Search Results (578)

Background: Artificial Intelligence (AI) and Machine Learning (ML) are increasingly integrated into sport and exercise through wearable biosensing systems that enable continuous monitoring and data-driven training adaptation. However, their practical value for coaching depends on the validity of biosensor data, the robustness of analytical models, and the conditions under which these systems have been empirically evaluated. Methods: A structured narrative review was conducted using Scopus, PubMed, Web of Science, and Google Scholar (2010–2026), synthesising empirical and applied evidence on wearable biosensing, signal processing, and ML-based adaptive training systems. To enhance transparency, an evidence map of core empirical studies was constructed, summarising sensing modalities, cohort sizes, experimental settings (laboratory vs. field), model types, evaluation protocols, and key outcomes. Results: Evidence from field and laboratory studies indicates that wearable biosensors can reliably capture physiological (e.g., heart rate variability), biomechanical (e.g., inertial and electromyographic signals), and biochemical (e.g., sweat lactate and electrolytes) markers relevant to training load, fatigue, and recovery, provided that signal quality control and calibration procedures are applied. ML models trained on these data can support training adaptation and recovery estimation, with improved performance over traditional workload metrics in endurance, strength, and team-sport contexts when evaluated using athlete-wise or longitudinal validation schemes. Nevertheless, the evidence map also highlights recurring limitations, including sensitivity to motion artefacts, inter-session variability, distribution shift between laboratory and field settings, and overconfident predictions when contextual or psychosocial inputs are absent. Conclusions: Current empirical evidence supports the use of AI-driven biosensor systems as decision-support tools for monitoring and adaptive training, but not as autonomous coaching agents. Their effectiveness is bounded by sensor reliability, appropriate validation protocols, and human oversight. The most defensible model emerging from the evidence is human–AI collaboration, in which ML enhances precision and consistency in data interpretation, while coaches retain responsibility for contextual judgement, ethical decision-making, and athlete-centred care. Full article

Background/Objectives: Neuromuscular functions (NMFs) encompass biomechanical and viscoelastic properties that are essential for coordinated movement and muscular control. While NMFs have been extensively investigated in the lower limb, normative data for the upper extremity remain limited, particularly regarding the interaction between neuromuscular properties, superficial fascia, and body composition. As body composition and fascial characteristics may influence neuromuscular behavior and the interpretation of mechanical measurements, this study aimed to establish reference values for upper limb NMF, analyze dominance-related differences, and investigate the relationship between superficial fascia thickness and body mass composition. Methods: A descriptive, non-experimental study was conducted involving 61 healthy adults (122 upper limbs). Assessments included body composition (bioimpedance), superficial fascia thickness (skinfolds), viscoelastic properties (MyotonPro), and isometric strength (handheld dynamometry). Standardized protocols were applied for all measurements. Comparisons were performed between sexes and between dominant and non-dominant limbs. Correlation analyses explored associations between NMF, adiposity, and fascia parameters. Results: Dominant limbs showed slightly greater strength; however, these differences were not statistically significant. Viscoelastic properties were largely symmetrical between limbs, with minimal dominance-related differences. Clear sex differences were observed: men demonstrated greater strength, lean mass, and increased stiffness, whereas women presented higher skinfold thickness and lower muscle tone. Weak correlations were identified between stiffness, relaxation, and strength, as well as between adiposity and superficial fascia thickness. Greater adipose thickness was associated with lower stiffness values in the triceps (rho= −0304; iC95% 0.041/0.528; p = 0.017). Conclusions: Upper limb neuromuscular properties exhibit high bilateral symmetry, with limb dominance influencing strength. Sex and body composition significantly modulate both viscoelastic and functional parameters. These findings provide normative reference values and highlight the relevance of considering body composition and fascial characteristics when assessing neuromuscular function in clinical and sports contexts. Full article

Precise foot contact detection (FCD) is essential for accurate biomechanical analysis in sport performance, injury prevention, and rehabilitation. This study developed and validated an inertial measurement units (IMUs)-based algorithm for FCD during sports movements. Thirty-four healthy athletes (22.8 ± 4.1 years old) performed 90° changes of direction and sprints with deceleration. Data were collected via a force platform (AMTI, 1000 Hz) and a full-body IMU suit (MTw Awinda, Movella, 60 Hz). Two IMU-based algorithms relying on pelvis vertical velocity (PVV) and resultant foot acceleration (RFA), respectively, were tested to detect initial contact (IC) and toe-off (TO). Force platform data served as the gold standard for comparison. Agreement was quantified through median offset and interquartile range (IQR); the influence of task, sex, leg, speed, and acceleration was investigated. The PVV algorithm showed higher offset than RFA for IC detection (16.7 ms vs. 10.2 ms) with comparable IQR and a substantially higher offset for TO (102.8 ms vs. 20.4 ms). Minimal influence of co-factors emerged (variance < 10%). Results were sensibly improved by combining PVV and RFA, for both IC (5.6 [70.4] ms) and TO (20.4 [78.7] ms). This algorithm offers a robust, portable alternative to force platforms, enabling accurate footstep detection and analysis of complex, sports movements in real-world environments, enhancing the ecological validity of sport assessments. Full article

Background/Objectives: Noncontact knee ligament injuries, including anterior cruciate ligament (ACL) ruptures and medial collateral ligament (MCL) sprains, are prevalent in sports that involve frequent cutting and pivoting. Conventional rigid knee braces can offer stability but often compromise comfort and performance, whereas soft sleeve-type supports provide minimal mechanical protection. The purpose of this study was to evaluate the acute biomechanical effects of a tensioned cable knee bracing system on peak knee valgus angle and external knee abduction moment during a controlled lateral shuffle task. Methods: Ten physically active adults (mean age 21.7 ± 3.8 years) performed submaximal lateral shuffle movements under three conditions: unbraced, sleeve-only (zero-tension), and a novel tensioned cable brace. Three-dimensional knee kinematics and ground reaction forces were collected, and peak knee valgus angle and external abduction moment were calculated during the eccentric phase of each movement. Results: Wearing the knee brace under tension significantly reduced knee valgus angle (4.5° vs. 7.9°) and peak external knee abduction moment (1.6 vs. 2.0–2.1 Nm/kg) compared to the unbraced condition. Conclusions: These findings indicate that the tensioned cable brace effectively reduced frontal plane knee loading during a lateral shuffle task, indicating its potential as an effective bracing approach. Full article

Soccer is the most widely practiced sport globally, but is also associated with a high incidence of lower limb injuries. Among multiple risk factors, soccer footwear represents a crucial biomechanical interface affecting traction, proprioception, and joint loading. This narrative review aims to explore how each component of modern soccer footwear impacts performance and injury risk, with a focus on evidence-based functional customization. A comprehensive narrative review of available literature was conducted across PubMed, Scopus, and Web of Science, integrating biomechanical, clinical, and materials science studies. We included studies concerning the structures composing soccer technical footwear. Conical studs were associated with reduced rotational stiffness and lower joint torque, while bladed studs enhanced linear traction but increased ACL strain risk. Upper materials, such as knitted fabrics and engineered mesh, improve proprioception and thermal regulation but show trade-offs in durability and protection. Soleplate stiffness influenced load distribution and performance: increased stiffness improves sprinting but compromises multidirectional agility. Fatigue and proprioception were modulated by insole and soleplate synergy. Soccer footwear should be seen as a clinical and performance tool requiring evidence-based customization. Advances in material technology, 4D foot scanning, and plantar pressure mapping enable functional matching between footwear and athlete characteristics. Translating these insights into player-specific footwear designs may reduce injury rates and enhance on-field performance. Full article

This study assessed the accuracy of the EXERGEN TAT-5000 temporal scanner (T_EXERGEN) (EXERGEN, Watertown, MA, USA) for estimating core body temperature (T_CORE) during rest, progressive cycling exercise, and post-exercise recovery in a hot environment. Fourteen healthy adults (7 men and 7 women) completed a laboratory protocol consisting of 10 min of rest, 60 min of cycling, and 25 min of recovery at an ambient temperature of 32 °C and a relative humidity of 60%. Gastrointestinal temperature (T_Gi), measured via telemetry capsules, served as the criterion method. A total of 5376 paired measurements were analyzed. Throughout the protocol, T_EXERGEN systematically underestimated T_CORE compared with T_Gi, with mean biases between −0.35 °C and −1.15 °C. The overall 95% confidence intervals ranged from ±0.91 to ±1.43 °C, demonstrating poor precision. Limits of agreement were wide (from −2.00 to 0.87 °C), and concordance correlation coefficients (CCC) indicated poor agreement (CCC < 0.90 in all conditions). The underestimation was more pronounced during exercise and recovery, when T_CORE remained high according to T_Gi but decreased according to T_EXERGEN. These results indicate that T_EXERGEN does not monitor T_CORE accurately under heat stress or during rapid metabolic changes. Therefore, the use of this device is not recommended during and after exercises under environmental heat stress. Full article

This study investigated the effects of 6 weeks of plyometric training (PT) performed on soft (unstable) and hard (stable) surfaces compared with conventional training on the balance, explosive power, and muscle strength of adolescent female basketball players. The participants were randomly assigned to three groups: soft-surface PT (n = 14), hard-surface PT (n = 14), and conventional training (n = 14). Performance outcomes included 30 m sprint time, vertical jump height, plantar flexion and dorsiflexion maximal voluntary isometric contraction (MVIC) torque, Y-balance dynamic balance, and center of pressure-based static balance. Ground reaction forces, MVIC torques, and balance parameters were measured using high-precision force sensors to ensure accurate quantification of biomechanical performance. Statistical analyses were performed using two-way repeated-measures ANOVA with post hoc comparisons to evaluate group × time interaction effects across all outcome variables. Results demonstrated that soft- and hard-surface PT significantly improved sprint performance, vertical jump height, and plantar flexion MVIC torque compared with conventional training, while dorsiflexion MVIC increased similarly across all the groups. Notably, soft-surface training elicited greater enhancements in vertical jump height, dynamic balance (posteromedial and posterolateral directions), and static balance under single- and double-leg eyes-closed conditions. The findings suggest that PT on an unstable surface provides unique advantages in optimizing neuromuscular control and postural stability beyond those achieved with stable-surface or conventional training. Thus, soft-surface PT may serve as an effective adjunct to traditional conditioning programs, enhancing sport-specific explosive power and balance. These results provide practical guidance for designing evidence-based and individualized training interventions to improve performance and reduce injury risk among adolescent female basketball athletes. Full article

Background: This study aimed to explore the effects of neuromuscular electrical stimulation (NMES) combined with water-based resistance training on muscle activation and coordination during freestyle kicking. Methods: Thirty National Level male freestyle swimmers were randomly assigned to an experimental group (NMES + water-based training) or a control group (water-based training only) for a 12-week intervention. The experimental group received NMES pretreatment before each session. Underwater surface electromyography (sEMG) synchronized with high-speed video was used to collect muscle activation data and corresponding kinematic information during the freestyle kick. The sEMG signals were then processed using time-domain analysis, including integrated electromyography (iEMG), which reflects the cumulative electrical activity of muscles, and root mean square amplitude (RMS), which indicates the intensity of muscle activation. Non-negative matrix factorization (NMF) was further applied to extract and characterize muscle synergy patterns. Results: The experimental group showed significantly higher iEMG and RMS values in key muscles during both kicking phases. Within the core propulsion synergy, muscle weighting of vastus medialis and biceps femoris increased significantly, while activation duration of the postural adjustment synergy was shortened. The number of synergies showed no significant difference. Conclusions: NMES combined with water-based resistance training enhances muscle activation and optimizes neuromuscular coordination strategies, offering a novel approach to improving sport-specific performance. Full article

Basketball is an intermittent sport with high neuromuscular and metabolic demands. To optimize specificity, training tasks should replicate competitive loads, but little is known about how drills compare to official matches. This study compared the physiological and biomechanical load of training tasks with official competition in elite U18 basketball players. Twelve male players (16.9 ± 0.8 years) were monitored across two seasons (179 training sessions, 21 matches). A total of 3136 individual records were collected using Catapult Vector S7 LPS units. Training drills were classified by specificity (0–5). Physiological (distance and intensity zones) and biomechanical variables (accelerations, decelerations, jumps, explosive efforts, PlayerLoad™) were analyzed using cluster analysis and linear mixed models. Competition imposed the highest physiological and biomechanical loads. Non-opposition drills (1v0–5v0) showed limited transfer, though 1v0–2v0 accumulated higher jump density. Among opposition formats, 3v3 full-court was the best at replicating match demands. Continuous opposition tasks (3v3v3, 4v4v4, 5v5v5) elicited lower physiological but comparable biomechanical load. Small-sided formats, particularly 3v3 and 4v4, are the most effective training tools for reproducing competition demands, while non-opposition drills are better suited for technical or rehabilitation purposes. Full article

Indoor bouldering is a popular and rapidly growing sport in which climbers fall repeatedly from walls up to 4–5 m high, making lower-limb injuries common. It is therefore essential to understand fall kinematics and impact conditions, yet fall kinematics remain poorly documented because laboratory motion capture is impractical in gyms. This study aimed to validate a markerless multi-camera pipeline (Pose2Sim) against a 2D video annotation tool (Kinovea) for displacement and velocity measurement, and against IMUs for peak acceleration. Ten teenage athletes (3 males, 7 females; 14–17 years) performed 40 falls recorded with five cameras (GoPro HERO12, USA, 2.7 K, 240 fps) and three IMUs (Blue Trident, Vicon, UK; ±200 g, 1600 Hz). Cut-off frequencies were set using Yu’s method (13 Hz for video, 39 Hz for IMUs). Pose2Sim’s results closely matched those of Kinovea for fall height and peak velocity with non-significant differences but underestimated peak acceleration. At the forehead, no significant difference was found, likely due to smaller accelerations at the head. Markerless video analysis is appropriate for studying fall kinematics and typology in indoor bouldering. IMUs remain necessary to quantify impact intensity, and future work should explore the combination of both IMUs and video to overcome this limitation. Full article

Cervical spine (c-spine) injuries are a prominent concern in sporting activities, and dynamic axial (i.e., head-first) impacts are associated with a high risk of c-spine trauma. This methodology study implanted pressure sensors in post-mortem human subject (PMHS) cervical intervertebral discs (CIVDs) to assess biomechanical response and disc pressure changes during dynamic injurious axial impacts. Two fresh frozen male head–neck PMHS (cephalus with complete c-spine) were instrumented with miniature pressure sensors (Model 060S, Precision Measurement Company, Ann Arbor, MI, USA) at three CIVD levels (upper, middle, and lower c-spine). Experiments replicated the Nightingale et al. studies, simulating a rigid unconstrained head vertex (0°) axial impact. PMHS were raised to a drop height of 0.53 m to reach the desired impact velocity of ~3.2 m/s and were allowed to drop vertically. Results showed characteristic c-spine deformations/buckling motion patterns and marked CIVD pressure differences between CIVD levels. The more cranial (C2–C4) and caudal (C6–T1) CIVD exhibited greater and more comparable pressure values than those of the mid-spine (C4–C6), and the pressure in upper/lower levels was at least ~four to six times higher than that of the middle. This study establishes the feasibility and assesses the potential of CIVD pressure as a biomechanical metric for assessing injurious axial loading and contributes a novel experimental framework for future injury tolerance research and model validation. Full article

Wearable inertial measurement units (IMUs) provide an accessible means of monitoring fatigue-related changes in running biomechanics, yet most existing methods rely on limited feature sets, lack personalization, or fail to generalize across individuals. This study introduces a bioinformatics-inspired stride sequence modeling framework that integrates spectral–entropy features, sample entropy, frequency-domain descriptors, and mixed-effects statistical modeling to detect fatigue using a single lumbar-mounted IMU. Nineteen recreational runners completed non-fatigued and fatigued 400 m runs, from which we extracted stride-level features and evaluated (1) population-level fatigue classification via global leave-one-participant-out (LOPO) models and (2) individualized fatigue detection through supervised participant-specific models and non-fatigued-only anomaly detection. Mixed-effects models revealed robust and multidimensional fatigue effects across key biomechanical features, with large standardized effect sizes (Cohen’s d up to 1.35) and substantial variance uniquely explained by fatigue (partial R² up to 0.31). Global LOPO machine learning models achieved modest accuracy (55%), highlighting strong inter-individual variability. In contrast, personalized supervised Random Forest classifiers achieved near-perfect performance (mean accuracy 97.7%; mean AUC 0.997), and NF-only One-Class SVMs detected fatigue as a deviation from individual baseline patterns (mean AUC 0.967). Entropy and stride-to-stride variability metrics further demonstrated consistent fatigue-linked increases in movement irregularity and reduced neuromuscular control. These findings show that IMU stride sequences contain highly informative, fatigue-sensitive biomechanical signatures, and that combining bioinformatics-inspired sequence analysis with hybrid statistical and personalized AI models enables both robust population-level insights and highly reliable individualized fatigue monitoring. The proposed framework supports future integration into sports analytics platforms, digital coaching systems, and real-time wearable fatigue detection technologies. This highlights the necessity of personalized fatigue-monitoring strategies in wearable systems. Full article

Cleated footwear in football increasingly incorporates sex-specific design features intended to address a clear gap in anthropometric and biomechanical differences in female athletes. However, experimental evidence evaluating how these designs may influence lower-extremity biomechanics during sport tasks in female athletes remains limited. The purpose of this exploratory pilot study was to examine the effects of sex-specific footwear on lower-extremity biomechanics, plantar pressure distribution, and perceived comfort in female football players during unanticipated side-step cutting. The study used a controlled laboratory-based repeated measures design. Twenty female football players performed unanticipated side-step cutting tasks in two randomized footwear conditions: a standard commercially available control cleat (CT) and a female-specific prototype cleat (PT). Ankle and knee biomechanics, in-shoe pressure distribution, and subjective comfort ratings were assessed. Compared with the CT, the PT cleat had reduced peak ankle inversion angle, inversion angular velocity, and inversion moment, indicating altered ankle biomechanics during cutting. No differences were observed in knee abduction between footwear conditions. However, participants subjectively rated greater comfort in CT compared to PT. Peak pressure was higher in the midfoot and central forefoot in the PT footwear compared to the CT. Given the pilot nature of the study, with multiple footwear alterations, the findings should be interpreted as hypothesis-generating and used to inform future targeted investigations. Full article

Background. Arm wrestling is a complex strength sport requiring detailed biomechanical analysis. This study investigated elbow functionality in medial epicondylitis using kinematic and electromyographic (EMG) approach. Methods. Hook technique specialists underwent a 10-session rehabilitation program (manual therapy and high-power laser). Outcomes were assessed via the NRS and QuickDASH. Functional analysis utilized surface EMG (Biceps Brachii, Pronator Teres, Brachioradialis, Extensor muscle) and an inertial sensor measuring Mean Jerk (MJ) for movement fluidity. Results. Data analysis for the eleven male athletes (mean age: 22.4 years) revealed substantial improvements following the intervention. NRS decreased from 5.1 to 1.5, and QuickDASH dropped from 25.2 ± 5.3 to 5.5 ± 1.0, while mean jerk remained stable (3.37 to 3.22). Pronator Teres activation markedly increased in the concentric phase (30.14 µV to 127.3 µV), indicating better coordination. Biceps Brachii (BB): Assumed a more pronounced concentric role, likely a compensatory adaptation after pain reduction; and lastly, Common Finger Extensor increased activation suggested increased extensor loading during the push phase. Conclusions. The combined kinematic and EMG data were crucial for identifying underlying musculoskeletal dysfunctions. The findings support an integrated approach for elbow health in arm wrestlers, providing objective data for targeted rehabilitation and prevention programs focusing on both pain and neuromuscular coordination. Full article

Accurate golf swing correction requires modeling not only static pose deviations but also temporal rhythm and biomechanical stability throughout the swing sequence. Most existing pose-based approaches rely on frame-wise similarity and therefore fail to capture timing, velocity transitions, and coordinated joint dynamics. This study proposes a reinforcement learning-based framework that generates frame-level corrective motions by formulating swing correction as a sequential decision-making problem optimized via Proximal Policy Optimization (PPO). A multi-term reward function is designed to integrate geometric pose accuracy, incremental correction improvement, hip-centered stability, and temporal rhythm consistency measured using a Velocity-DTW metric. Experiments conducted with swing sequences from one professional and five amateur golfers demonstrate that the proposed method produces smoother and more temporally coherent corrections than static pose–based baselines. In particular, rhythm-aware rewards substantially improve the motion of highly dynamic joints, such as the wrists and shoulders, while preserving lower-body stability. Visual analyses further confirm that the corrected trajectories follow expert patterns in both spatial alignment and timing. These results indicate that explicitly incorporating temporal rhythm within a reinforcement learning framework is essential for realistic and effective swing correction. The proposed method provides a principled foundation for automated, expert-level coaching systems in golf and other dynamic sports requiring temporally coordinated whole-body motion. Full article