. One patient was found to carry a novel homozygous frameshift variant (c.2568_2569del) in the IGHMBP2 gene, consistent with CMT2S. Other variants were identified in the NEFH (CMT2CC), DYNC1H1 (CMT2O), and MPV17 (CMT2EE) genes. Notably, a previously unreported co-occurrence of MPV17 mutation and congenital heart disease was observed in one case. Conclusions: This study expands the clinical and genetic spectrum of pediatric axonal CMT and highlights the role of early physical examination and molecular diagnostics in detecting rare variants. Identification of a novel IGHMBP2 variant and unique phenotypic associations provides new insights for future genotype–phenotype correlation studies. Full article

Gait analysis is a valuable tool for aiding in the diagnosis of neurological diseases, providing objective measurements of human gait kinematics and kinetics. These data enable the quantitative estimation of movement abnormalities, which helps to diagnose disorders and assess their severity. In this regard, machine learning techniques and explainability methods offer an opportunity to enhance anomaly detection in gait measurements and support a more objective assessment of neurodegenerative disease, providing insights into the most relevant gait parameters used for disease identification. This study employs several classifiers and explainability methods to analyze gait data from a public dataset composed of patients affected by degenerative neurological diseases and healthy controls. The work investigates the relevance of spatial, temporal, and kinematic gait parameters in distinguishing such diseases. The findings are consistent among the classifiers employed and in agreement with known clinical findings about the major gait impairments for each disease. This work promotes the use of data-driven assessments in clinical settings, helping reduce subjectivity in gait evaluation and enabling broader deployment in healthcare environments. Full article

Gait recognition is a reliable biometric approach that uniquely identifies individuals based on their natural walking patterns. It is widely used to recognize individuals who are challenging to camouflage and do not require a person’s cooperation. The general face-based person recognition system often fails to determine the offender’s identity when they conceal their face by wearing helmets and masks to evade identification. In such cases, gait-based recognition is ideal for identifying offenders, and most existing work leverages a deep learning (DL) model. However, a single model often fails to capture a comprehensive selection of refined patterns in input data when external factors are present, such as variation in viewing angle, clothing, and carrying conditions. In response to this, this paper introduces a fusion-based multi-model gait recognition framework that leverages the potential of convolutional neural networks (CNNs) and a vision transformer (ViT) in an ensemble manner to enhance gait recognition performance. Here, CNNs capture spatiotemporal features, and ViT features multiple attention layers that focus on a particular region of the gait image. The first step in this framework is to obtain the Gait Energy Image (GEI) by averaging a height-normalized gait silhouette sequence over a gait cycle, which can handle the left–right gait symmetry of the gait. After that, the GEI image is fed through multiple pre-trained models and fine-tuned precisely to extract the depth spatiotemporal feature. Later, three separate fusion strategies are conducted, and the first one is decision-level fusion (DLF), which takes each model’s decision and employs majority voting for the final decision. The second is feature-level fusion (FLF), which combines the features from individual models through pointwise addition before performing gait recognition. Finally, a hybrid fusion combines DLF and FLF for gait recognition. The performance of the multi-model fusion-based framework was evaluated on three publicly available gait databases: CASIA-B, OU-ISIR D, and the OU-ISIR Large Population dataset. The experimental results demonstrate that the fusion-enhanced framework achieves superior performance. Full article

In forensic sciences, particularly in forensic anthropology and podiatry, assessing a person’s stature helps create a biological profile that allows for more accurate identification. Background/Objectives: When considering dynamic footprints as part of the gait pattern, certain parameters such as stride length, step length, gait width, and gait angle can be evaluated in relation to stature. The aim of this study was to assess footstep and stride length from the gait of dynamic footprints and determine if they correlate with stature and could be useful for biological profiling. Methods: Gait patterns from dynamic footprints and stature were determined in 114 females and 104 males aged 18 to 33 years. Results: All participants took the first step with their preferred foot, 56% with the right foot. Regarding step sequence, there were non-significant differences between the 4th and 5th footsteps in both sexes. Sex differences were significant in four of seven footsteps. Only a few steps significantly correlated in sequence with stature, and even these had low correlation coefficients (r = 0.295). In females, positive values of mean differences between actual and estimated stature predictions indicate that the equations tend to overestimate, whereas in a mixed sex group, most negative values of mean differences indicate underestimation. Conclusions: Given the weak correlations observed, footstep and stride length should not be considered reliable indicators for forensic stature estimation. These parameters are more suitable for biomechanical and anthropological research, while forensic applications should be considered supplementary and interpreted with caution. Full article

This research addresses critical challenges in clinical gait analysis by developing an automated video quality assessment framework to support Edinburgh Visual Gait Score (EVGS) scoring. The proposed methodology uses the MoveNet Lightning pose estimation model to extract body keypoints from video frames, enabling detection of multiple persons, tracking the person of interest, assessment of plane orientation, identification of overlapping individuals, detection of zoom artifacts, and evaluation of video resolution. These components are integrated into a unified quality classification system using a random forest classifier. The framework achieved high performance across key metrics, with 96% accuracy in detecting multiple persons, 95% in assessing overlaps, and 92% in identifying zoom events, culminating in an overall video quality categorization accuracy of 95%. This performance not only facilitates the automated selection of videos suitable for analysis but also provides specific video improvement suggestions when quality standards are not met. Consequently, the proposed system has the potential to streamline gait analysis workflows, reduce reliance on manual quality checks in clinical practice, and enable automated EVGS scoring by ensuring appropriate video quality as input to the gait scoring system. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder leading to movement impairment, cognitive decline, and psychiatric symptoms. Key manifestations of PD include bradykinesia (the slowness of movement), changes in voice or speech, and gait disturbances. The quantification of neurological disorders through voice analysis has emerged as a rapidly expanding research domain, offering the potential for non-invasive and large-scale monitoring. This review explores existing research on the application of machine learning (ML) in speech, voice, and language processing for the diagnosis of PD. It comprehensively analyzes current methodologies, highlights key findings and their associated limitations, and proposes strategies to address existing challenges. A systematic review was conducted following PRISMA guidelines. We searched four databases: PubMed, Web of Science, Scopus, and IEEE Xplore. The primary focus was on the diagnosis, detection, or identification of PD through voice, speech, and language characteristics. We included 34 studies that used ML techniques to detect or classify PD based on vocal features. The most used approaches involved free speech and reading-speech tasks. In addition to widely used feature extraction toolkits, several studies implemented custom-built feature sets. Although nearly all studies reported high classification performance, significant limitations were identified, including challenges in comparability and incomplete integration with clinical applications. Emerging trends in this field include the collection of real-world, everyday speech data to facilitate longitudinal tracking and capture participants’ natural behaviors. Another promising direction involves the incorporation of additional modalities alongside voice analysis, which may enhance both analytical performance and clinical applicability. Further research is required to determine optimal methodologies for leveraging speech and voice changes as early biomarkers of PD, thereby enhancing early detection and informing clinical intervention strategies. Full article

Background/Objectives: Cognitive impairment and vestibular dysfunction commonly co-occur in older adults and may share overlapping neuroanatomical pathways. Understanding their association may enhance the early identification of cognitive decline using clinically feasible vestibular assessments. This study aimed to examine the relationship between vestibular dysfunction and early cognitive impairment, assess the diagnostic accuracy of vestibular markers, and explore the association of subjective dizziness and balance measures with cognitive performance. Methods: Our cross-sectional study included 90 participants aged ≥60 years, classified into cognitively healthy, mild cognitive impairment (MCI), and early Alzheimer’s disease (AD) groups. Cognitive function was assessed using the MoCA and the MMSE; vestibular function was evaluated via posturography sway and horizontal vHIT gain. Subjective dizziness and balance were measured using the Dizziness Handicap Inventory (DHI), gait speed, and eyes-closed balance time. The data were analyzed using SPSS v24 with ANOVA, Pearson correlations, linear regression, and ROC curve analyses. Results: Significant group differences were found across the cognitive and vestibular scores (MoCA: p = 0.001. Sway: p = 0.001. vHIT: p = 0.001). vHIT gain and posturography sway independently predicted the MoCA and MMSE scores (adjusted R² = 0.68 and 0.65, respectively). The ROC analysis showed a strong diagnostic accuracy for posturography sway (AUC = 0.87) and vHIT gain (AUC = 0.82). Conclusions: Vestibular dysfunction is significantly associated with early cognitive impairment and may serve as a useful clinical marker for cognitive screening in older adults. Full article

Background: Falls are common among individuals with multiple sclerosis (MS), yet standard clinical mobility assessments—such as the Timed Up and Go (TUG)—may not fully capture the complexities of real-world ambulation, leading to suboptimal fall identification. There is a critical need to evaluate the ecological validity of these assessments and identify alternative tests that better reflect real-world mobility and more accurately detect falls. This study examined the ecological validity of the TUG and novel dual-task clinical assessments by comparing laboratory-based gait metrics to community ambulation in individuals with MS and evaluated their ability to identify fallers. Methods: Twenty-seven individuals with MS (age 59.11 ± 10.57) completed the TUG test and three novel dual-task mobility assessments (TUG-extended, 25-foot walk and turn, and Figure 8 walk), each performed concurrently with a phonemic verbal fluency task. After lab assessments, the participants wore accelerometers for three consecutive days. Gait speed and stride regularity data was collected during both the in-lab clinical assessments and identified walking bouts in the community. The participants were stratified as fallers or non-fallers based on self-reported fall history over the previous six months. Findings: Significant differences were observed between the TUG and real-world ambulation for both gait speed (p < 0.01) and stride regularity (p = 0.04). No significant differences were found in gait metrics between real-world ambulation and both the 25-foot walk and turn and TUG-extended. Intraclass correlation coefficient analysis demonstrated good agreement between the 25-foot walk and turn and real-world ambulation for both gait speed (ICC = 0.75) and stride regularity (ICC = 0.81). When comparing the TUG to real-world ambulation, moderate agreement was observed for gait speed (ICC = 0.56) and poor agreement for stride regularity (ICC = 0.41). The 25-foot walk and turn exhibited superior predictive ability of fall status (AUC = 0.76) compared to the TUG (AUC = 0.67). Conclusions: The 25-foot walk and turn demonstrated strong ecological validity. It also exhibited superior predictive ability of fall status compared to the TUG. These findings support the 25-foot walk and turn as a promising tool for assessing mobility and fall risk in MS, warranting further study. Full article

Background: Advanced sensor insoles and motion capture technology can significantly enhance the monitoring of rehabilitation progress for patients with distal tibial fractures. This study leverages the potential of these innovative tools to provide a more comprehensive assessment of a patient’s gait and weight-bearing capacity following surgical intervention, thereby offering the possibility of improved patient outcomes. Methods: A patient who underwent distal medial tibial plating surgery in August 2023 and subsequently required revision surgery due to implant failure, involving plate removal and the insertion of an intramedullary nail in December 2023, was meticulously monitored over a 12-week period. Initial assessments in November 2023 revealed pain upon full weight-bearing without crutches. Following the revision, precise weekly measurements were taken, starting two days after surgery, which instilled confidence in accurately tracking the patient’s progress from initial crutch-assisted walking to full recovery. The monitoring tools included insoles, hand pads for force absorption of the crutches, and a motion capture system. The patient was accompanied throughout all steps of his daily life. Objectives: The study aimed to evaluate the hypothesis that the approximation and formation of a healthy gait curve are decisive tools for monitoring healing. Specifically, it investigated whether cadence, imbalance factors, and ground reaction forces could be significant indicators of healing status and potential disorders. Results: The gait parameters, cadence, factor of imbalance ground reaction forces, and the temporal progression of kinematic parameters significantly correlate with the patient’s recovery trajectory. These metrics enable the early identification of deviations from expected healing patterns, facilitating timely interventions and underscoring the transformative potential of these technologies in patient care. Conclusions: Integrating sensor insoles and motion capture technology offers a promising approach for monitoring the recovery process in patients with distal tibial fractures. This method provides valuable insights into the patient’s healing status, potentially predicting and addressing healing disorders more effectively. Future studies are recommended to validate these findings in a larger cohort and explore the potential integration of these technologies into clinical practice. Full article

Gait recognition, as a non-contact biometric technology, offers unique advantages in scenarios requiring long-distance identification without active cooperation from subjects. However, existing gait recognition methods predominantly rely on single-modal data, which demonstrates insufficient feature expression capabilities when confronted with complex factors in real-world environments, including viewpoint variations, clothing differences, occlusion problems, and illumination changes. This paper addresses these challenges by introducing a multi-modal gait recognition network based on channel shuffle regulation and spatial-frequency joint learning, which integrates two complementary modalities (silhouette data and heatmap data) to construct a more comprehensive gait representation. The channel shuffle-based feature selective regulation module achieves cross-channel information interaction and feature enhancement through channel grouping and feature shuffling strategies. This module divides input features along the channel dimension into multiple subspaces, which undergo channel-aware and spatial-aware processing to capture dependency relationships across different dimensions. Subsequently, channel shuffling operations facilitate information exchange between different semantic groups, achieving adaptive enhancement and optimization of features with relatively low parameter overhead. The spatial-frequency joint learning module maps spatiotemporal features to the spectral domain through fast Fourier transform, effectively capturing inherent periodic patterns and long-range dependencies in gait sequences. The global receptive field advantage of frequency domain processing enables the model to transcend local spatiotemporal constraints and capture global motion patterns. Concurrently, the spatial domain processing branch balances the contributions of frequency and spatial domain information through an adaptive weighting mechanism, maintaining computational efficiency while enhancing features. Experimental results demonstrate that the proposed GaitCSF model achieves significant performance improvements on mainstream datasets including GREW, Gait3D, and SUSTech1k, breaking through the performance bottlenecks of traditional methods. The implications of this research are significant for improving the performance and robustness of gait recognition systems when implemented in practical application scenarios. Full article

Gait speed and grip strength are widely used measures of physical function in older adults and are predictive of disability, hospitalization, and mortality. However, there is a limited understanding of the long-term trajectories of these measures and which older adults are at the highest risk of functional decline. We used data from the National Health and Aging Trends Study (NHATS) to identify subgroups of community-dwelling older adults with distinct 10-year trajectories in gait speed and grip strength and to examine the baseline factors associated with these patterns. The sample included 4961 adults aged 65 years and older who completed gait speed and grip strength assessments in 2011 and at least one subsequent wave between 2013 and 2021. Using latent class growth analysis, we identified three trajectories for each measure: worsening, stable, and improving. More than one-third of participants were in the worsening group for at least one measure. In multinomial logistic regression models, lower income, Medicaid coverage, cognitive impairment, and multiple chronic conditions were associated with membership in worsening trajectory groups. These findings highlight the heterogeneity of physical aging and the importance of the early identification of older adults who may benefit from targeted interventions to maintain function and independence over time. Full article

This research study proposes a heuristic hybrid deep neural network (DNN) gait sub-phase recognition model based on multi-source heterogeneous motion data fusion which quantifies gait phases and is applied in balance disorder rehabilitation control, achieving a recognition accuracy exceeding 99%. Building upon this model, a motion control strategy for a novel rehabilitation training robot is designed and developed. For patients with some degree of independent movement, an active training strategy is introduced; it combines gait recognition with a variable admittance control strategy. This strategy provides assistance during the stance phase and moderate support during the swing phase, effectively enhancing the patient’s autonomous movement capabilities and increasing engagement in the rehabilitation process. The gait phase recognition system not only provides rehabilitation practitioners with a comprehensive tool for patient assessment but also serves as a theoretical foundation for collaborative control in rehabilitation robots. Through the innovative active–passive training control strategy and its application in the novel rehabilitation robot, this research study overcomes the limitations of traditional rehabilitation robots, which typically operate in a single functional mode, thereby expanding their functional boundaries and enabling more precise, personalized rehabilitation training programs tailored to the needs of patients in different stages of recovery. Full article

Gait refers to the walking pattern of an individual and it varies from person to person. Consequently, it can be considered to be a biometric feature, similar to the face, iris, or fingerprints, and can easily be used for human identification purposes. Person identification using gait analysis has direct applications in user authentication, visual surveillance and monitoring, and access control—to name a few. Naturally, gait analysis has attracted many researchers both from academia and industry over the past few decades. Within a small population, the accuracy of person identification could be very high; however, with the growing number of people in a given gait database, identifying a person only from gait becomes a daunting task. Hence, the focus of researchers in this field has exhibited a paradigm shift to a broader problem of sex and age prediction using different biometric parameters—with gait analysis obviously being one of them. Recent works on sex and age prediction using gait pattern obtained from the inertial sensors lacks an analysis of the features being used. In this paper, we propose a number of features inherent to gait data and analyze key features from the time–series data of accelerometer and gyroscopes for the automatic recognition of sex and the prediction of age. We have trained various traditional machine learning models and achieved the highest accuracy of 94% in sex prediction and an $R^2$ score of 0.83 in age estimation. Full article

Human gait identification is a biometric technique that permits recognizing an individual from a long distance focusing on numerous features such as movement, time, and clothing. This approach in particular is highly useful in video surveillance scenarios, where biometric systems allow people to be easily recognized without intruding on their privacy. In the domain of computer vision, one of the essential and most difficult tasks is tracking a person across multiple camera views, specifically, recognizing the similar person in diverse scenes. However, the accuracy of the gait identification system is significantly affected by covariate factors, such as different view angles, clothing, walking speeds, occlusion, and low-lighting conditions. Previous studies have often overlooked the influence of these factors, leaving a gap in the comprehensive understanding of gait recognition systems. This paper provides a comprehensive review of the most effective gait recognition methods, assessing their performance across various image source databases while highlighting the limitations of existing datasets. Additionally, it explores the influence of key covariate factors, such as viewing angle, clothing, and environmental conditions, on model performance. The paper also compares traditional gait recognition methods with advanced deep learning techniques, offering theoretical insights into the impact of covariates and addressing real-world application challenges. The contrasts and discussions presented provide valuable insights for developing a robust and improved gait-based identification framework for future advancements. Full article

Alterations in static plantar pressure distribution serve as important indicators of gait and balance impairments in individuals with Multiple Sclerosis (MS). In addition, the identification of altered patterns of plantar load distribution, along with restricted ankle dorsiflexion, may serve as early markers of postural instability and gait dysfunction in women with MS. Objectives: To assess differences in static plantar pressure, load distribution, and ankle dorsiflexion range of motion between women diagnosed with MS and women without the condition. Methods: A cross-sectional observational study was conducted between April and December 2024. Women with MS were recruited from patient associations in the provinces of Alicante and Murcia, as well as from the neurology outpatient clinic at the Doctor Balmis University Hospital (Alicante, Spain). Static postural assessment was performed using the Neo-Plate^® pressure platform, which measured maximum and mean plantar pressure (kPa), load distribution (%), contact surface area (cm²), and anterior–posterior weight distribution between the forefoot and rearfoot. The ankle dorsiflexion range of motion was assessed with a universal two-arm goniometer. All parameters were compared with those of a group of women without a diagnosis of MS. Results: Compared to women without MS, participants with MS showed a significantly greater load on the right forefoot (25.75% vs. 23.41%, p = 0.021), and reduced load on the right (23.09% vs. 26.01%, p = 0.004) and left rearfoot (26.60% vs. 30.85%, p = 0.033). Total forefoot loading was significantly higher (52.33% vs. 46.40%, p < 0.001), and rearfoot loading was lower (47.64% vs. 52.42%, p = 0.006) in the MS group. Ankle dorsiflexion range of motion was also significantly reduced in women with MS, both with the knee flexed (5.95° ± 4.50 and 6.76° ± 4.69 vs. 15.45° ± 5.04 and 14.90° ± 5.43) and extended (2.69° ± 3.69 and 3.12° ± 3.83 vs. 8.17° ± 3.41 and 8.60° ± 3.31), with all differences reaching statistical significance (p < 0.001). Conclusions: Women with MS present significant alterations in static plantar load distribution, with increased forefoot and decreased rearfoot loading, as well as markedly reduced ankle dorsiflexion, in comparison to women without the disease. These findings suggest the presence of postural imbalances associated with MS, potentially affecting functional stability and mobility. Full article