Yaodong Gu
26321078600
Publications - 32
Comparison of Interlimb Coordination During Soccer Instep Kicking Between Elite and Amateur Players
Publication Name: European Journal of Sport Science
Publication Date: 2025-09-01
Volume: 25
Issue: 9
Page Range: Unknown
Description:
This study investigates how interlimb joint coordination influences foot speed during soccer instep kicking, using continuous relative phase (CRP) as a quantitative method. The sample includes 15 elite and 15 amateur players to examine potential differences in coordination patterns and their impact on performance. Specifically, we focused on the coordination between hip, knee, and ankle joints in the forefoot-back kicking motion. Results indicated that elite players exhibited significantly higher hip-knee CRP in the coronal plane during 62%–81% of movement duration (p = 0.015) and higher knee-ankle CRP in the vertical plane during 78%–100% (p = 0.013). Moreover, elite players had significantly greater hip-knee mean absolute relative phase (MARP) and deviation phase (DP) in the coronal plane (p < 0.001), as well as increased knee-ankle DP (p = 0.04). In the horizontal plane, hip-knee MARP was also greater in the elite players compared to amateurs (p < 0.001). Further analysis revealed a significant negative correlation between hip-knee CRP and foot velocity in the sagittal plane (R = −0.66, p < 0.001), whereas a significant positive correlation was observed between knee-ankle CRP and foot velocity in the horizontal plane (R = 0.56, p = 0.002). These findings suggest that elite players have superior joint coordination, which contributes to a faster foot velocity at the moment of ball impact. Understanding these coordination patterns provides valuable insights into optimizing kicking techniques. The findings of this study suggest that joint coordination may play an important role in enhancing kicking foot speed, which could inform future training approaches aimed at improving soccer performance.
Open Access: Yes
DOI: 10.1002/ejsc.70041
Data-driven deep learning for predicting ligament fatigue failure risk mechanisms
Publication Name: International Journal of Mechanical Sciences
Publication Date: 2025-09-01
Volume: 301
Issue: Unknown
Page Range: Unknown
Description:
The pathogenesis of musculoskeletal disorders is closely associated with the cumulative damage and fatigue failure behavior of fibrous connective tissues under long-term repetitive loading. However, significant technological challenges remain in real-time dynamic monitoring of ligament fatigue life, particularly the lack of efficient computational mechanics modeling frameworks and precise assessment tools adaptable to real-world movement scenarios. The multimodal integrated framework for ligament fatigue life assessment was proposed in this study. First, the high-accuracy subject-specific musculoskeletal models were developed based on individualized medical imaging data. A coupled hyperelastic-viscoelastic constitutive model was incorporated to accurately characterize the nonlinear mechanical behavior of ligamentous tissues and their fatigue damage evolution under cyclic loading. Furthermore, by integrating continuum damage mechanics theory, a time-dependent cumulative damage evolution equation was established to systematically quantify the coupling relationship between fatigue failure probability and dynamic mechanical loading. In the data-driven prediction module, an innovative deep-learning model that integrates kinematic-dynamic coupling was developed. By integrating wearable inertial measurement units, the model enables real-time inversion of ligament loading force-fatigue failure states and prediction of fatigue life. This approach effectively overcomes the limitations of traditional mechanical modeling in long-term, multi-scenario dynamic monitoring, achieving high-precision and minimally invasive fatigue life evaluation of ligaments. The proposed computational framework breaks the static-loading constraints of conventional fatigue testing, achieving the dynamic biomechanical analysis and fatigue life prediction under real movement conditions. This work not only provides novel theoretical insights into the mechanisms and modeling of ligament fatigue damage, but also provides a generalizable tool for biomechanical injury prevention, rehabilitation planning, and soft tissue fatigue analysis in the musculoskeletal system.
Open Access: Yes
Running-Induced Fatigue Exacerbates Anteromedial ACL Bundle Stress in Females with Genu Valgum: A Biomechanical Comparison with Healthy Controls
Publication Name: Sensors
Publication Date: 2025-08-01
Volume: 25
Issue: 15
Page Range: Unknown
Description:
Genu valgum (GV) is a common lower limb deformity that may increase the risk of anterior cruciate ligament (ACL) injury. This study used OpenSim musculoskeletal modeling and kinematic analysis to investigate the mechanical responses of the ACL under fatigue in females with GV. Eight females with GV and eight healthy controls completed a running-induced fatigue protocol. Lower limb kinematic and kinetic data were collected and used to simulate stress and strain in the anteromedial ACL (A–ACL) and posterolateral ACL (P–ACL) bundles, as well as peak joint angles and knee joint stiffness. The results showed a significant interaction effect between group and fatigue condition on A–ACL stress. In the GV group, A–ACL stress was significantly higher than in the healthy group both before and after fatigue (p < 0.001) and further increased following fatigue (p < 0.001). In the pre-fatigued state, A–ACL strain was significantly higher during the late stance phase in the GV group (p = 0.036), while P–ACL strain significantly decreased post-fatigue (p = 0.005). Additionally, post-fatigue peak hip extension and knee flexion angles, as well as pre-fatigue knee abduction angles, showed significant differences between groups. Fatigue also led to substantial changes in knee flexion, adduction, abduction, and hip/knee external rotation angles within the GV group. Notably, knee joint stiffness in this group was significantly lower than in controls and decreased further post-fatigue. These findings suggest that the structural characteristics of GV, combined with exercise-induced fatigue, exacerbate A–ACL loading and compromise knee joint stability, indicating a higher risk of ACL injury in fatigued females with GV.
Open Access: Yes
DOI: 10.3390/s25154814
Parametric cushioning lattice insole based on finite element method and machine learning: A preliminary computational analysis
Publication Name: Journal of Biomechanics
Publication Date: 2025-05-01
Volume: 184
Issue: Unknown
Page Range: Unknown
Description:
The cushioning performance of insole has always been a critical consideration in its design. While the development of intelligent methods and the emergence of additive manufacturing (AM) technology have enhanced design freedom and convenience, a standardized approach to guide designers in selecting optimal materials and structures for specific scenarios is still lacking. This study aims to propose a controllable parameterized lattice cushioning insole (PLI) by integrating finite element (FE) and machine learning (ML) methods. The insole performance can be adjusted by modifying the structural parameters (a, b) and the internal strut thickness (t). The findings indicate that PLI, under the optimal parameter combination (a = 2.54, b = 3.56, t = 3.15), can reduce plantar pressure by up to 44.45 %, which may be achieved by increasing the contact between the footwear and the foot. The data-driven PLI optimization design method proposed in this study significantly enhances the cushioning performance of insole structures, simplifies the optimization process for selecting insole structures or materials, and provides a systematic and efficient solution for insole design. Although the initial preparation of material data is time-intensive, the trained model eliminates the need for repeated laboratory gait analysis or plantar pressure measurements, offering a foundational reference for clinical applications in insole structure design.
Open Access: Yes
Bilateral Asymmetries of Plantar Pressure and Foot Balance During Walking, Running, and Turning Gait in Typically Developing Children
Publication Name: Bioengineering
Publication Date: 2025-02-01
Volume: 12
Issue: 2
Page Range: Unknown
Description:
Biomechanical asymmetries between children’s left and right feet can affect stability and coordination, especially during dynamic movements. This study aimed to examine plantar pressure distribution, foot balance, and center of pressure (COP) trajectories in children during walking, running, and turning activities to understand how different movements influence these asymmetries. Fifteen children participated in the study, using a FootScan plantar pressure plate to capture detailed pressure and balance data. The parameters, including time-varying forces, COP, and Foot Balance Index (FBI), were analyzed through a one-dimensional Statistical Parametric Mapping (SPM1d) package. Results showed that asymmetries in COP and FBI became more pronounced, particularly during the tasks of running and directional turns. Regional plantar pressure analysis also revealed a more significant load on specific foot areas during these dynamic movements, indicating an increased reliance on one foot for stability and control. These findings suggest that early identification of asymmetrical loading patterns may be vital in promoting a balanced gait and preventing potential foot health issues in children. This study contributes to understanding pediatric foot biomechanics and provides insights for developing targeted interventions to support healthy physical development in children.
Open Access: Yes
Will this be the next step? A systematic review of 3D printing in footwear biomechanics
Publication Name: Footwear Science
Publication Date: 2025-01-01
Volume: 17
Issue: 2
Page Range: 127-142
Description:
Three-dimensional (3D) printing technology enables designers to push the limits of their creativity, creating new possibilities for high-performance footwear. With advancements in engineering and a deeper understanding of biomechanics, researchers have designed footwear with complex structures comprising various materials. These materials and structures exhibit diverse physical properties and are used in physical activity, sports rehabilitation and competitive athletics. This article offers a systematic review of the biomechanical responses to advancements in 3D-printed footwear research from the past decade, focusing on three key domains: injury prevention, comfort, and athletic performance. Current research suggests that adjusting material stiffness or incorporating specific design elements in 3D-printed footwear can modulate plantar pressure distribution, which plays a crucial role in injury prevention, while also enhancing comfort. However, a consensus has yet to be reached regarding the impact of such footwear on athletic performance. Owing to the heterogeneity of research methodologies, the effectiveness of these designs may be significantly influenced by the design specifics, materials used, and individual user differences. Further systematic research and long-term clinical trials are crucial to advancing this field.
Open Access: Yes
The effects of different carbon-fiber plate shapes in shoes on lower limb biomechanics following running-induced fatigue
Publication Name: Frontiers in Bioengineering and Biotechnology
Publication Date: 2025-01-01
Volume: 13
Issue: Unknown
Page Range: Unknown
Description:
Different shapes of carbon-fiber plates (CFPs) are likely to affect lower limb biomechanics, particularly under conditions of running-induced fatigue, and potentially impact runners’ performance and risk of injury. However, no studies have yet elucidated the precise effects of CFP shapes on the lower limb biomechanical characteristics subsequent to running-induced fatigue. The purpose of this study was to investigate the effects of different CFP shapes in running shoes on the lower limb biomechanics of runners following running-induced fatigue. 12 male runners (aged 21.8 ± 1.3 years, mass 59.1 ± 4.1 kg, height 168.9 ± 2.2 cm, weekly running distance 68.8 ± 5.5 km/week) were recruited for this study. Two-way repeated measures ANOVA was used to compare kinematic and kinetic data, while SPM (Statistical Parametric Mapping) was used to assess the activation levels of lower limb muscles. Compared to wearing flat CFP shoes (“Flat”), wearing curved CFP shoes (“Curve”) resulted in a significant reduction in the hip (p = 0.034) and knee contact angle (p < 0.000), as well as a significant decrease in the hip flexion moment (p = 0.008). The activation level of the tibialis anterior (TA) was significantly higher when wearing “Curve” in pre-fatigue compared to “Flat”, whereas the opposite was observed post-fatigue. The curved CFP altered the bending angle of the forefoot, thereby significantly reducing the joint angles and joint moments of the hip and knee.
Open Access: Yes
Integrating footwear features into fatigue prediction models for marathon runners: A hybrid CNN-LSTM approach
Publication Name: Proceedings of the Institution of Mechanical Engineers Part P Journal of Sports Engineering and Technology
Publication Date: 2025-01-01
Volume: Unknown
Issue: Unknown
Page Range: Unknown
Description:
Footwear design, especially the curvature of carbon plates, may influence fatigue perception, but few studies have integrated footwear features into fatigue prediction models. This study aimed to develop a hybrid CNN-LSTM model to predict runners’ fatigue states and evaluate the impact of footwear characteristics on fatigue perception. Twelve male marathon runners (age = 21.8 ± 1.3 years; body mass = 59.1 ± 4.1 kg; height = 168.9 ± 2.2 cm; and weekly mileage = 68.8 ± 5.5 km) participated. They wore two types of carbon-plated shoes (flat plate, FP, and curved plate (CP)) and ran at a steady pace (Borg score 13) until a Borg score of 16 or 85% of maximum heart rate was reached for 2 min. EMG signals and physiological data were collected during treadmill running. A hybrid CNN-LSTM model was trained with and without footwear features to predict fatigue states. The model with footwear features achieved 85% accuracy, compared to 69% without. Curved carbon plate (CP) shoes delayed semi-fatigue onset, indicating better initial support, but the time to full fatigue was similar for both shoe types. The CNN-LSTM model effectively predicted fatigue states, with significant improvement when footwear features were included. Footwear design, particularly carbon plate curvature, influenced fatigue perception.
Open Access: Yes
Influence of bionic footwear on lower limb biomechanics across running experience levels: a controlled laboratory study
Publication Name: Frontiers in Sports and Active Living
Publication Date: 2025-01-01
Volume: 7
Issue: Unknown
Page Range: Unknown
Description:
Introduction: While the biomechanics of lower extremity during running and the impact of conventional running shoes on these traits have been extensively investigated, the influence of bionic shoes on runners remains largely, especially those runners with different experience levels. The aim of this study was to evaluate the biomechanical differences between experienced and novice runners when wearing two distinct types of footwear: bionic shoes and neutral shoes. Methods: Fourteen healthy male heel-strike runners participated and completed the running test wearing two pairs of running shoes respectively. A two-way-repeated-measures analysis of variance was used to determine the effects of participant experience level and shoe type on joint biomechanics. During the stance phase, shoe design primarily influenced the kinematic and dynamic performance of the ankles, knees, and hip joints. Results: When participants wore bionic shoes, there was a significant increase in the range of motion of the ankle and hip joints (p < 0.010), a remarkable increase in knee joint angular velocity (p < 0.010), and a significant decrease in hip joint angular velocity (p < 0.001). Concerning differences in experience levels, experienced runners exhibited significantly higher ankle joint angular velocity (p = 0.005) and knee joint angular velocity (p < 0.010) compared to novice runners, whereas novice runners demonstrated a significantly greater range of knee joint motion than experienced runners (p < 0.050). Conclusion: Our findings preliminarily suggest that experienced runners demonstrate superior performance as well as better stability and motor control of knee joint compared to novice runners who showed smaller knee angular velocity and greater range of motion during running. Furthermore, the increased range of motion of the ankle and hip joints in bionic shoes can activate the relevant muscle groups to a greater extent, which have a certain potential effect on the training performance of runners and the improvement of muscle control ability. While, due to the lack of a certain movement foundation, novice runners may have higher risk of injury.
Open Access: Yes
Mixed comparison of intervention with eccentric, isometric, and heavy slow resistance for Victorian Institute of Sport Assessment Patella Questionnaire in adults with patellar tendinopathy: A systematic review and network meta-analysis
Publication Name: Heliyon
Publication Date: 2024-11-15
Volume: 10
Issue: 21
Page Range: Unknown
Description:
Background: PT (Patellar Tendinopathy) is a degenerative disorder of the tendons induced via extended overstretching or overuse of the tendons instead than usual inflammation. In the past, humans have centered on a number of strategies of treating PT such as ultrasound and surgical treatment. However, they did no longer genuinely consider the effectiveness of eccentric, isometric, or HSR (Heavy Slow Resistance Training) education for PT; They did now not really outline the stage of PT to beautify the uniformity of the find out about participants; They did no longer immediately examine the affects of isometric, eccentric, and HSR training. This systematic assessment chosen eccentric, isometric, and heavy gradual resistance coaching for the remedy of patellar tendinopathy and their respective prognostic effects will supply valuable, top notch evidence-based insights as properly as vital facts and advice for future scientific administration of patellar tendinopathy. Methods: A thorough and comprehensive search was conducted across the Web of Science, PubMed, and Scopus databases, encompassing a wide range of relevant journals and sources, in order to perform a rigorous systematic review and network meta-analysis, ensuring the inclusion of all pertinent and high-quality studies. The selected studies satisfied predetermined eligibility requirements, which included: (1) PT patients included in the studies; (2) use of eccentric, isometric, and heavy slow resistance training as interventions; and (3) evaluation of VISA-P (Victorian Institute of Sport Assessment Patella Questionnaire) outcome measures. The effect magnitude was measured using the standard mean difference. The risk of bias inherent in each of the studies that were meticulously selected and included in the comprehensive analysis was rigorously evaluated and assessed using the well-established Cochrane Collaboration Risk of Bias Assessment Tool, ensuring the robustness and reliability of the research findings. Results: Three scientific databases yielded a total of 1460 studies, of which 7 were included in the final analysis. The findings indicated that eccentric training (0.01 in Rank 1 and 0.06 in Rank 8) is the worst method for increasing VISA-P level in patients with patellar tendinopathy, while moderate resistance slow training (0.25) and Rank 1 and Rank 8 are the best options. Conclusions: While heavy slow resistance is more suited for attaining long-term improvements in knee function, progressive tendon-loading exercises combined with isometric training or moderate slow resistance training are more beneficial than eccentric training alone. Eccentric training gives a greater range of exercise venues and doesn't require any additional training equipment. The inability to directly compare the effects of heavy slow, eccentric, and isometric resistance training constitutes a significant drawback of this review. This limitation stems from the scarcity of research that compares the outcomes of these various therapeutic approaches. To address this constraint, future research endeavors should strive to conduct comparative studies of these strategies. By doing so, they can aim to bridge this evaluation gap and facilitate a more effective and comprehensive assessment of their respective efficacies.
Open Access: Yes
Contribution of ankle motion pattern during landing to reduce the knee-related injury risk
Publication Name: Computers in Biology and Medicine
Publication Date: 2024-09-01
Volume: 180
Issue: Unknown
Page Range: Unknown
Description:
Background: Single-leg landing (SL) is an essential technique in sports such as basketball, soccer, and volleyball, which is often associated with a high risk of knee-related injury. The ankle motion pattern plays a crucial role in absorbing the load shocks during SL, but the effect on the knee joint is not yet clear. This work aims to explore the effects of different ankle plantarflexion angles during SL on the risk of knee-related injury. Methods: Thirty healthy male subjects were recruited to perform SL biomechanics tests, and one standard subject was selected to develop the finite element model of foot-ankle-knee integration. The joint impact force was used to evaluate the impact loads on the knee at various landing angles. The internal load forces (musculoskeletal modeling) and stress (finite element analysis) around the knee joint were simulated and calculated to evaluate the risk of knee-related injury during SL. To more realistically revert and simulate the anterior cruciate ligament (ACL) injury mechanics, we developed a knee musculoskeletal model that reverts the ACL ligament to a nonlinear short-term viscoelastic mechanical mechanism (strain rate-dependent) generated by the dense connective tissue as a function of strain. Results: As the ankle plantarflexion angle increased during landing, both the peak knee vertical impact force (p = 0.001) and ACL force (p = 0.001) decreased significantly. The maximum von Mises stress of ACL, meniscus, and femoral cartilage decreased as the ankle plantarflexion angle increased. The overall range of variation in ACL stress was small and was mainly distributed in the femoral and tibial attachment regions, as well as in the mid-lateral region. Conclusion: The current findings revealed that the use of larger ankle plantarflexion angles during landing may be an effective solution to reduce knee impact load and the risk of rupture of the medial femoral attachment area in the ACL. The findings of this study have the potential to offer novel perspectives in the optimized application of landing strategies, thus giving crucial theoretical backing for decreasing the risk of knee-related injury.
Open Access: Yes
Adaptive Adjustments in Lower Limb Muscle Coordination during Single-Leg Landing Tasks in Latin Dancers
Publication Name: Biomimetics
Publication Date: 2024-08-01
Volume: 9
Issue: 8
Page Range: Unknown
Description:
Previous research has primarily focused on evaluating the activity of individual muscles in dancers, often neglecting their synergistic interactions. Investigating the differences in lower limb muscle synergy during landing between dancers and healthy controls will contribute to a comprehensive understanding of their neuromuscular control patterns. This study enrolled 22 Latin dancers and 22 healthy participants, who performed a task involving landing from a 30 cm high platform. The data were collected using Vicon systems, force plates, and electromyography (EMG). The processed EMG data were subjected to non-negative matrix factorization (NNMF) for decomposition, followed by classification using K-means clustering algorithm and Pearson correlation coefficients. Three synergies were extracted for both Latin dancers and healthy participants. Synergy 1 showed increased contributions from the tibialis anterior (p < 0.001) and medial gastrocnemius (p = 0.024) in Latin dancers compared to healthy participants. Synergy 3 highlighted significantly greater contributions from the vastus lateralis in healthy participants compared to Latin dancers (p = 0.039). This study demonstrates that Latin dancers exhibit muscle synergies similar to those observed in healthy controls, revealing specific adjustments in the tibialis anterior and medial gastrocnemius muscles among dancers. This research illustrates how dancers optimize control strategies during landing tasks, offering a novel perspective for comprehensively understanding dancers’ neuromuscular control patterns.
Open Access: Yes
Biomechanical Investigation of Lower Limbs during Slope Transformation Running with Different Longitudinal Bending Stiffness Shoes
Publication Name: Sensors
Publication Date: 2024-06-01
Volume: 24
Issue: 12
Page Range: Unknown
Description:
Background: During city running or marathon races, shifts in level ground and up-and-down slopes are regularly encountered, resulting in changes in lower limb biomechanics. The longitudinal bending stiffness of the running shoe affects the running performance. Purpose: This research aimed to investigate the biomechanical changes in the lower limbs when transitioning from level ground to an uphill slope under different longitudinal bending stiffness (LBS) levels in running shoes. Methods: Fifteen male amateur runners were recruited and tested while wearing three different LBS running shoes. The participants were asked to pass the force platform with their right foot at a speed of 3.3 m/s ± 0.2. Kinematics data and GRFs were collected synchronously. Each participant completed and recorded ten successful experiments per pair of shoes. Results: The range of motion in the sagittal of the knee joint was reduced with the increase in the longitudinal bending stiffness. Positive work was increased in the sagittal plane of the ankle joint and reduced in the keen joint. The negative work of the knee joint increased in the sagittal plane. The positive work of the metatarsophalangeal joint in the sagittal plane increased. Conclusion: Transitioning from running on a level surface to running uphill, while wearing running shoes with high LBS, could lead to improved efficiency in lower limb function. However, the higher LBS of running shoes increases the energy absorption of the knee joint, potentially increasing the risk of knee injuries. Thus, amateurs should choose running shoes with optimal stiffness when running.
Open Access: Yes
DOI: 10.3390/s24123902
Influence of Torsional Stiffness in Badminton Footwear on Lower Limb Biomechanics
Publication Name: Journal of Sports Science and Medicine
Publication Date: 2024-03-01
Volume: 23
Issue: 1
Page Range: 196-208
Description:
Torsional stiffness of athletic footwear plays a crucial role in pre-venting injury and improving sports performance. Yet, there is a lack of research focused on the biomechanical effect of torsional stiffness in badminton shoes. This study aimed to comprehen-sively investigate the influence of three different levels of torsional stiffness in badminton shoes on biomechanical character-istics, sports performance, and injury risk in badminton players. Fifteen male players, aged 22.8 ± 1.96 years, participated in the study, performing badminton-specific tasks, including forehand clear stroke [left foot (FCL) and right foot (FCR)], 45-degree sidestep cutting (45C), and consecutive vertical jumps (CVJ). The tasks were conducted wearing badminton shoes of torsional stiffness measured with Shore D hardness 50, 60, and 70 (referred to as 50D, 60D, and 70D, respectively). The primary biomechanical parameters included ankle, knee, and MTP joint kinematics, ankle and knee joint moments, peak ground reaction forces, joint range of motion (ROM), and stance time. A one-way repeated measures ANOVA was employed for normally distributed data and Fried-man tests for non-normally distributed data. The 70D shoe exhib-ited the highest ankle dorsiflexion and lowest ankle inversion peak angles during 45C task. The 60D shoe showed significantly lower knee abduction angle and coronal motions compared to the 50D and 70D shoes. Increased torsional stiffness reduced stance time in the FCR task. No significant differences were observed in anterior-posterior and medial-lateral ground reaction forces (GRF). However, the 70D shoe demonstrated higher vertical GRF than the 50D shoe while performing the FCR task, particularly during 70%-75% of stance. Findings from this study revealed the significant role of torsional stiffness in reducing injury risk and optimizing performance during badminton tasks, indicating that shoes with an intermediate level of stiffness (60D) could provide a beneficial balance between flexibility and stability. These findings may provide practical references in guiding future badminton shoe research and development. Further research is nec-essary to explore the long-term effects of altering stiffness, con-sidering factors such as athletic levels and foot morphology, to understand of the influence of torsional stiffness on motion bio-mechanics and injury prevalence in badminton-specific tasks.
Open Access: Yes
A new method applied for explaining the landing patterns: Interpretability analysis of machine learning
Publication Name: Heliyon
Publication Date: 2024-02-29
Volume: 10
Issue: 4
Page Range: Unknown
Description:
As one of many fundamental sports techniques, the landing maneuver is also frequently used in clinical injury screening and diagnosis. However, the landing patterns are different under different constraints, which will cause great difficulties for clinical experts in clinical diagnosis. Machine learning (ML) have been very successful in solving a variety of clinical diagnosis tasks, but they all have the disadvantage of being black boxes and rarely provide and explain useful information about the reasons for making a particular decision. The current work validates the feasibility of applying an explainable ML (XML) model constructed by Layer-wise Relevance Propagation (LRP) for landing pattern recognition in clinical biomechanics. This study collected 560 groups landing data. By incorporating these landing data into the XML model as input signals, the prediction results were interpreted based on the relevance score (RS) derived from LRP. The interpretation obtained from XML was evaluated comprehensively from the statistical perspective based on Statistical Parametric Mapping (SPM) and Effect Size. The RS has excellent statistical characteristics in the interpretation of landing patterns between classes, and also conforms to the clinical characteristics of landing pattern recognition. The current work highlights the applicability of XML methods that can not only satisfy the traditional decision problem between classes, but also largely solve the lack of transparency in landing pattern recognition. We provide a feasible framework for realizing interpretability of ML decision results in landing analysis, providing a methodological reference and solid foundation for future clinical diagnosis and biomechanical analysis.
Open Access: Yes
Effect of Waist Strap Reinforcement in Backpacks on Children Gait Parameters During Walking and Running: A Randomized Cross-Over Prospective Study
Publication Name: Advances in Transdisciplinary Engineering
Publication Date: 2024-01-01
Volume: 59
Issue: Unknown
Page Range: 538-545
Description:
As academic demands increase, school-aged children and adolescents often carry heavy backpacks, impacting their posture and musculoskeletal health. This study examines how backpack carriage affects children's gait, focusing on the influence of waist strap design. In this study, twelve children underwent biomechanical tests while walking and running with and without backpacks, with weights adjusted based on daily habits. It can be found that waist strap-equipped backpacks significantly increased load response (F = 58.031, P < .001) and pre-swing phases (F = 58.031, P < .001) during both activities. In running, these backpacks also prolonged load response (F = 3.10, P = 0.004) and pre-swing phases (F = 3.10, P = 0.004). The study concludes that waist strap-equipped backpacks alter gait dynamics in children, affecting phases and contact times without impacting symmetry. This underscores the importance of waist straps in enhancing stability and reducing fatigue during backpack carriage.
Open Access: Yes
DOI: 10.3233/ATDE240591
The Impact of Shoe Heel-Toe Drop on Plantar Pressure During the Third Trimester of Pregnancy
Publication Name: Advances in Transdisciplinary Engineering
Publication Date: 2024-01-01
Volume: 59
Issue: Unknown
Page Range: 509-514
Description:
Pregnancy induces various physiological adaptations to accommodate the growing fetus. Pregnant women commonly experience changes in gait, balance, and center of gravity, which may increase the risk of falls. This study investigates the effects of negative heel shoes on plantar pressure distribution during walking in third-trimester pregnant women. Twelve healthy primigravidas participated, wearing both flat shoes and negative heel shoes while walking. Plantar pressure data were collected using the Pedar-X® insole system. Results revealed that negative heel shoes significantly reduced maximum force in the medial forefoot regions compared to flat shoes, and the force-time integral only significantly decreased in the medial forefoot region. Wearing negative-heeled shoes resulted in an increase in peak force in the hallux region. The study suggests that modifying heel-toe drop in shoes can effectively mitigate plantar pressure during third-trimester pregnancy, reducing the risk of forefoot discomfort and potential injuries. Negative heel shoes could be beneficial for pregnant women, offering a solution to alleviate forefoot pressure and promote foot blood circulation during walking. However, further optimization is needed in the hallux region for negative heel shoes.
Open Access: Yes
DOI: 10.3233/ATDE240587
Biomechanical Analysis of Gymnastics Movements Using Wearable Motion Capture Systems and Linear Sensors: A Case Study of the Kipping Bar Muscle-Up
Publication Name: Advances in Transdisciplinary Engineering
Publication Date: 2024-01-01
Volume: 59
Issue: Unknown
Page Range: 523-529
Description:
Gymnastics moves are complex and varied, needing precise technique and body coordination, which traditional biomechanics methods struggle to capture in detail. This study aims to look at and judge how well new motion capture and analysis technology works in gymnastics biomechanics. This study picks the kipping bar muscle up move and uses the IMU-based Xsens system and the GymAware RS unit power test system to finely look at how athletes do the move in terms of body position, power, work done by the body, and main upper limb joint movements. The study tested 8 male elite collegiate gymnasts, collecting movement data with Xsens and power data with GymAware RS unit. Results show the kipping bar muscle up takes 1.42 seconds, with a 1.13-meter shift of the body's center and a peak speed of 3.40m/s. In terms of power, the peak output was 2772.96J/s, showing the need for explosive power and fast strength. Also, the total work done was 889.70J, showing the move's efficiency and energy level. This study shows that new motion capture and analysis tech is effective in capturing complex gymnastics moves. The use of these techs not only expands the ways biomechanics can be studied but also helps in making training better and improving how efficiently moves are done.
Open Access: Yes
DOI: 10.3233/ATDE240589
Customized 3D-Printed Insoles for Diabetic Foot Care: Finite Element analysis and Machine Learning Approach
Publication Name: Advances in Transdisciplinary Engineering
Publication Date: 2024-01-01
Volume: 59
Issue: Unknown
Page Range: 515-522
Description:
Diabetic foot is a common complication in patients with diabetes, which can lead to plantar ulcers and even necessitate amputation. This study aims to utilize finite element analysis to simulate the offloading effects of 3D-printed insoles with various structures on plantar pressure and to explore the use of machine learning in providing optimal plantar pressure offloading solutions for patients with diabetic foot. The results demonstrated that negative Poisson's ratio structured insoles were more effective in reducing plantar pressure (reducing pressure by an average of 39.2%) than barefoot and conventional structures. This was achieved through a unique lateral contraction deformation, which increased the contact area with the foot. The pressure-reducing effect of insoles may be weight-related, suggesting that heavier patients may require stiffer insoles. However, the machine learning algorithm demonstrated a poor fit (only 60.75%) in the task of recommending suitable insoles. In conclusion, this study demonstrated the significant effect of negative Poisson's ratio structured insoles in reducing plantar pressure in diabetic patients, providing new ideas for diabetic foot protection. With the development of data analysis technology in the future, the feasibility and application of personalised insole design will be more promising.
Open Access: Yes
DOI: 10.3233/ATDE240588
Pregnancy-induced gait alterations: meta-regression evidence of spatiotemporal adjustments
Publication Name: Frontiers in Bioengineering and Biotechnology
Publication Date: 2024-01-01
Volume: 12
Issue: Unknown
Page Range: Unknown
Description:
During pregnancy, women undergo significant physiological, hormonal, and biomechanical changes that influence their gait. The forward shift of the center of mass and increased joint loads often result in a “waddling gait,” elevating the risk of falls. While gait changes during pregnancy have been documented, findings across studies remain inconsistent, particularly regarding variations at different pregnancy stages. This systematic review and meta-analysis aimed to quantify the impact of pregnancy stages on spatiotemporal gait parameters. A comprehensive literature search across six databases (PubMed, Web of Science, Scopus, EBSCO, Embase, and Cochrane Library) was conducted to identify studies on pregnancy and gait, and data on publication details, methodology, participant characteristics, gait outcomes, and study limitations were extracted. Out of 4,581 initial records, 21 studies met the inclusion criteria. The meta-analysis revealed significant changes in gait parameters during pregnancy, with decreases in stride length (effect size = −0.29) and gait speed (effect size = −0.55), and increases in stride width (effect size = 0.45), cycle time (effect size = 0.38), and double support time (effect size = 0.41). Meta-regression analyses indicated that gestational weeks significantly impacted stride length (β = −0.03 [95% CI, −0.055 to −0.002], p < 0.05) and stride width (β = 0.02 [95% CI, 0.003 to 0.039], p < 0.05), while no significant effects were found for cycle time, double support time, or gait speed. In conclusion, pregnancy leads to significant changes in gait patterns, with a notable increase in stride width and a decrease in stride length as gestation progresses, suggesting these adjustments are strategies for maintaining balance and stability in response to physiological changes. The analysis also emphasizes that while gestational age influences gait adaptations, other factors such as pelvic girdle pain, footwear, and psychological influences play crucial roles. Understanding these complex gait changes can inform interventions and guidelines to support mobility and safety for pregnant women throughout their pregnancy.
Open Access: Yes
Rethinking running biomechanics: a critical review of ground reaction forces, tibial bone loading, and the role of wearable sensors
Publication Name: Frontiers in Bioengineering and Biotechnology
Publication Date: 2024-01-01
Volume: 12
Issue: Unknown
Page Range: Unknown
Description:
This study presents a comprehensive review of the correlation between tibial acceleration (TA), ground reaction forces (GRF), and tibial bone loading, emphasizing the critical role of wearable sensor technology in accurately measuring these biomechanical forces in the context of running. This systematic review and meta-analysis searched various electronic databases (PubMed, SPORTDiscus, Scopus, IEEE Xplore, and ScienceDirect) to identify relevant studies. It critically evaluates existing research on GRF and tibial acceleration (TA) as indicators of running-related injuries, revealing mixed findings. Intriguingly, recent empirical data indicate only a marginal link between GRF, TA, and tibial bone stress, thus challenging the conventional understanding in this field. The study also highlights the limitations of current biomechanical models and methodologies, proposing a paradigm shift towards more holistic and integrated approaches. The study underscores wearable sensors’ potential, enhanced by machine learning, in transforming the monitoring, prevention, and rehabilitation of running-related injuries.
Open Access: Yes
A new method proposed for realizing human gait pattern recognition: Inspirations for the application of sports and clinical gait analysis
Publication Name: Gait and Posture
Publication Date: 2024-01-01
Volume: 107
Issue: Unknown
Page Range: 293-305
Description:
Background: Finding the best subset of gait features among biomechanical variables is considered very important because of its ability to identify relevant sports and clinical gait pattern differences to be explored under specific study conditions. This study proposes a new method of metaheuristic optimization-based selection of optimal gait features, and then investigates how much contribution the selected gait features can achieve in gait pattern recognition. Methods: Firstly, 800 group gait datasets performed feature extraction to initially eliminate redundant variables. Then, the metaheuristic optimization algorithm model was performed to select the optimal gait feature, and four classification algorithm models were used to recognize the selected gait feature. Meanwhile, the accuracy results were compared with two widely used feature selection methods and previous studies to verify the validity of the new method. Finally, the final selected features were used to reconstruct the data waveform to interpret the biomechanical meaning of the gait feature. Results: The new method finalized 10 optimal gait features (6 ankle-related and 4-related knee features) based on the extracted 36 gait features (85 % variable explanation) by feature extraction. The accuracy in gait pattern recognition among the optimal gait features selected by the new method (99.81 % ± 0.53 %) was significantly higher than that of the feature-based sorting of effect size (94.69 % ± 2.68 %), the sequential forward selection (95.59 % ± 2.38 %), and the results of previous study. The interval between reconstructed waveform-high and reconstructed waveform-low curves based on the selected feature was larger during the whole stance phase. Significance: The selected gait feature based on the proposed new method (metaheuristic optimization-based selection) has a great contribution to gait pattern recognition. Sports and clinical gait pattern recognition can benefit from population-based metaheuristic optimization techniques. The metaheuristic optimization algorithms are expected to provide a practical and elegant solution for sports and clinical biomechanical feature selection with better economy and accuracy.
Open Access: Yes
New Insights Optimize Landing Strategies to Reduce Lower Limb Injury Risk
Publication Name: Cyborg and Bionic Systems
Publication Date: 2024-01-01
Volume: 5
Issue: Unknown
Page Range: Unknown
Description:
Single-leg landing (SL) is often associated with a high injury risk, especially anterior cruciate ligament (ACL) injuries and lateral ankle sprain. This work investigates the relationship between ankle motion patterns (ankle initial contact angle [AICA] and ankle range of motion [AROM]) and the lower limb injury risk during SL, and proposes an optimized landing strategy that can reduce the injury risk. To more realistically revert and simulate the ACL injury mechanics, we developed a knee musculoskeletal model that reverts the ACL ligament to a nonlinear short-term viscoelastic mechanical mechanism (strain ratedependent) generated by the dense connective tissue as a function of strain. Sixty healthy male subjects were recruited to collect biomechanics data during SL. The correlation analysis was conducted to explore the relationship between AICA, AROM, and peak vertical ground reaction force (PVGRF), joint total energy dissipation (TED), peak ankle knee hip sagittal moment, peak ankle inversion angle (PAIA), and peak ACL force (PAF). AICA exhibits a negative correlation with PVGRF (r = -0.591) and PAF (r = -0.554), and a positive correlation with TED (r = 0.490) and PAIA (r = 0.502). AROM exhibits a positive correlation with TED (r = 0.687) and PAIA (r = 0.600). The results suggested that the appropriate increases in AICA (30° to 40°) and AROM (50° to 70°) may reduce the lower limb injury risk. This study has the potential to offer novel perspectives on the optimized application of landing strategies, thus giving the crucial theoretical basis for decreasing injury risk.
Open Access: Yes
Musculoskeletal modelling sequentially integrated with stress simulation reveals asymmetrical knee loading and ligament stress during long-distance running
Publication Name: BMC Sports Science Medicine and Rehabilitation
Publication Date: 2025-12-01
Volume: 17
Issue: 1
Page Range: Unknown
Description:
Background: Understanding the internal load characteristics of the knee joint is essential for investigating unilateral knee injuries associated with running. This study examined the differences in the location and magnitude of von Mises stress in the internal structures of bilateral knee joints during the stance phase of gait following 10 km running at submaximal speeds. Methods: A healthy male recreational runner participated in this study. We employed a synergistic approach, integrating subject-specific knee joint angles, reaction forces, and moments derived from musculoskeletal modeling to inform and drive the finite element (FE) modeling of running. This methodology ensured a detailed and accurate representation of knee joint mechanics. The peak stresses of the bilateral knee menisci, tibial cartilage, and five main ligaments were quantified using a FE model during the stance phase. Results: The meniscus, tibial cartilage, anterior (ACL), posterior cruciate ligament (PCL), medial (MCL), lateral collateral ligament (LCL) and experienced larger loads in the non-dominant limb across most phases of stance. Additionally, fatigue elevated the peak loading on the non-dominant limb’s ACL, PCL, and LCL during the gait stance phase but diminished the load on these ligaments in the dominant knee joint. For Patellar ligament (PL), the non-dominant side showed maximal stress at initial contact, while the dominant side dominated during the remaining stance phases. Conclusions: This proof-of-concept substantially enhances our understanding of the impact of running-induced fatigue on bilateral knee loading. It provides a detailed analysis of factors leading to unilateral knee overload during extended running. These insights are essential in formulating targeted strategies to reduce injury risks.
Open Access: Yes
Foot Progression Angle Modulates Three-Dimensional Lower-Limb Biomechanics in Flexible Flatfoot: Kinematic–Kinetic Patterns and Clinical Implications
Publication Name: Journal of Foot and Ankle Research
Publication Date: 2026-03-01
Volume: 19
Issue: 1
Page Range: Unknown
Description:
Introduction: Foot progression angle affects gait and lowerlimb alignment. Altered angles may increase knee and ankle loading and produce tissue loading patterns previously linked to musculoskeletal injury. This study investigates how different foot progression angles modify knee and ankle biomechanics in young adults with flexible flatfoot. Methods: 28 participants (aged 18–35 years) with flexible flatfoot completed gait trials under three foot progression angle conditions. Kinematic and kinetic variables were analyzed using one-dimensional statistical parametric mapping. A 1D convolutional neural network was applied to classify progression angle patterns based on flexible flatfoot severity and gait biomechanics. Results: Decreasing foot progression angle reduced the ankle eversion/inversion range and knee abduction and external rotation (p < 0.05). Increasing foot progression angle lowered early stance ankle plantarflexion and increased knee abduction/external rotation (p < 0.05). Kinetically, a smaller foot progression angle reduced peak ankle plantarflexion moment and knee extension moment but increased the first peak of the knee adduction moment and rotational moment fluctuations (p < 0.05). A larger foot progression angle reduced rotational fluctuations and terminal stance knee extension moment (p < 0.05). The convolutional neural network model was most accurate for moderate flexible flatfoot cases, and ankle coronal and knee transverse biomechanics showed the strongest discriminative power. Conclusion: Modifying the foot progression angle can meaningfully alter knee and ankle loading in young adults with flexible flatfoot. Neutral or mild toe-in angles may help mitigate excessive eversion and rotational stress, suggesting a simple noninvasive adjustment that clinicians can incorporate during gait retraining or orthotic prescription. Because biomechanical responses vary across individuals, FPA modification may be the most effective when tailored to patient-specific gait characteristics. In addition, deep-learning-based gait classification shows promise for supporting personalized monitoring and guiding clinical decision-making during rehabilitation.
Open Access: Yes
DOI: 10.1002/jfa2.70126
Biomechanical effects of maximal footwear on running: a systematic review and network meta-analysis
Publication Name: Footwear Science
Publication Date: 2026-01-01
Volume: 18
Issue: 1
Page Range: 83-98
Description:
Running is widely recognised for its substantial health benefits; however, it is frequently associated with lower limb injuries caused by repetitive impact forces. To mitigate such injuries, maximal footwear has been developed; nevertheless, evidence comparing its biomechanical effects with those of other footwear types remains inconclusive. A Bayesian network meta-analysis of 14 studies (222 participants) was conducted, based on systematic searches of PubMed, Web of Science, the Cochrane Library, Scopus, and Embase (from inception to 12 November 2024). Multiple biomechanical parameters were evaluated, including vertical average loading rate, vertical instantaneous loading rate, impact peak, active peak and ankle peak eversion. The results revealed a complex and sometimes contradictory biomechanical profile for maximal footwear. Specifically, maximal footwear resulted in a significantly higher impact peak compared to both conventional and minimal footwear. In contrast, for the vertical average loading rate, it performed significantly better than minimal footwear but showed no significant difference compared to conventional footwear. For other impact metrics, no significant differences were observed. Notably, maximal footwear was associated with a significantly lower ankle peak eversion compared to minimal footwear, suggesting a potential for greater control of ankle motion.
Open Access: Yes
Impact of wearable resistance training on knee and ankle joint biomechanics: Enhancing change of direction ability in football athletes
Publication Name: Proceedings of the Institution of Mechanical Engineers Part P Journal of Sports Engineering and Technology
Publication Date: 2026-01-01
Volume: Unknown
Issue: Unknown
Page Range: Unknown
Description:
This study aimed to examine the effects of wearable resistance (WR) training on change of direction ability (CODA), muscle activation patterns, and knee joint stress in athletes. Fifteen healthy male football players participated in a pre- and post-training intervention designed to target the quadriceps, hamstrings, and calf muscles to improve neuromuscular control and joint stability. Surface electromyography (EMG) was used to assess muscle activation, and finite element analysis (FEA) was applied to evaluate stress distribution in the knee joint. Following the WR training program, there was a significant reduction in knee abduction angle during the stance phase (p = 0.001), indicating enhanced joint stability. Strength in the calf muscles increased significantly, while muscle activation levels in the quadriceps (p < 0.001) and hamstrings (p = 0.007) were also elevated. Enhanced co-activation between quadriceps and hamstrings was observed, and FEA demonstrated a significant decrease in the maximal von Mises stress in the anterior cruciate ligament (ACL) and meniscus. These findings suggest that WR training improves CODA and lower limb muscle coordination while reducing internal knee joint stress, potentially lowering the risk of ACL injuries and enhancing athletic performance.
Open Access: Yes
The impact of cognitive load on lower limb biomechanics during the take-off phase before service in tennis players of different levels
Publication Name: Journal of Sports Sciences
Publication Date: 2026-01-01
Volume: 44
Issue: 7
Page Range: 896-906
Description:
This study examines the impact of cognitive load (CL) on lower limb biomechanics during the take-off preparation phase of the platform serve in tennis players of varying skill levels. Fifteen elite and fifteen amateur tennis players performed platform serves before and after completing a 30-minute Stroop task designed to induce CL. Key biomechanical parameters, including joint range of motion (ROM), joint moments, centre of mass (COM) displacement, and ground reaction force (GRF), were assessed using both kinematic and kinetic analysis. After CL, the biomechanical performance of amateur athletes significantly decreased compared to elite athletes. Specifically, amateur athletes showed a 14.19° lower ankle joint range of motion in the sagittal plane (p < 0.001), a 0.04-meter lower COM displacement in the frontal plane (p = 0.017), and a 0.15 Nm/BW lower knee extension moment (p < 0.001). CL adversely affects the lower limb biomechanics of amateur players more than elite players, with elite players demonstrating greater stability. These findings suggest that elite players have developed more efficient motor control mechanisms through extensive training. Tailored training interventions that account for different skill levels could enhance performance stability and mitigate the risk of injury.
Open Access: Yes
Foot Progression Angle Modulates Knee Loading During Walking in Individuals with Flexible Flatfoot
Publication Name: Annals of Biomedical Engineering
Publication Date: 2026-01-01
Volume: Unknown
Issue: Unknown
Page Range: Unknown
Description:
Purpose: This study evaluated tibiofemoral loading and medial meniscal stress distribution in individuals with flexible flatfoot (FFF) during walking under different foot progression angle (FPA) conditions. Methods: This study analyzed the gait of 28 FFF patients (16 males, 12 females) under three FPA conditions (neutral, toe-in, toe-out). Kinematic (Vicon) and kinetic (Kistler) data were used to estimate tibiofemoral forces in OpenSim. Subsequently, joint angles and muscle forces at peak tibiofemoral forces were used to drive a finite element (FE) model of the knee, enabling the comparison of meniscal von Mises stress, maximum shear stress, and contact pressure across FPA conditions. Results: Tibiofemoral force increased during early stance (9–11%) in the toe-in condition with this increase reaching statistical significance in males (p = 0.008, mean partial η2=0.70 within the SPM-identified cluster). FE analysis showed that peak stresses and contact pressure were primarily localized in the anterior region of the medial meniscus. A consistent directional response to FPA was observed with the lowest peak values occurring in the toe-in condition and the highest values in the toe-out condition. Conclusion: Adjusting FPA modulates intra-articular knee loading via the kinetic chain. For FFF patients, neutral FPA provides stable loading. The toe-in condition presents a complex mechanism: despite increasing tibiofemoral force (notably in males), it reduces peak stress by altering contact mechanics and stress distribution. Therefore, FFF gait interventions must be individualized based on factors like foot morphology, sex, and functional goals.
Open Access: Yes
Optimizing landing mechanics to modulate patellar tendon loading: An individualized moment arm analysis
Publication Name: Iscience
Publication Date: 2026-05-15
Volume: 29
Issue: 5
Page Range: Unknown
Description:
Single-leg landing (SL) imposes substantial mechanical demand on the patellar tendon, with peak patellar tendon force (PPTF) serving as a key metric for characterizing the internal mechanical environment of the tendon. This study integrates 3D modeling with high-resolution in vivo kinematics to quantify the patellar tendon moment arm (PTMA) and the PPTF, examining their biomechanical correlations and neuromuscular features. Minimal sex-related PTMA differences suggest comparable anatomical leverage during knee flexion across both sexes. In both sexes, PPTF was significantly positively correlated with the knee flexion angle at initial contact (IC) and significantly negatively correlated with the knee range of motion (ROM). Muscle network analysis showed lower clustering coefficients in high-frequency versus low-frequency bands. Reduced IC knee flexion and increased ROM attenuate patellar tendon mechanical demand. By incorporating individualized moment-arm analysis, this study provides a biomechanical basis for understanding patellar tendon loading during landing.
Open Access: Yes
The effect of mixed fatigue on knee biomechanics and muscle activation during sidestep cutting in elite soccer players
Publication Name: BMC Sports Science Medicine and Rehabilitation
Publication Date: 2026-12-01
Volume: 18
Issue: 1
Page Range: Unknown
Description:
Background: Football is one of the most popular sports in the world, and it is also a sport with a high rate of injury. The study aims to investigate the effects of physical and mental mixed fatigue (PMF) on knee biomechanics during sidestep cutting maneuvers in elite male soccer players, thereby assessing the potential mechanisms underlying non-contact knee injuries. Methods: Thirty-six elite male soccer players were recruited (age: 21.61 ± 1.22 years; body mass: 75.16 ± 6.34 kg; height: 175.8 ± 3.53 cm; shoe size: 41–44 EUR). Following a targeted fatigue induction protocol, key lower limb biomechanical data were acquired during anticipated sidestep cutting maneuvers both pre- and post-PMF. Statistical analyses were performed utilizing paired sample t-tests and one-dimensional Statistical Parametric Mapping (SPM1d). Results: Following PMF, knee valgus increased at initial contact (P = 0.022). Kinetic analysis, supported by SPM1d, revealed a marked transition from an extensor-dominant to a flexor-dominant pattern in sagittal knee moments (P = 0.007), alongside elevated knee valgus moments (P = 0.039). Neuromuscularly, quadriceps and lateral gastrocnemius activation (iEMG/RMS) significantly decreased, whereas compensatory increases were observed in the hamstrings and medial gastrocnemius (all P < 0.001). Conclusion: While PMF preserved most kinematics, the statistically significant increase in knee valgus, though small in magnitude, suggests an impaired frontal-plane control that may elevate Anterior Cruciate Ligament (ACL) strain. The shift from quadriceps to hamstring dominance reflects a compensatory neuromuscular strategy. These findings emphasize the importance of incorporating cognitive load into injury-prevention programs and monitoring mental fatigue to reduce non-contact knee injury risks.
Open Access: Yes
AI-powered biomechanical modeling for ACL-reconstructed knees: predicting knee joint contact forces via computer vision and deep learning
Publication Name: Journal of Neuroengineering and Rehabilitation
Publication Date: 2026-12-01
Volume: 23
Issue: 1
Page Range: Unknown
Description:
Background: Patients undergoing anterior cruciate ligament reconstruction (ACLR) are at high risk of osteoarthritis or secondary injuries, with abnormal knee contact forces (KCFs) identified as a key factor in joint degeneration. Traditional KCF assessment relies on expensive lab systems while advances in computer vision and AI now enable low-cost alternatives. However, currently available methods oversimplify knee mechanics and neglect compensatory movements, highlighting the urgent need for intelligent, real-time monitoring tools for personalized rehabilitation. Therefore, the aim of this study was to develop and validate an integrated, non-invasive framework for accurate KCFs prediction in ACLR patients during daily activities. We hypothesized that combining enhanced musculoskeletal modeling with a deep learning architecture incorporating spatiotemporal attention would improve the prediction accuracy across multiple movement tasks. Methods: This study simultaneously recorded three daily movements of 29 post-ACLR patients using both Vicon and OpenCap. Motion trajectories captured by Vicon were imported into OpenSim for musculoskeletal modeling and KCFs calculation. Dataset comprising OpenCap-derived kinematics and OpenSim-computed KCFs was used to train 3 learning models for the prediction of KCFs in ACLR patients across different movements. Results: Among three models, CNN-BiGRU-Attention model demonstrated the best predictive performance across all three movement tasks (R2walking = 0.973 ± 0.003, R2running = 0.982 ± 0.004, R2descending stairs = 0.951 ± 0.007). CNN and self-attention mechanism collectively enhanced the model's ability to capture key features in ACLR patients' movement data, thereby improving KCF prediction accuracy. Furthermore, for the three daily activities, all models showed superior KCFs prediction performance in running and stair-descent tasks compared to walking. Conclusion: The developed framework successfully achieved high-precision prediction of KCFs. This technological breakthrough not only provides a real-time quantitative tool for rehabilitation monitoring in patients with ACLR, but also facilitates a paradigm shift from static laboratory analysis to dynamic real-time monitoring, with broad application prospects in sports medicine, rehabilitation engineering.
Open Access: Yes
