Comparison of joint kinematics between upright front squat exercise and horizontal squat exercise performed on a short arm human centrifugation.

This study compared the joint kinematics between the front squat (FS) conducted in the upright (natural gravity) position and in the supine position on a short arm human centrifuge (SAHC). Male participants (N = 12) with no prior experience exercising on a centrifuge completed a FS in the upright position before (PRE) and after (POST) a FS exercise conducted on the SAHC while exposed to artificial gravity (AG). Participants completed, in randomized order, three sets of six repetitions with a load equal to body weight or 1.25 × body weight for upright squats, and 1 g and 1.25 g at the center of gravity (COG) for AG. During the terrestrial squats, the load was applied with a barbell. Knee (left/right) and hip (left/right) flexion angles were recorded with a set of inertial measurement units. AG decreased the maximum flexion angle (MAX) of knees and hips as well as the range of motion (ROM), both at 1 and 1.25 g. Minor adaptation was observed between the first and the last repetition performed in AG. AG affects the ability to FS in naïve participants by reducing MAX, MIN and ROM of the knees and hip.

Inclusion of a skeletal model partly improves the reliability of lower limb joint angles derived from a markerless depth camera.

A single depth camera provides a fast and easy approach to performing biomechanical assessments in a clinical setting; however, there are currently no established methods to reliably determine joint angles from these devices. The primary aim of this study was to compare joint angles as well as the between-day reliability of direct kinematics to model-constrained inverse kinematics recorded using a single markerless depth camera during a range of clinical and athletic movement assessments.A secondary aim was to determine the minimum number of trials required to maximize reliability. Eighteen healthy participants attended two testing sessions one week apart. Tasks included treadmill walking, treadmill running, single-leg squats, single-leg countermovement jumps, bilateral countermovement jumps, and drop vertical jumps. Keypoint data were processed using direct kinematics as well as in OpenSim using a full-body musculoskeletal model and inverse kinematics. Kinematic methods were compared using statistical parametric mapping and between-day reliability was calculated using intraclass correlation coefficients, mean absolute error, and minimal detectable change. Keypoint-derived inverse kinematics resulted in significantly smaller hip flexion (range = -9 to -2°), hip abduction (range = -3 to -2°), knee flexion (range = -5° to -2°), and greater dorsiflexion angles (range = 6-15°) than direct kinematics. Both markerless kinematic methods had high between-day reliability (inverse kinematics ICC 95 %CI = 0.83-0.90; direct kinematics ICC 95 %CI = 0.80-0.93). For certain tasks and joints, keypoint-derived inverse kinematics resulted in greater reliability (up to 0.47 ICC) and smaller minimal detectable changes (up to 13°) than direct kinematics. Performing 2-4 trials was sufficient to maximize reliability for most tasks. A single markerless depth camera can reliably measure lower limb joint angles, and skeletal model-constrained inverse kinematics improves lower limb joint angle reliability for certain tasks and joints.

A novel post-processing technique for correcting symmetric implant ambiguity in measuring total knee arthroplasty kinematics from single-plane fluoroscopy.

Recent advancements in computer vision and machine learning enable autonomous measurement of total knee arthroplasty kinematics through single-plane fluoroscopy. However, symmetric components present challenges in optimization routines, causing "symmetry traps" and ambiguous poses. Achieving clinically robust kinematics measurement requires addressing this issue. We devised an algorithm that converts a "true" pose to its corresponding "symmetry trap" orientation. From a dataset of nearly 13,000 human supervised kinematics, this algorithm constructs an augmented dataset of "true" and "symmetry trap" kinematics, used to train eight classification machine learning algorithms. The outputs from the highest-performing algorithm classify kinematics sequences as 'obviously true' or 'potentially ambiguous.' We construct a spline through 'obviously true' poses, and 'ambiguous' poses are compared to the spline to determine correct orientation. The machine learning algorithms achieved 88-94% accuracy on our internal test set and 91-93% on our external test set. Applying our spline algorithm to kinematics sequences yielded 91.1% accuracy, 94% specificity, but 67% sensitivity. The accuracy of standard ML algorithms for implants within 5 degrees of a pure-lateral view was 71%, rising to 88% beyond 5 degrees. This pioneering study systematizes addressing model-image registration issues with symmetric tibial implants. High accuracy suggests potential use of ML algorithms to mitigate shape-ambiguity errors in pose measurements from single-plane fluoroscopy. Our results also suggest an imaging protocol for measuring kinematics that favors more oblique viewing angles, which could further disambiguate "true" and "symmetry trap" poses.

Double-Bundle Medial Collateral Ligament Reconstruction Improves Anteromedial Rotatory Instability.

BACKGROUND: New techniques have been proposed to better address anteromedial rotatory instability in a medial collateral ligament (MCL)-injured knee that require an extra graft and more surgical implants, which might not be feasible in every clinical setting. PURPOSE: To investigate if improved resistance to anteromedial rotatory instability can be achieved by using a single-graft, double-bundle (DB) MCL reconstruction with a proximal fixation more anteriorly on the tibia, in comparison with the gold standard single-bundle (SB) MCL reconstruction. STUDY DESIGN: Controlled laboratory study. METHODS: Eight fresh-frozen human cadaveric knees were tested using a 6 degrees of freedom robotic simulator in intact knee, superficial MCL/deep MCL-deficient, and reconstruction states. Three different reconstructions were tested: DB MCL no proximal tibial fixation and DB and SB MCL reconstruction with proximal tibial fixation. Knee kinematics were recorded at 0°, 30°, 60°, and 90° of knee flexion for the following measurements: 8 N·m of valgus rotation (VR), 5 N·m of external tibial rotation, 5 N·m of internal tibial rotation, combined 89 N of anterior tibial translation and 5 N·m of external rotation for anteromedial rotation (AMR) and anteromedial translation (AMT). The differences between each state for every measurement were analyzed with VR and AMR/AMT as primary outcomes. RESULTS: Cutting the superficial MCL/deep MCL increased VR and AMR/AMT in all knee positions except at 90° for VR (P < .05). All reconstructions restored VR to the intact state except at 90° of knee flexion (P < .05). The DB MCL no proximal tibial fixation reconstruction could not restore intact AMR/AMT kinematics in any knee position (P < .05). Adding an anterior-based proximal tibial fixation restored intact AMR/AMT kinematics at ≥30° of knee flexion except at 90° for AMT (P < .05). The SB MCL reconstruction could not restore intact AMR/AMT kinematics at 0° and 90° of knee flexion (P < .05). CONCLUSION: In this in vitro cadaveric study, a DB MCL reconstruction with anteriorly placed proximal tibial fixation was able to control AMR and AMT better than the gold standard SB MCL reconstruction. CLINICAL RELEVANCE: In patients with anteromedial rotatory instability and valgus instability, a DB MCL reconstruction may be superior to the SB MCL reconstruction, without causing extra surgical morbidity or additional costs.

The effect of including a mobile arch, toe joint, and joint coupling on predictive neuromuscular simulations of human walking.

Predictive neuromuscular simulations are a powerful tool for studying the biomechanics of human walking, and deriving design criteria for technical devices like prostheses or biorobots. Good agreement between simulation and human data is essential for transferability to the real world. The human foot is often modeled with a single rigid element, but knowledge of how the foot model affects gait prediction is limited. Standardized procedures for selecting appropriate foot models are lacking. We performed 2D predictive neuromuscular simulations with six different foot models of increasing complexity to answer two questions: What is the effect of a mobile arch, a toe joint, and the coupling of toe and arch motion through the plantar fascia on gait prediction? and How much of the foot's anatomy do we need to model to predict sagittal plane walking kinematics and kinetics in good agreement with human data? We found that the foot model had a significant impact on ankle kinematics during terminal stance, push-off, and toe and arch kinematics. When focusing only on hip and knee kinematics, rigid foot models are sufficient. We hope our findings will help guide the community in modeling the human foot according to specific research goals and improve neuromuscular simulation accuracy.

Intra- and inter-operator reliability of measuring compressive stiffness of the patellar tendon in volleyball players using a handheld digital palpation device.

This observational study aimed to evaluate the intra- and inter-operator reliability of a digital palpation device in measuring compressive stiffness of the patellar tendon at different knee angles in talent and elite volleyball players. Second aim was to examine differences in reliability when measuring at different knee angles, between dominant and non-dominant knees, between sexes, and with age. Two operators measured stiffness at the midpoint of the patellar tendon in 45 Dutch volleyball players at 0°, 45° and 90° knee flexion, on both the dominant and non-dominant side. We found excellent intra-operator reliability (ICC>0.979). For inter-operator reliability, significant differences were found in stiffness measured between operators (p<0.007). The coefficient of variance significantly decreased with increasing knee flexion (2.27% at 0°, 1.65% at 45° and 1.20% at 90°, p<0.001). In conclusion, the device appeared to be reliable when measuring compressive stiffness of the patellar tendon in elite volleyball players, especially at 90° knee flexion. Inter-operator reliability appeared to be questionable. More standardized positioning and measurement protocols seem necessary.

Comparing the Drop Vertical Jump Tracking Performance of the Azure Kinect to the Kinect V2.

Traditional motion analysis systems are impractical for widespread screening of non-contact anterior cruciate ligament (ACL) injury risk. The Kinect V2 has been identified as a portable and reliable alternative but was replaced by the Azure Kinect. We hypothesize that the Azure Kinect will assess drop vertical jump (DVJ) parameters associated with ACL injury risk with similar accuracy to its predecessor, the Kinect V2. Sixty-nine participants performed DVJs while being recorded by both the Azure Kinect and the Kinect V2 simultaneously. Our software analyzed the data to identify initial coronal, peak coronal, and peak sagittal knee angles. Agreement between the two systems was evaluated using the intraclass correlation coefficient (ICC). There was poor agreement between the Azure Kinect and the Kinect V2 for initial and peak coronal angles (ICC values ranging from 0.135 to 0.446), and moderate agreement for peak sagittal angles (ICC = 0.608, 0.655 for left and right knees, respectively). At this point in time, the Azure Kinect system is not a reliable successor to the Kinect V2 system for assessment of initial coronal, peak coronal, and peak sagittal angles during a DVJ, despite demonstrating superior tracking of continuous knee angles. Alternative motion analysis systems should be explored.

Biomechanical Investigation of Lower Limbs during Slope Transformation Running with Different Longitudinal Bending Stiffness Shoes.

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.

Investigation of the functional and biomechanical effect of instrument-assisted soft tissue mobilization technique in individuals with asymptomatic dynamic knee valgus - Randomized controlled trial.

Although there are studies showing that myofascial release will increase muscle force production, the contribution of its application alone to muscle force production has not been examined. Aim of the study is to investigate the effect of instrument-assisted soft tissue mobilization (IASTM) on eccentric strength, frontal plane projection angle (FPPA), dynamic (DPS), and static postural stability (SPS), femoral internal rotation (FIR) angle in females with dynamic knee valgus (DKV). A total of 44 recreationally active females with asymptomatic DKV (age: 21,39 ± 1,79, body mass index: 20,09 ± 2,45) participated and were randomly assigned to either control group (CG) or IASTM group (IASTMG). Participants' eccentric contraction strength, FPPA, DPS, SPS, and FIR on the involved leg were measured pre- and post. IASTM application was applied to IASTMG for 6 weeks, twice a week, for 5 min, using Graston Technique® instruments on gluteus medius. CG received no intervention. In comparison of ECS difference values, change in IASTMG was found to be statistically significantly higher than CG (p = .004; p < .01). There was no statistical difference in comparison of FIR and FPPA values (respectively p = .213, p = .360; p < .05). In SPS and DPS evaluation, a statistically significant improvement was observed in favor of IASTMG in comparison of both intergroup and difference values (p < .05 for all). Strength gain without exercise can increase postural stability, but it isn't sufficient to correct faulty movement patterns. We recommend adding IASTM to injury prevention programs, but there is a need to investigate the effect of IASTM with technique correction feedback.

Regional and widespread pain sensitivity decreases following stretching in both men and women - Indications of stretch-induced hypoalgesia.

INTRODUCTION: This study aimed to investigate the effect of sex on regional and widespread pain sensitivity following acute bouts of stretching and to investigate the acute effect of stretching on regional and widespread pain sensitivity following stretching. METHODS: 73 healthy adults (36 females; mean age 25.6 ± 6.7 years) with an age range from 19 to 62 years were recruited for this experimental study. Regional and distant pain pressure pain thresholds, passive knee extension range of motion and passive resistive torque were measured before and 30 s after four bouts of 30-s static muscle stretching of the knee flexors with 20-s rest between bouts. RESULTS: No significant sex differences were found for pressure pain thresholds (p > 0.132), range of motion (p = 0.446) or passive resistive torque (p = 0.559) between pre-stretch and post-stretch measures. There were significant increases in pressure pain thresholds (p = 0.010), range of motion (p = 0.001) and passive resistive torque (p = 0.007) between pre-stretch and post-stretch measures. CONCLUSION: Muscle stretching significantly decreased regional and widespread pain sensitivity, indicating that central pain-modulating mechanisms are engaged during muscle stretching, resulting in stretch-induced hypoalgesia. Moreover, the results showed that the effect of stretching on regional and widespread pain sensitivity is not sex-specific.

Acute effects of Nordic hamstring exercise on hip and knee joints proprioception.

BACKGROUND AND OBJECTIVES: Nordic Hamstring Exercise (NHE) is one of the best exercises proposed for injury prevention of hamstring muscles. However, its effects on lower extremity proprioception are unclear. The aim of this study was to investigate the immediate effects of a single bout of NHE on hip and knee joints' proprioception. METHODS: Forty collegiate male soccer players participated in this study with a mean age of 22.85 ± 1.82 years and were randomized into either control (n = 20) or experimental (n = 20) groups. Each subject participated in pre-test measurements in which hip and knee active joints position sense (JPS) were assessed in standing and lying tasks using the image-capturing method. The experimental group then performed three sets of NHE with 10 repetitions in each set, while the control group rested for 10 min. Paired and independent t-tests were used for calculating the differences within and between groups on SPSS software, respectively. The level of significance was P ≤ 0.05. RESULTS: Hip JPS in the lying task and knee JPS in both of the standing and lying tasks were impaired significantly after performing a single bout of NHE (P ≤ 0.05). However, the effects of this exercise on hip JPS in the standing task were not significant (P ≥ 0.05). CONCLUSIONS: NHE performing with three sets of 10 repetitions can significantly impair hip and knee JPS immediately after exercise and reduce the proprioception acuity of the lower limbs. It is recommended to perform this exercise at a time rather than before training or match sessions.

Lower limb muscles' thicknesses are weakly associated with dynamic knee valgus during single-leg squat in women with patellofemoral pain.

INTRODUCTION: Patellofemoral pain (PFP) patients often show an altered lower limb alignment during the single-leg squat (SLS). There is evidence that proximal and distal-to-the-knee muscle alterations can modify the lower limb alignment in PFP patients. However, we observed a lack of studies investigating the possible association between the thickness and strength of proximal and distal-to-the-knee muscles and lower limb alignment during SLS in women with PFP. Therefore, this study aimed to investigate the association between the thickness and strength of lower limb muscles and dynamic knee valgus (DKV) during SLS in women with PFP. METHODS: Cross-sectional study, where fifty-five women with PFP were submitted to the following evaluations: (1) muscle thickness (MT) of Gluteus Medius (GMed), Gluteus Maximus (GMax), Vastus Lateralis (VL), and Tibialis Anterior (TA); (2) isometric peak torque of hip abductors, hip external rotators, knee extensors, and foot inversors; and (3) DKV during SLS. RESULTS: There was a significant negative association between GMax's MT and DKV (r = -0.32; p = 0.01), and between TA's MT and DKV (r = -0.28; p = 0.03). No significant correlations were observed between isometric torques and DKV. Regression analysis found that GMax's MT explained 10% of the DKV's variance during SLS. DISCUSSION: Poor lower limb alignment during SLS is weakly associated with proximal and distal-to-the-knee muscle thicknesses, with no association with isometric torque in PFP women. CONCLUSION: Our results suggest that other factors besides strength and muscle thicknesses may explain and improve lower limb alignment in women with PFP.

Single-legged landing behavior of high school basketball players with chronic ankle instability.

OBJECTIVES: Anterior cruciate ligament injury is one of the most serious ligamentous injuries. The purpose is to compare the impact of the ankle joint on the knee during landing between athletes with chronic instability and a control group (coper group) and to verify the effects of the kinetic chain from other joints. DESIGN: Prospective study. SETTING: High school basketball. PARTICIPANTS: Participants were 62 female high school basketball players who had participated in team sports for >6 months. MAIN OUTCOME MEASURES: Player joint angles, movements, and moments. RESULTS: The knee valgus moment was significantly higher in the chronic ankle instability group than in the coper group (20%-60% [p < 0.01]; 80%-100% [p < 0.05]) during landing motion. The knee valgus moment was also significantly higher during the change from the maximum knee joint flexion position to the maximum extension (p < 0.05). In addition, the landing motions of the chronic instability group may have utilized suboptimal compensatory motor strategy on the sagittal plane, depending heavily on the knee joint's abduction moment. CONCLUSIONS: Our findings indicate that the chronic ankle instability group uses a different landing strategy pattern than the coper group by changing the joint moment and joint angle during landing, which may increase the risk of anterior cruciate ligament injury.

Immediate effects of kinesiology tape on quadriceps muscle peak torque and knee joint repositioning error in healthy males: Effects of different tensions and directions.

BACKGROUND: Knee joint injuries may result from compromised quadriceps muscle strength or diminished knee joint proprioception. The application of Kinesio tape (KT) on the quadriceps muscle from origin to insertion (OTI-KT) or insertion to origin (ITO-KT) could impact knee joint proprioception and quadriceps muscle strength. This study aims to assess the effects of different tensions and directions of KT application on active and passive knee joint repositioning errors (AJRE and PJRE) and peak concentric and eccentric peak torque (CPT and EPT) of the quadriceps muscles in healthy males. METHOD: Twenty-one healthy males participated in this repeated-measures study design. CPT, EPT, AJRE, and PJRE of the dominant limb were measured by a Biodex dynamometer before and after applying OTI-KT with 0%, 15%, and 40% extra tensions and ITO-KT with 0% tension. RESULTS: ITO-KT demonstrated a significant reduction in AJRE (p < 0.05). Meanwhile, for OTI-KT, a statistically significant difference was observed in both AJRE and PJRE concerning time (F1,126 = 19.74, p < 0.05 for AJRE; F1,126 = 9.96, p < 0.05 for PJRE) and tension (F2,126 = 22.14, p < 0.05 for AJRE; F2,126 = 20.67, p < 0.05 for PJRE). CONCLUSION: Applying KT, especially OTI KT with 40% and 15% extra tension, shows potential in enhancing knee proprioception without immediate impacts on quadriceps muscle torque. This suggests applications in sports performance and knee injury rehabilitation.

Rethinking Exoskeleton Simulation-Based Design: The Effect of Using Different Cost Functions.

Designing an exoskeleton that can improve user capabilities is a challenging task, and most designs rely on experiments to achieve this goal. A different approach is to use simulation-based designs to determine optimal device parameters. Most of these simulations use full trajectory tracking limb kinematics during a natural gait as a reference. However, exoskeletons typically change the natural gait kinematics of the user. Other types of simulations assume that human gait is optimized for a cost function that combines several objectives, such as the cost of transport, injury prevention, and stabilization. In this study, we use a 2D OpenSim model consisting of 10 degrees of freedom and considering 18 muscles, together with the Moco optimization tool, to investigate the differences between these two approaches with respect to running with a passive knee exoskeleton. Utilizing this model, we test the effect of a full trajectory tracking objective with different weights (representing the importance of the objective in the optimization cost function) and show that when using weights that are typically used in the literature, there is no deviation from the experimental data. Next, we develop a multi-objective cost function with foot clearance term based on peak knee angle during swing, that achieves trajectories similar (RMSE=7.4 deg) to experimental running data. Finally, we investigate the effect of different parameters in the design of a clutch-based passive knee exoskeleton (1.5 kg at each leg) and find that a design that utilizes a 2.5 Nm/deg spring achieves an improvement of up to 8% in net metabolic energy. Our results show that tracking objectives in the cost function, even with a low weight, hinders the simulation's ability to change the gait trajectory. Thus, there is a need for other predictive simulation methods for exoskeletons.

Human-in-the-Loop Optimization of Knee Exoskeleton Assistance for Minimizing User's Metabolic and Muscular Effort.

Lower limb exoskeletons have the potential to mitigate work-related musculoskeletal disorders; however, they often lack user-oriented control strategies. Human-in-the-loop (HITL) controls adapt an exoskeleton's assistance in real time, to optimize the user-exoskeleton interaction. This study presents a HITL control for a knee exoskeleton using a CMA-ES algorithm to minimize the users' physical effort, a parameter innovatively evaluated using the interaction torque with the exoskeleton (a muscular effort indicator) and metabolic cost. This work innovates by estimating the user's metabolic cost within the HITL control through a machine-learning model. The regression model estimated the metabolic cost, in real time, with a root mean squared error of 0.66 W/kg and mean absolute percentage error of 26% (n = 5), making faster (10 s) and less noisy estimations than a respirometer (K5, Cosmed). The HITL reduced the user's metabolic cost by 7.3% and 5.9% compared to the zero-torque and no-device conditions, respectively, and reduced the interaction torque by 32.3% compared to a zero-torque control (n = 1). The developed HITL control surpassed a non-exoskeleton and zero-torque condition regarding the user's physical effort, even for a task such as slow walking. Furthermore, the user-specific control had a lower metabolic cost than the non-user-specific assistance. This proof-of-concept demonstrated the potential of HITL controls in assisted walking.

Validation of Inertial-Measurement-Unit-Based Ex Vivo Knee Kinematics during a Loaded Squat before and after Reference-Frame-Orientation Optimisation.

Recently, inertial measurement units have been gaining popularity as a potential alternative to optical motion capture systems in the analysis of joint kinematics. In a previous study, the accuracy of knee joint angles calculated from inertial data and an extended Kalman filter and smoother algorithm was tested using ground truth data originating from a joint simulator guided by fluoroscopy-based signals. Although high levels of accuracy were achieved, the experimental setup leveraged multiple iterations of the same movement pattern and an absence of soft tissue artefacts. Here, the algorithm is tested against an optical marker-based system in a more challenging setting, with single iterations of a loaded squat cycle simulated on seven cadaveric specimens on a force-controlled knee rig. Prior to the optimisation of local coordinate systems using the REference FRame Alignment MEthod (REFRAME) to account for the effect of differences in local reference frame orientation, root-mean-square errors between the kinematic signals of the inertial and optical systems were as high as 3.8° ± 3.5° for flexion/extension, 20.4° ± 10.0° for abduction/adduction and 8.6° ± 5.7° for external/internal rotation. After REFRAME implementation, however, average root-mean-square errors decreased to 0.9° ± 0.4° and to 1.5° ± 0.7° for abduction/adduction and for external/internal rotation, respectively, with a slight increase to 4.2° ± 3.6° for flexion/extension. While these results demonstrate promising potential in the approach's ability to estimate knee joint angles during a single loaded squat cycle, they highlight the limiting effects that a reduced number of iterations and the lack of a reliable consistent reference pose inflicts on the sensor fusion algorithm's performance. They similarly stress the importance of adapting underlying assumptions and correctly tuning filter parameters to ensure satisfactory performance. More importantly, our findings emphasise the notable impact that properly aligning reference-frame orientations before comparing joint kinematics can have on results and the conclusions derived from them.

Application of Machine Learning Methods to Investigate Joint Load in Agility on the Football Field: Creating the Model, Part I.

Laboratory studies have limitations in screening for anterior cruciate ligament (ACL) injury risk due to their lack of ecological validity. Machine learning (ML) methods coupled with wearable sensors are state-of-art approaches for joint load estimation outside the laboratory in athletic tasks. The aim of this study was to investigate ML approaches in predicting knee joint loading during sport-specific agility tasks. We explored the possibility of predicting high and low knee abduction moments (KAMs) from kinematic data collected in a laboratory setting through wearable sensors and of predicting the actual KAM from kinematics. Xsens MVN Analyze and Vicon motion analysis, together with Bertec force plates, were used. Talented female football (soccer) players (n = 32, age 14.8 ± 1.0 y, height 167.9 ± 5.1 cm, mass 57.5 ± 8.0 kg) performed unanticipated sidestep cutting movements (number of trials analyzed = 1105). According to the findings of this technical note, classification models that aim to identify the players exhibiting high or low KAM are preferable to the ones that aim to predict the actual peak KAM magnitude. The possibility of classifying high versus low KAMs during agility with good approximation (AUC 0.81-0.85) represents a step towards testing in an ecologically valid environment.

The Effect of Sensor Feature Inputs on Joint Angle Prediction across Simple Movements.

The use of wearable sensors, such as inertial measurement units (IMUs), and machine learning for human intent recognition in health-related areas has grown considerably. However, there is limited research exploring how IMU quantity and placement affect human movement intent prediction (HMIP) at the joint level. The objective of this study was to analyze various combinations of IMU input signals to maximize the machine learning prediction accuracy for multiple simple movements. We trained a Random Forest algorithm to predict future joint angles across these movements using various sensor features. We hypothesized that joint angle prediction accuracy would increase with the addition of IMUs attached to adjacent body segments and that non-adjacent IMUs would not increase the prediction accuracy. The results indicated that the addition of adjacent IMUs to current joint angle inputs did not significantly increase the prediction accuracy (RMSE of 1.92° vs. 3.32° at the ankle, 8.78° vs. 12.54° at the knee, and 5.48° vs. 9.67° at the hip). Additionally, including non-adjacent IMUs did not increase the prediction accuracy (RMSE of 5.35° vs. 5.55° at the ankle, 20.29° vs. 20.71° at the knee, and 14.86° vs. 13.55° at the hip). These results demonstrated how future joint angle prediction during simple movements did not improve with the addition of IMUs alongside current joint angle inputs.

Feature Decoupling for Multimodal Locomotion and Estimation of Knee and Ankle Angles Implemented by Multi-Model Fusion.

Many challenges exist in the study of using orthotics, exoskeletons or exosuits as tools for rehabilitation and assistance of healthy people in daily activities due to the requirements of portability and safe interaction with the user and the environment. One approach to dealing with these challenges is to design a control system that can be deployed in a portable device to identify the relationships that exist between the gait variables and gait cycle for different locomotion modes. In order to estimate the knee and ankle angles in the sagittal plane for different locomotion modes, a novel multimodal feature-decoupled kinematic estimation system consisting of a multimodal locomotion classifier and an optimal joint angle estimator is proposed in this paper. The multi-source information output from different conventional primary models are fused by assigning the non-fixed weight. To improve the performance of the primary models, a data augmentation module based on the time-frequency domain analysis method is designed. The results show that the inclusion of the data augmentation module and multi-source information fusion modules has improved the classification accuracy to 98.56% and kinematic estimation performance (PCC) to 0.904 (walking), 0.956 (running), 0.899 (stair ascent), 0.851 (stair descent), respectively. The kinematic estimation quality is generally higher for faster speed (running) or proximal joint (knee) compared to other modes and ankle. The limitations and advantages of the proposed approach are discussed. Based on our findings, the multimodal kinematic estimation system has potential in facilitating the deployment for human-in-loop control of lower-limb intelligent assistive devices.