Search Results (69)

Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by motor control, balance, and gait impairments that significantly elevate fall risk. Traditional gait analysis focuses on spatiotemporal parameters, while gait variability, asymmetry, and balance measures offer more sensitive indicators of PD-related motor deficits. Machine learning studies using wearable gait data frequently report high classification accuracy but lack biomechanical interpretability and methodological rigor. Using the PhysioNet Gait in Parkinson’s Disease database, 93 individuals with PD and 72 healthy controls were analyzed during level-ground walking. Key biomechanical differences were identified: stride time coefficient of variation was significantly higher in PD bilaterally (left p = 0.001; right p = 0.003); swing-phase time was significantly reduced in both limbs (left p = 0.003; right p = 0.001); anterior–posterior center of pressure (COP) variability was significantly lower in PD for both limbs (p < 0.001); and COP path symmetry index was the most prominent asymmetry marker, significantly elevated in PD relative to controls (p = 0.003). A machine-learning analysis pipeline identified HistGradientBoosting as the best-performing classifier (AUC = 0.992; accuracy = 97.6%), but leave-one-study-out evaluation exposed substantial cross-protocol heterogeneity (AUC: 0.500–1.000), indicating that the model relied partly on dataset-specific patterns and may not generalize to independent acquisition protocols. Shapley Additive Explanations (SHAP) analysis showed classification was driven by a multimodal combination of clinical severity measures and biomechanical gait features rather than wearable metrics alone. A pre-specified gait-only sensitivity analysis that excluded clinical severity variables (UPDRS, UPDRSM, Hoehn and Yahr) confirmed that biomechanical features alone retained moderate, but substantially reduced, discriminative ability (gait-only holdout AUC = 0.844), supporting the interpretation that the headline performance reflects multimodal clinical separation rather than a stand-alone wearable-gait biomarker. These findings indicate that Parkinsonian gait impairment is characterized by timing instability and constrained forward COP progression. The combination of biomechanical analysis with interpretable predictive modeling represents a structured analysis pipeline for gait-based PD assessment; however, external validation in independent cohorts and prospective testing across acquisition protocols are required before such a pipeline can be deployed as a clinically generalizable digital biomarker. Full article

The reliable identification of impairment relevant to safety-critical activities remains a significant challenge for public safety, motivating the exploration of unobtrusive and widely accessible sensing technologies. This study examines the viability of utilising inertial data acquired from consumer-grade smartphones to characterise gait disturbances associated with simulated visual impairment. The study simulates intoxication-related effects using alcohol-impairment goggles and does not involve the measurement of real alcohol intoxication. Two supervised experimental protocols were conducted in which participants traversed predefined walking routes under normal conditions and while wearing alcohol-impairment simulation goggles representing five manufacturer-declared blood alcohol concentration (BAC)-related goggle conditions plus a no-goggles control condition. An initial indoor trial, conducted in a structured corridor environment, yielded limited discrimination of gait dynamics due to strong spatial and visual stabilisation cues. To address this limitation, a subsequent outdoor experiment was conducted along a 100 m path lacking prominent visual reference points, resulting in motion patterns that more closely reflect unconstrained, real-world locomotion. Tri-axial accelerometer and gyroscope signals were recorded using smartphones, followed by artefact removal, segmentation, and standardisation to ensure inter-trial comparability. The resulting curated dataset comprises 290,919 multi-channel samples derived from 96 walking trials involving 16 participants and is released as an openly accessible resource to support further research in gait analysis and classification of gait alterations associated with simulated impairment. Model evaluation was performed using an 80/20 train–test split conducted within each traversal, with training and test windows originating from the same participant and walking session. Consequently, the reported results reflect within-subject performance instead of subject-independent generalisation. Multiple deep learning architectures combining convolutional feature extraction, bidirectional long short-term memory layers, and self-attention mechanisms were systematically evaluated. Using a subject-dependent evaluation protocol, the best-performing architecture achieved an accuracy of 71.4% and a weighted F1-score of 71.5% in distinguishing gait patterns associated with different levels of simulated visual impairment. The best-performing architectures yielded classification performance consistent with exploratory, low-stakes assessment of gait alterations associated with simulated visual impairment, using accelerometer data alone. These findings illustrate the feasibility of using smartphones as auxiliary tools for exploratory, low-stakes screening or educational applications and contribute a publicly released dataset and benchmark results to facilitate methodological advancement in inertial sensor-based gait impairment analysis. Full article

Parkinson’s disease (PD) is a neurodegenerative disorder affecting millions worldwide, characterized by motor symptoms such as tremor, rigidity, and bradykinesia that significantly impair daily life. The current diagnosis and monitoring rely primarily on clinical observations and rating scales (e.g., the MDS-UPDRS), which are subjective and limited in detecting subtle motor alterations, leading to inter- and intra-rater variability. In recent years, wearable sensors such as surface electromyography (sEMG) and inertial measurement units (IMUs) have emerged as non-invasive tools for quantifying neuromuscular activity and motor performance in PD. When combined with machine learning (ML) and deep learning (DL) techniques, these signals enable the development of models for disease detection, patient classification, and symptom severity assessment. This review provides a structured overview of recent ML and DL approaches applied to surface electromyography for PD monitoring, addressing a gap in the current literature. It analyzes data acquisition strategies, preprocessing techniques, feature extraction methods, model architectures, and evaluation protocols across tasks such as diagnosis, tremor analysis, freezing of gait detection, and gait assessment. Despite promising results, key challenges remain, including limited dataset size, lack of standardization, and poor generalization. Finally, this work highlights emerging trends and identifies a representative processing pipeline to support real-world clinical translation. Full article

Background/Objectives: Metabolic syndrome (MetS) is a cluster of cardiometabolic risk factors that increases the risk for cardiovascular disease. Although gait impairments are documented in older adults with MetS, few studies have examined gait biomechanics or the potential for gait-related measures to differentiate metabolic syndrome status in young adults. This study examined whether gait biomechanics, functional gait performance, and muscle strength are associated with MetS risk factors in young adults, and whether these measures predict MetS classification. Methods: Twenty-four young adults meeting criteria for metabolic syndrome (MetS+) and 24 participants without MetS (MetS−) completed cardiometabolic assessments, gait analysis, functional gait testing, and lower extremity isometric strength testing. Multiple linear regression examined associations between gait velocity and MetS risk factors, and binary logistic regression assessed the ability of biomechanical, functional, and strength variables to differentiate MetS status. Results: Compared with matched controls, MetS+ participants demonstrated slower gait velocity, longer stance time, and lower propulsive ground reaction forces. Regression models examining MetS risk factors did not significantly explain variance in gait velocity. Logistic regression indicated that spatiotemporal gait parameters and GRF variables could differentiate MetS classification with fair predictive ability, whereas functional gait performance and strength measures showed limited classification performance. Conclusions: Young adults with MetS demonstrated modest differences in select gait variables, but the MetS risk factors did not show strong relationships with gait velocity in regression analyses. Spatiotemporal gait parameters differentiated MetS+ and MetS− groups but offered limited predictive value. These findings suggest that subtle biomechanical differences may be present early in the progression of MetS, although stronger functional impairments may not yet be detectable in young adults. Full article

Background/Objectives: Parkinsonian gait is characterized by impaired motor adaptability, altered temporal organization, and reduced movement variability. While data augmentation is commonly used to mitigate class imbalance in gait-based machine learning models, conventional strategies often ignore physiological differences between healthy and pathological movements, potentially distorting meaningful motor dynamics. This study explores whether preserving healthy motor variability while selectively augmenting pathological gait signals can improve the robustness and physiological coherence of gait pattern classification models. Methods: Eight patients with Parkinsonian gait patterns and forty-eight healthy participants performed walking tasks on the Motigravity platform under hypogravity conditions. Full-body kinematic data were acquired using wearable inertial sensors. A selective augmentation strategy based on smooth time-warping was applied exclusively to pathological gait segments (×5, σ = 0.2), while healthy gait signals were left unaltered to preserve natural motor variability. Model performance was evaluated using a hybrid convolutional neural network–long short-term memory (CNN–LSTM) architecture across multiple augmentation configurations. Results: Selective augmentation of pathological gait signals achieved the highest classification performance (94.1% accuracy, AUC = 0.97), with balanced sensitivity (93.8%) and specificity (94.3%). Performance decreased when augmentation exceeded an optimal range of variability, suggesting that beneficial augmentation is constrained by physiologically plausible temporal dynamics. Conclusions: These findings demonstrate that physiology-informed, selective data augmentation can improve gait pattern classification under constrained data conditions. Rather than supporting disease-specific diagnosis, this proof-of-concept study highlights the importance of respecting intrinsic differences in motor variability when designing augmentation strategies for clinical gait analysis. Future studies incorporating disease-control cohorts and subject-independent validation are required to assess specificity and clinical generalizability. Full article

Parkinson’s Disease (PD) is a neurodegenerative disorder in which gait abnormalities serve as key indicators of motor impairment and disease progression. Although wearable sensor-based gait analysis has advanced, existing methods still face challenges in modeling multi-sensor spatial relationships, extracting adaptive multi-scale temporal features, and effectively integrating time–frequency information. To address these issues, this paper proposes a multi-sensor gait neural network that integrates biomechanical priors with time–frequency collaborative learning for the automatic assessment of PD gait severity. The framework consists of three core modules: (1) BGS-GAT (Biomechanics-Guided Graph Attention Network), which constructs a sensor graph based on plantar anatomy and explicitly models inter-regional force dependencies via graph attention; (2) AMS-Inception1D (Adaptive Multi-Scale Inception-1D), which employs dilated convolutions and channel attention to extract multi-scale temporal features adaptively; and (3) TF-Branch (Time–Frequency Branch), which applies Real-valued Fast Fourier Transform (RFFT) and frequency-domain convolution to capture rhythmic and high-frequency components, enabling complementary time–frequency representation. Experiments on the PhysioNet multi-channel foot pressure dataset demonstrate that the proposed model achieves 0.930 in accuracy and 0.925 in F1-score for four-class severity classification, outperforming state-of-the-art deep learning models. Full article

Post-stroke gait dysfunction is biomechanically heterogeneous, yet biomechanically informed classifications of functional walking remain underdeveloped. In particular, there is a lack of clinically accessible methods for classifying gait deficits that account for propulsion impairments—a historically laboratory-dependent gait parameter requiring measurement with force plate systems. This study examined whether propulsion impairment can be classified by combining a global measure of walking function (i.e., the 10 m walk test speed) with specific measures of dynamic walking ability derived from the Functional Gait Assessment (FGA). Forty participants >6 months post-stroke completed biomechanical evaluations quantifying propulsion during walking and clinical assessments including the FGA. Multivariable stepwise regression identified the FGA items most strongly associated with paretic propulsion. Models augmented with these FGA items explained 15% greater variance in the paretic propulsion peak and 7% greater variance in paretic propulsion impulse compared with models using Comfortable Walking Speed (CWS) alone. Incorporating FGA items also yielded the highest overall accuracy (72.5% vs. 60% with CWS alone) and best per-class performance in propulsion severity classification. These findings establish the co-assessment of walking speed and targeted FGA items as a clinically feasible approach to biomechanically informed classification of post-stroke gait dysfunction. Full article

Background: Wolfram syndrome (WS) is an ultrarare neuroendocrine disorder caused by pathogenic variants in WFS1, frequently leading to progressive neurological, autonomic, and cognitive impairment. Anticipating neurological trajectories remains challenging due to marked phenotypic variability and limited genotype–phenotype data. Methods: Forty-five genetically confirmed patients with WS were evaluated between 1998 and 2024 in Spain. All WFS1 variants were systematically classified by exon, zygosity, protein-level functional impact, and predicted wolframin production (Classes 0–3). Machine learning models (Random Forests with engineered gene–gene interaction terms) were applied to predict neurological manifestations and identify the strongest genetic determinants of symptom severity. Results: Neurological involvement was present in 93% of patients. The most prevalent manifestations were absence of gag reflex (67%), gait instability (64%), dysphagia (60%), and sialorrhea (60%), followed by dysmetria (56%), impaired tandem gait (53%), anosmia (44%), dysarthria (44%), and adiadochokinesia (42%). Most symptoms emerged in early adulthood (23–26 years), whereas cognitive decline occurred later (29.9 ± 12.2 years). Homozygosity for truncating variants—particularly c.409_424dup16 (Val142fsX110)—and complete loss of wolframin production (Class 0; 67–83% across symptoms) were the strongest predictors of early and severe neurological involvement. Machine learning models achieved high discrimination for ataxia, gait instability, and absent gag reflex (AUC 0.63–0.86; calibrated AUC up to 0.97), identifying Mut1_Protein_Class and Mut2_Protein_Class as dominant predictors across all phenotypes, followed by coherent secondary effects from zygosity × exon interaction terms (Prod_mgm). Conclusions: Integrating detailed genetic classification with machine learning methods enables accurate prediction of neurological outcomes in WS. Protein-level dysfunction and allele interaction structure are the principal drivers of neurological vulnerability. This framework enhances precision diagnosis and offers a foundation for individualized surveillance, clinical risk stratification, and future therapeutic trial design in WFS1-related disorders. Full article

This study explores the potential of accelerometer-based gait analysis as a non-invasive approach for predicting cognitive impairment in older adults. A total of 75 participants (61.3% female; mean age: 78.9 years), including cognitively normal individuals and patients with dementia, were enrolled. Walking data were collected using a six-axis waist-worn accelerometer during self-paced locomotion. Allan variance (AVAR), a robust statistical measure of frequency stability, was applied to characterize gait dynamics. AVAR-derived features, combined with participant age, were used as inputs to machine learning models, logistic regression and Light Gradient Boosting Machine (LightGBM) for classifying cognitive status based on Mini-Mental State Examination (MMSE) scores. LightGBM achieved superior performance (AUC = 0.92) compared to logistic regression (AUC = 0.85). Although mild cognitive impairment (MCI) cases were grouped with cognitively normal participants, gait-based classification revealed that MCI individuals exhibited patterns more similar to those with cognitive impairment. These results suggest that AVAR-based gait features are promising for early detection of cognitive decline in older adults. Full article

People with Parkinson’s disease (PD) experience mobility impairments that impact daily functioning, yet conventional clinical assessments provide limited insight into real-world mobility. This study evaluated motor-state classification and the concurrent validity of mobility metrics derived from augmented-reality (AR) glasses against a markerless motion capture system (Theia3D) during gamified AR exercises. Fifteen participants with PD completed five gamified AR exercises measured with both systems. Motor-state segments included straight walking, turning, squatting, and sit-to-stand/stand-to-sit transfers, from which the following mobility metrics were derived: step length, gait speed, cadence, transfer and squat durations, squat depth, turn duration, and peak turn angular velocity. We found excellent between-systems consistency for head position (X, Y, Z) and yaw-angle time series (ICC_(c,1) > 0.932). The AR-based motor-state classification showed high accuracy, with F1-scores of 0.947–1.000. Absolute agreement with Theia3D was excellent for all mobility metrics (ICC_(A,1) > 0.904), except for cadence during straight walking and peak angular velocity during turns, which were good and moderate (ICC_(A,1) = 0.890, ICC_(A,1) = 0.477, respectively). These results indicate that motor states and associated mobility metrics can be accurately derived during gamified AR exercises, verified in a controlled laboratory environment in people with mild to moderate PD, a necessary first step towards unobtrusive derivation of mobility metrics during in-clinic and at-home AR neurorehabilitation exercise programs. Full article

Foot drop, a form of paralysis affecting ankle and foot control, impairs walking and increases the risk of falls. Effective rehabilitation requires monitoring gait to guide personalized interventions. This study presents a proof-of-concept smart foot–ankle brace integrating low-cost sensors, including gyroscopes, accelerometers, and a Fiber Bragg Grating (FBG) array, with an Arduino-based processing platform. The system captures, in real time, the key locomotion parameters, namely, angular rotation, acceleration, and sole deformation. Experiments using a 3D-printed insole demonstrated that the device detects foot-drop-related gait deviations, with toe acceleration approximately twice that of normal walking. It also precisely detects foot deformation through FBG sensing. These results demonstrate the feasibility of the proposed system for monitoring gait abnormalities. Unlike commercial gait analysis devices, this work focuses on proof-of-concept development, providing a foundation for future improvements, including wireless integration, AI-based gait classification, and mobile application support for home-based or tele-rehabilitation applications. Full article

Lameness remains a significant welfare and productivity challenge in dairy farming, often underdiagnosed due to the limitations of conventional detection methods. Unlike most previous approaches to lameness detection that rely on a single-sensor or gait-based measurement, this study integrates four complementary data domains—behavioural, physiological, biochemical, and milk composition parameters—collected from 272 dairy cows during early lactation to enhance diagnostic accuracy and biological interpretability. The main objective of this study was to evaluate and compare the diagnostic classification performance of multiple machine learning (ML) algorithms trained on multimodal data collected at the time of clinical lameness diagnosis during early lactation, and to identify the most influential physiological and biochemical traits contributing to classification accuracy. Specifically, six algorithms—random forest (RF), neural network (NN), Ensemble, support vector machine (SVM), k-nearest neighbors (KNN), and logistic regression (LR)—were assessed. The input dataset integrated physiological parameters (e.g., water intake, body temperature), behavioural indicators (rumination time, activity), blood biochemical biomarkers (non-esterified fatty acids (NEFA), aspartate aminotransferase (AST), lactate dehydrogenase (LDH), gamma-glutamyl transferase (GGT)), and milk quality traits (fat, protein, lactose, temperature). Among all models, RF achieved the highest validation accuracy (97.04%), perfect validation specificity (100%), and the highest normalized Matthews correlation coefficient (nMCC = 0.94), as determined through Monte Carlo cross-validation on independent validation sets. Lame cows showed significantly elevated NEFA and body temperatures, reflecting enhanced lipid mobilization and inflammatory stress, alongside reduced water intake, milk protein, and lactose content, indicative of systemic energy imbalance and impaired mammary function. These physiological and biochemical deviations emphasize the multifactorial nature of lameness. Linear models like LR underperformed, likely due to their inability to capture the non-linear and interactive relationships among physiological, biochemical, and milk composition features, which were better represented by tree-based and neural models. Overall, the study demonstrates that combining sensor data with blood biomarkers and milk traits using advanced ML models provides a powerful, objective tool for the clinical classification of lameness, offering practical applications for precision livestock management by supporting early, data-driven decision-making to improve welfare and productivity on dairy farms. Full article

Gait analysis is essential in the evaluation of neuromuscular and musculoskeletal disorders; however, traditional approaches based on expert visual observation remain subjective and often lack consistency. Accurate and objective assessment of gait impairments is critical for early diagnosis, monitoring rehabilitation progress, and guiding clinical decision-making. Although Gait Energy Images (GEI) have become widely used in automated, vision-based gait analysis, they are limited in capturing boundary details and time-resolved motion dynamics, both critical for robust clinical interpretation. To overcome these limitations, we introduce four novel gait representation maps: the time-coded gait boundary image (tGBI), color-coded GEI (cGEI), time-coded gait delta image (tGDI), and color-coded boundary-to-image transform (cBIT). These representations are specifically designed to embed spatial, temporal, and boundary-specific features of the gait cycle, and are constructed from binary silhouette sequences through straightforward yet effective transformations that preserve key structural and dynamic information. Experiments on the INIT GAIT dataset demonstrate that the proposed representations consistently outperform the conventional GEI across multiple machine learning models and classification tasks involving different numbers of gait impairment categories (four and six classes). These findings highlight the potential of the proposed approaches to enhance the accuracy and reliability of automated clinical gait analysis. Full article

This study aims to explore the utility of artificial intelligence (AI) in classifying dementia severity based on gait analysis data and to examine how machine learning (ML) can address the limitations of conventional statistical approaches. The study included 34 individuals with mild cognitive impairment (MCI), 25 with mild dementia, 26 with moderate dementia, and 54 healthy controls. A support vector machine (SVM) classifier was employed to categorize dementia severity using gait parameters. As complexity and high dimensionality of gait data increase, traditional statistical methods may struggle to capture subtle patterns and interactions among variables. In contrast, ML techniques, including dimensionality reduction methods such as principal component analysis (PCA) and gradient-based feature selection, can effectively identify key gait features relevant to dementia severity classification. This study shows that ML can complement traditional statistical analyses by efficiently handling high-dimensional data and uncovering meaningful patterns that may be overlooked by conventional methods. Our findings highlight the promise of AI-based tools in advancing our understanding of gait characteristics in dementia and supporting the development of more accurate diagnostic models for complex or large datasets. Full article

Background/Objectives: Cognitive impairment in older adults is a growing public health concern due to global population aging. Early detection is crucial, yet current screening methods are time-consuming and require clinical expertise. Gait analysis has emerged as a promising alternative for cognitive screening. The aim of the study was to identify gait variables associated with cognitive impairment and to develop predictive algorithms capable of distinguishing between cognitively impaired and non-impaired older adults using gold-standard gait analysis. Methods: A cross-sectional study was conducted with 42 adults aged > 60 years. Cognitive function was assessed using the Mini-Mental State Examination (MMSE), and participants were divided into high (MMSE > 24) and low (MMSE ≤ 24) cognitive function groups. Spatiotemporal gait parameters were recorded at participants’ usual pace using the Optogait system. Logistic regression models were developed using half of the sample (training group) and validated in the remaining participants (verification group). Results: Algorithms based on stride length and double support time demonstrated high classification performance. In the training group, the best-performing model achieved an AUC-ROC of 0.91, with a sensitivity of 71.4% and specificity of 92.3%. Validation in the verification group yielded an AUC-ROC of 0.84 and accuracy of 81.0%. Alternative models showed acceptable to excellent predictive power. Conclusions: Gait analysis using gold-standard methods can effectively identify cognitive impairment in older adults. The developed algorithms offer a rapid, objective, and accurate screening alternative with strong potential for clinical application. Full article