Search Results (914)

Background/Objectives: This scoping review evaluates the use of computer vision (CV) for analyzing conventional video recordings of gait in older adults. In the rapidly evolving world of CV, methods that use conventional video recordings offer a practical and affordable solution to quantifying gait impairments, especially in resource-limited areas. In this review, we evaluate the aims, methods, variables, and validation of the literature utilizing videos of gait in older adults. Methods: Inclusion criteria were limited to journal articles and conference papers published between 2020 and 2025. Three reviewers extracted data from selected articles. Results: The search identified 46 studies that demonstrate a wide variety of clinical conditions, methodological approaches, and analyzed variables. Three main aims emerged, with 15 screening studies for clinical conditions, 14 studies classifying severity or mobility levels, 16 characterization studies of healthy and pathological gait, and one person-identification study. Methodological approaches ranged across 35 studies utilizing commercially available cameras, six studies utilizing conventional video from specialized cameras, two using surveillance-style cameras, and four that did not specify. Methods of validation were inconsistent, comparing either to lab-based biomechanical gold standards or broad clinical labels, with limited interdisciplinary validation through both methods. Conclusions: This scoping review demonstrates methodological growth and diversification in CV-based gait analysis using conventional video in older adults. The available evidence primarily supports technical feasibility and preliminary screening or classification performance rather than established clinical validity. Standardized methods and external, longitudinal, and real-world validation are needed before these approaches can reliably support routine clinical decision-making. Full article

Background/Objectives: Sciatica and hip osteoarthritis (OA) are common causes of lower extremity pain and functional impairment. Because both conditions may produce overlapping symptoms, distinguishing them can be challenging. Misdiagnosis may lead to inappropriate treatment, delayed intervention and unnecessary procedures. In addition, the frequent coexistence of hip and lumbar degenerative pathology, commonly referred to as hip–spine syndrome, further complicates diagnostic evaluation. This review aims to examine current diagnostic strategies used to differentiate lumbar radiculopathy from hip OA and to introduce the Athena Sign, which is presented as a preliminary, hypothesis-generating clinical observation requiring prospective validation. Methods: A narrative review of the literature was performed focusing on the pathophysiology, clinical presentation, differential diagnosis, physical examination and imaging evaluation of sciatica and hip OA. Particular emphasis was placed on clinical examination techniques and diagnostic injections used to identify the primary pain generator. Results: Both conditions share overlapping symptom patterns and inflammatory mechanisms, which may obscure the source of pain. Careful assessment of gait, hip range of motion, neurological findings and provocative maneuvers remains essential for accurate diagnosis. Imaging findings should be interpreted in conjunction with clinical examination due to the high prevalence of asymptomatic degenerative changes. The Athena Sign, observed with internal and external rotation of the hips in a prone position with the knee flexed, is associated with anterior intra-articular hip pathology and may provide an additional diagnostic indicator in patients with ambiguous hip–spine presentations. Conclusions: A systematic diagnostic approach integrating clinical examination, imaging and targeted diagnostic injections is essential for distinguishing between lumbar radiculopathy and hip OA. Recognition of dynamic clinical findings such as the Athena Sign may further improve diagnostic accuracy and guide appropriate management in patients presenting with overlapping hip and lumbar symptoms. Full article

(1) Background/Objectives: Sarcopenia is common in older surgical candidates and may affect perioperative risk and recovery after total hip arthroplasty (THA). Quantifying its burden and severity gradient in THA pathways can inform surgeon-led optimization. (2) Methods: A cross-sectional analysis of baseline preoperative data at a tertiary center (December 2019 to December 2022) was conducted. Consecutive adults with hip osteoarthritis undergoing primary THA were screened. Sarcopenia was staged per EWGSOP2: probable (low handgrip), confirmed (probable and low skeletal muscle index by whole-body DXA), and severe (confirmed and low gait speed). (3) Results: Of 312 screened patients, 203 completed baseline assessment (95 men, 108 women). According to the EWGSOP2 algorithm, 57 patients (28.1%; 95% CI 22.3–34.6%) had low handgrip strength, 30 (14.8%; 95% CI 10.6–20.3%) fulfilled criteria for confirmed sarcopenia, and 21 (10.3%; 95% CI 6.9–15.3%) had severe sarcopenia. No significant association was observed for sex. Sarcopenia diagnosis was associated with older age, lower body mass index (BMI), higher comorbidity burden, lower functional independence, greater cognitive impairment, poorer mental health, and worse hip-related function (all p < 0.05). In multivariable analysis, older age (OR 1.51 per 5-year increase; 95% CI 1.11–2.12), lower BMI (OR 0.88 per kg/m²; 95% CI 0.79–0.98), and lower functional independence (Barthel Index: OR 2.02 per 10-point decrease; 95% CI 1.20–3.60) were independently associated with confirmed sarcopenia. Across EWGSOP2 categories, differences in age, BMI, pain, comorbidity, functional independence, cognition, mental health and hip function showed significant differences (all p < 0.05), with ordered trends in most domains but no uniform monotonic pattern. (4) Conclusions: In THA candidates, sarcopenia is prevalent and is related to older age, lower BMI and lower functional independence. Integrating sarcopenia screening by EWGSOP2 may help to identify THA candidates with greater clinical vulnerability who may warrant further preoperative assessment and targeted optimization strategies. Full article

Background: Vitamin D deficiency in older adults may impair muscle function and physical performance. This prospective observational cohort study examined the 12-month outcomes of vitamin D supplementation, delivered as part of routine clinical care, in older adults with vitamin D deficiency compared with an insufficiency comparison group. Methods: A total of 194 participants aged ≥60 years were enrolled: 164 with vitamin D deficiency (25(OH)D <20 ng/mL; supplementation group) and 30 with insufficiency (20–29 ng/mL; comparison group). The supplementation group received supplementation targeting 25(OH)D >30 ng/mL; the comparison group received no supplementation. The Handgrip Strength Test (HGS), the Gait Speed Test (GST), the Short Physical Performance Battery Test (SPPB), and the Timed Up and Go Test (TUG) were assessed at baseline and 12 months. Results: Supplementation raised 25(OH)D by 142.9% versus 5.4% in the comparison group (p < 0.001). For the primary outcome, the supplementation group showed a 16.2% increase in the HGS versus no change in the comparison group (p < 0.001; ANCOVA partial η² = 0.284). For the secondary outcomes, the comparison group was associated with a significant functional decline relative to the supplementation group: the median change on the SPPB in the comparison group was 0.0% (IQR: −8.7, 0.0; between-group p < 0.001) and the TUG worsened by +3.2% (between-group p < 0.001), while the supplementation group remained stable. The ANCOVA indicated between-group differences on the SPPB (p < 0.001) and TUG (p = 0.002). Gait speed showed no significant difference. Conclusions: Vitamin D supplementation was associated with more favourable functional outcomes across multiple musculoskeletal domains in vitamin D-deficient older adults. The comparison group’s deterioration on the SPPB and TUG is consistent with an association between correcting deficiency and preserved function. Full article

Background/Objectives: Wolfram syndrome is an ultra-rare, progressive multisystem disorder in which endocrine and sensory manifestations coexist with neurological involvement. Quantitative magnetic resonance imaging (MRI) may help characterize central nervous system involvement in this condition; however, evidence derived from small imaging cohorts requires cautious interpretation. This study aimed to examine the relationships between different MRI-derived attributes and neurological symptoms in Wolfram syndrome, with the goal of identifying exploratory imaging patterns that may suggest the involvement of specific neural systems. Methods: We analyzed a Spanish cohort of 45 genetically confirmed patients with Wolfram syndrome. A homogeneous subset of 15 patients with standardized 3-Tesla multimodal MRI and adequate image quality was included in the quantitative imaging analysis. T1-weighted MRI, T2-weighted/fluid-attenuated inversion recovery (FLAIR) imaging, and diffusion tensor imaging (DTI) were processed using a standardized workflow for brain extraction, anatomical segmentation, cortical reconstruction, and quantitative feature extraction. A total of 172 MRI-derived features were examined in relation to neurological phenotypes, including dysphagia, ataxia, gait instability, and cognitive impairment. Analyses included principal component analysis, exploratory factor analysis, correlation analyses, and symptom-specific group comparisons. Given the small MRI sample size and the high feature-to-subject ratio, all analyses were considered exploratory and hypothesis-generating, and the findings should be interpreted cautiously pending validation in larger, independent cohorts. Results: Multimodal MRI-derived features showed distributed associations with neurological manifestations. The most recurrent exploratory imaging correlates involved the thalamus, lateral geniculate nucleus, cerebellum, brainstem, ventricular system, corpus callosum, posterior cortical regions, and white-matter pathways. FLAIR-derived signal heterogeneity in the thalamus and lateral geniculate nucleus appeared repeatedly across several clinical manifestations. Dysphagia was associated with a distributed pattern involving cortical thinning, thalamic and brainstem volume reduction, reduced cerebellar white-matter integrity, increased FLAIR heterogeneity, and ventricular enlargement. Ataxia and gait instability showed overlapping but partially distinct imaging profiles, whereas cognitive impairment was associated with broader cortical, subcortical, callosal, cerebellar, and ventricular alterations. Conclusions: In this exploratory pilot study, multimodal MRI-derived features showed clinically plausible associations with neurological manifestations in Wolfram syndrome. The findings support a distributed model of neurological involvement affecting cerebello-thalamo-cortical circuits, visual relay structures, brainstem pathways, and long-range white-matter connections. These results should be interpreted as exploratory MRI-derived attributes rather than as validated biomarkers, prognostic indicators, or clinically applicable imaging signatures. Confirmation in future longitudinal, multicenter studies with harmonized imaging protocols and external validation will be required. Full article

Background: Aging is marked by a series of changes that impair mobility. These changes are accompanied by declines in balance, postural control, and cognitive function. While the relationship between balance, postural control, and mobility has been extensively investigated, evidence on how different cognitive demands influence mobility performance in daily life remains limited. Accordingly, this study investigated how different cognitive demands associated with cell phone use affect mobility performance in young and older adults. Methods: In this cross-sectional study, 124 cognitively preserved participants (n = 62 young and n = 62 older adults) were enrolled. The participants were subjected to three walking conditions: without distraction, while texting, and while talking on the phone. Wearable motion sensors were used to quantify mobility performance across different task-specific components. Age and cognitive function were assessed to investigate their roles in mobility performance. Results: Older adults exhibited poorer gait performance than young adults, demonstrating longer completion times across multiple functional mobility tasks. Texting and phone conversations adversely affected gait performance to a similar extent. Age explained up to 42.4% of the variability in mobility performance during dual task, whereas cognitive function accounted for an additional 16.6% of the variance. Conclusions: In a cognitively preserved sample, the negative impact of cell phone use while walking was greater in older than in young adults. Age was the primary determinant of mobility performance while cognition played a lesser role. These findings support the need for interventions addressing age-related changes and cognitive demands to improve mobility in older adults. Full article

Walking recovery is a central goal of geriatric rehabilitation, but it is shaped by multiple interacting factors rather than by muscle impairment alone. This mini-review examines whether sarcopenia-related weakness, low muscle quality, and reduced physical reserve identify a clinically important vulnerability phenotype relevant to delayed gait recovery in older adults after hospitalization, hip fracture, surgery, or cardiac procedures. We summarize current consensus definitions of sarcopenia, explain why muscle strength and physical performance are often more clinically informative than muscle mass alone, and review the mechanistic pathways that may connect sarcopenia with impaired walking, including anabolic resistance, inflammation, disuse, neuromuscular remodeling, trunk weakness, and cognitive–emotional modifiers. Across community, orthogeriatric, post-acute, and cardiac rehabilitation settings, sarcopenia markers are generally associated with slower gait or poorer attained mobility; however, findings for change in mobility are inconsistent, and most available studies are observational, heterogeneous, or indirect. Sarcopenia should therefore be interpreted as one potential marker of reduced reserve and mobility risk rather than as a determinant of walking recovery or evidence that sarcopenia-aware rehabilitation improves outcomes. Future work should use more consistent diagnostic frameworks and test whether a sarcopenia-aware rehabilitation integrating early strength assessment, individualized nutrition care, and multicomponent gait rehabilitation improve walking outcomes in medically complex older adults beyond current standards of care. Full article

Cerebral palsy is a leading cause of childhood motor disability, and ambulatory children with spastic hemiplegia commonly present with dynamic equinus, calf muscle overactivity, and gait impairment. Evidence on focal vibration after botulinum toxin type A injection remains limited. This exploratory proof-of-concept pilot study assessed short-term changes following a four-week multimodal rehabilitation program incorporating focal vibration. In this uncontrolled single-group pre–post study, nine ambulatory children (mean age, 12.1 years), all classified as level II on the Gross Motor Function Classification System, received onabotulinumtoxinA injections into the affected gastrocnemius muscles, followed by twelve outpatient sessions combining focal vibration, conventional physiotherapy, and robotic gait training. Passive ankle dorsiflexion increased, calf muscle spasticity decreased, and selected gait parameters improved. Walking speed increased from 0.79 to 0.90 m per second, an absolute change of 0.11 m per second, comparable in magnitude to published estimates of clinically important change in ambulatory children with cerebral palsy. After Bonferroni correction, only walking speed and affected-limb stride length remained significant. No adverse events occurred. These findings describe outcomes associated with the combined program but do not establish the efficacy or independent contribution of focal vibration. Full article

Background: Falls in older adults are a major public health and rehabilitation concern and may reflect interacting chronic disease-related mechanisms rather than diagnostic labels alone. Type 2 diabetes mellitus (T2DM), hypertension (HTN), and osteoarthritis (OA) are common in later life and may influence fall vulnerability through sensory, vascular, musculoskeletal, cognitive, medication-related, and functional pathways. This scoping review aimed to map mechanism-oriented evidence linking T2DM, HTN, and OA to falls and fall-related outcomes in older adults. Methods: A scoping review was conducted in accordance with established scoping review methodology and PRISMA-ScR guidance. PubMed, Web of Science, and Embase were searched for English-language studies published from 2016 to 2026; the final search was conducted on 15 April 2026. Evidence was charted in a structured table and synthesised descriptively and thematically across disease-specific and shared mechanism domains. Results: A total of 151 studies were included. The evidence was organised into T2DM-related sensory-neural, gait and balance, vestibular/visual-cognitive, strength-related, and glycaemic or medication-related mechanisms; HTN-related haemodynamic, cerebral perfusion, dizziness/syncope, and medication-related mechanisms; and OA-related pain, proprioceptive, strength-related, gait and balance, psychological, and compensatory-control mechanisms. Shared pathways included frailty, multimorbidity, polypharmacy, pain burden, cognitive impairment, sleep disturbance, ADL decline, dizziness, and reduced physical function. Conclusions: Falls in older adults with T2DM, HTN, OA, or multimorbidity may be better understood through interacting disease-specific and shared mechanisms than through diagnostic labels alone. Future longitudinal and multimorbidity-specific studies using standardised fall ascertainment are needed to test these pathways more directly. Full article

Introduction: Chronic stroke frequently causes structural and functional impairments in the tibialis anterior (TA) muscle, leading to foot-drop and altered gait kinematics. We investigated the relationship between ultrasonographic parameters of the TA muscle and functional gait performance in chronic stroke survivors. Methods: This cross-sectional, observational pilot study evaluated eight consecutive chronic stroke patients (>6 months post-stroke). Structural parameters of TA (rest and contraction thickness, pennation angle) were documented by ultrasound imaging. A dynamic feature calculated was the Contraction Index (CI = effort/resting thickness). Functional metrics included the Medical Research Council (MRC) muscle strength scale and the 10-Meter Walk Test (10MWT) for gait velocity. Results: Statistical analysis revealed a moderate negative correlation trend between resting TA muscle thickness and functional gait speed (r = −0.618, p = 0.102). Conversely, a moderate positive correlation trend was found (r = 0.548, p = 0.160). Ultrasound imaging successfully differentiated three distinct pathological phenotypes: an atrophic phenotype (low pennation angle, flaccid muscle failure), a severely shortened spastic phenotype (increased resting thickness, high pennation angle, pathological CI < 1.0), and a spastic co-contraction loop. Patients with the atrophic phenotype achieved high mechanical efficiency with an ankle–foot orthosis (AFO), whereas the spastic phenotype exhibited resistance against the orthotic device. Conclusions: Musculoskeletal ultrasound provides objective parameters for post-stroke TA muscle remodeling and contributes to completing the assessment and therapy. Identifying specific structural muscle phenotypes allows clinicians to optimize target-specific neurorehabilitation strategies, predict AFO efficiency, and guide antispastic interventions such as botulinum toxin injections. Full article

Gait symmetry analysis has emerged as an important tool in rehabilitation engineering and neurological disorder assessment, as it provides clinically relevant indicators of mobility impairment and gait abnormalities. The proposed framework integrates gait symmetry variability, statistical gait features and Dynamic Time Warping (DTW)-based temporal alignment to enhance robustness against gait variations and irregular walking patterns. A hybrid feature vector comprising DTW similarity scores, the hybrid gait symmetry index (GSI), and statistical gait descriptors was employed to classify gait patterns into five categories: normal, slow, medium, fast, and abnormal. The system was implemented as a wearable edge-computing platform using an NI myRIO device equipped with a tri-axial Inertial Measurement Unit (IMU) mounted on the subject’s body. The onboard FPGA performs real-time signal preprocessing, GSI computation, feature extraction, constrained DTW matching, and gait classification using fixed-point streaming architectures and BRAM-based buffering. Meanwhile, the embedded ARM processor manages TCP/IP communication and transmits real-time gait information to a remote monitoring workstation via a WiFi interface for visualization and analysis. Operating at a clock frequency of 100 MHz, the complete architecture achieves an end-to-end processing latency of approximately 4 ms. The proposed FPGA-based implementation provides low-latency, energy-efficient, and real-time gait analysis, making it well suited for wearable rehabilitation systems, assistive healthcare devices, and continuous mobility monitoring applications. Full article

Background: Physical activity plays a vital role in caring for people with multiple sclerosis (MS). Yet, challenges like fatigue, mobility impairment, fall risk, symptom fluctuation, and poor access to rehabilitation often make sustained participation difficult. Adhering to physical activity programmes is tough. Artificial intelligence (AI) may transform wearable, smartphone, clinical, and patient-reported data into interpretable information for monitoring, prediction and individualized support. Objective: Building on the identified need for individualized support, this scoping review mapped original AI-based studies relevant to physical activity, gait, mobility, ambulation, fatigue, fall risk, and real-world functioning in people with MS. Methods: The review followed PRISMA-ScR principles. Search covered records published from 1 January 2016 to 14 May 2026 across biomedical, rehabilitation, technology-oriented, trial registry, and citation-searching sources. Eligible studies included MS or MS-specific data, an explicit AI/ML or model-derived predictive analytics component, and an activity-related clinical domain. Results: The search identified 332 records/reports. After removing 127 duplicates, 205 records were screened, 45 full texts were assessed, and 21 original AI studies met the eligibility criteria. These addressed inertial sensor deep learning, wearable gait speed estimation, postural sway fall risk prediction, connected device prediction of fatigue and health state, smartphone-based ambulation characterization, treadmill or walkway gait classification, chair stand fall status prediction, daily life gait/turning fall prediction, fear-of-falling detection, sensor-derived fatigue prediction, mobile/wearable modelling of MS, and physical activity prediction. Conclusions: AI can extract clinically relevant patterns from gait, wearable, smartphone, connected device, clinical, and patient-reported data in MS. However, evidence does not yet show that AI-supported systems improve physical activity, adherence, fatigue burden, fall risk, quality of life, or functional independence. AI is therefore promising but early, and prospective, externally validated, human-supervised, fatigue-aware, safety-sensitive studies are needed to support clinically meaningful, patient-centred MS rehabilitation and activity planning. Full article

Background: Parkinson’s disease (PD) diagnosis is often delayed until signature motor symptoms manifest, at which point profound dopaminergic neuron loss has already occurred, necessitating advanced motor diagnostic biomarkers. Quantitative gait analysis is a promising tool, but phase-specific kinematic parameters remain underexplored. This study aims to identify novel, stage-divided Timed Up and Go (TUG) biomarkers not only to differentiate healthy controls (HCs) from patients with PD but also to objectively monitor and track disease progression across advancing severity stages, which are further validated against conventional clinical motor scales. Methods: A total of 81 participants (48 PD, 33 HCs) performed a 3 m TUG test using MotionCore (JEIOS Inc., Busan, Republic of Korea). The test was subdivided into three movement phases (Stage 1, sit-to-walk; Stage 2, turning; Stage 3, walk-to-sit). Results: PD patients exhibited significantly prolonged durations and altered turning metrics compared to HCs. Turning parameters including turning radius (ETR), area (EMA), and turning stability (FN) demonstrated strong correlations with disease severity and clinical scales. Notably, stage-specific analyses revealed that step counts, time, and speed metrics across Stages 1, 2, and 3 effectively differentiated disease severity, with transitional decelerating and seating metrics in Stage 3 showing the most pronounced clinical correlations. Discussion: This study confirms that the TUG test systematically deteriorates with increasing PD severity. The robust correlations with clinical scales (UPDRS, FOG-Q, BBS) validate TUG metrics as objective measures of motor and balance impairments. Utilizing novel, staging-specific indices significantly enhances the TUG test’s clinical utility for supporting diagnosis, accurate staging, and monitoring disease progression. Although the overall group comparisons demonstrated statistical significance, a data overlap remains between mild PD and HCs, underscoring the need for large-scale longitudinal studies to validate these metrics for early detection. Full article

Background and Clinical Significance: Alien hand syndrome (AHS) is a rare disorder of agency and complex motor control characterized by involuntary, apparently purposeful limb movements experienced as outside voluntary control. Pontine hemorrhage is an uncommon substrate, and its manifestations may overlap with sensory ataxia and other post-stroke movement disorders. Case Presentation: An 86-year-old right-handed man developed right-sided alien hand phenomena after a left pontine hemorrhage. Examination showed dysarthria, limited left gaze, diplopia, preserved muscle strength, marked right-sided proprioceptive impairment, a thalamic-hand-like posture, impaired spatial control, involuntary levitation, intermanual conflict, and purposeful-appearing rubbing movements when distracted. The diagnosis was based on loss of agency and autonomous limb behavior that could not be explained by sensory ataxia alone. Serial CT demonstrated an interval reduction in the size of the pontine hemorrhage; a representative thalamic level CT showed no evident thalamic hemorrhage or gross structural lesion, although a small CT occult ischemic lesion could not be excluded. Repeat MRI was not completed because of severe claustrophobia and anesthesia risk. EEG, formal neuropsychological testing, and standardized functional scales were unavailable. The NIHSS, assessed 15 days after admission to our hospital, was 6 points. No specific pharmacological treatment was initiated. Cognitive-behavioral rehabilitation was recommended, but transportation difficulties prevented regular attendance. Approximately three months after discharge, physician relatives reported resolution of abnormal movements and improved independent gait; no formal post-discharge examination was performed. Conclusions: Pontine hemorrhage may rarely be associated with mixed AHS phenomenology. Disruption of ascending proprioceptive and sensorimotor pathways is plausible, but the absence of advanced imaging and neurophysiological assessment precludes definitive anatomical or causal conclusions. Full article

Parkinson’s disease (PD) is associated with gait impairment, bilateral asymmetry, and increased gait variability, highlighting the need for objective and interpretable wearable gait assessment. Plantar insole recordings directly capture foot–ground loading, but their use in PD assessment is often limited by global or low-order descriptors that do not fully represent regional loading organization. This study proposes a region-specific information-theoretic framework for PD gait assessment using wearable plantar-pressure insoles. Bilateral plantar insole signals were reorganized into five anatomical regions: heel, rearfoot, midfoot, forefoot, and toe. Self-information index (SII), Shannon entropy (EN), negentropy (NEG), sample entropy (SEN), and Kullback–Leibler divergence (KL) features were extracted to characterize self-information fluctuation, probabilistic uncertainty, non-Gaussian organization, temporal irregularity, and directional distributional discrepancy in plantar-pressure dynamics. The resulting feature representation was evaluated at gait-cycle, walking-recording, and subject-independent levels using conventional classifiers, ablation analysis, subject-balanced cycle aggregation, and an information-theoretic three-dimensional feature-space rule model (ITFS-RM). KNN achieved an accuracy of 0.9668 at the gait-cycle level, and MLP achieved an accuracy of 0.9344 at the walking-recording level. Under stricter subject-independent evaluation, the accuracy was 0.8475, and subject-balanced-cycle aggregation achieved an accuracy of 0.8655. Region-specific analysis and ablation experiments showed spatially heterogeneous HC–PD differences, with the toe region showing the most consistent contribution. SII, KL, and NEG provided stable discriminative contributions, particularly in toe-related and regional-transition features. ITFS-RM provided explicit feature combinations, value ranges, and spatial rule boundaries for interpretable walking-recording level and subject-grouped separation. These results support region-specific information-theoretic analysis as an interpretable representation of plantar-pressure dynamics for PD gait assessment and emphasize the need for subject-wise validation when repeated walking recordings are available. Full article