Combining wearable sensor signals, machine learning and biomechanics to estimate tibial bone force and damage during running

Predicting Musculoskeletal Loading at Common Running Injury Locations Using Machine Learning and Instrumented Insoles

INTRODUCTION

Wearables have the potential to provide accurate estimates of tissue loads at common running injury locations. Here we investigate the accuracy by which commercially available instrumented insoles (ARION; ATO-GEAR, Eindhoven, The Netherlands) can predict musculoskeletal loading at common running injury locations.

METHODS

Nineteen runners (10 males) ran at five different speeds, four slopes, with different step frequencies, and forward trunk lean on an instrumented treadmill while wearing instrumented insoles. The insole data were used as input to an artificial neural network that was trained to predict the Achilles tendon strain, and tibia and patellofemoral stress impulses and weighted impulses (damage proxy) as determined with musculoskeletal modeling. Accuracy was investigated using leave-one-out cross-validation and correlations. The effect of different input metrics was also assessed.

RESULTS

The neural network predicted tissue loading with overall relative percentage errors of 1.95 ± 8.40%, -7.37 ± 6.41%, and -12.8 ± 9.44% for the patellofemoral joint, tibia, and Achilles tendon impulse, respectively. The accuracy significantly changed with altered running speed, slope, or step frequency. Mean (95% confidence interval) within-individual correlations between modeled and predicted impulses across conditions were generally nearly perfect, being 0.92 (0.89 to 0.94), 0.95 (0.93 to 0.96), and 0.95 (0.94 to 0.96) for the patellofemoral, tibial, and Achilles tendon stress/strain impulses, respectively.

CONCLUSIONS

This study shows that commercially available instrumented insoles can predict loading at common running injury locations with variable absolute but (very) high relative accuracy. The absolute error was lower than the methods that measure only the step count or assume a constant load per speed or slope. This developed model may allow for quantification of in-field tissue loading and real-time tissue loading-based feedback to reduce injury risk.

Tibial acceleration alone is not a valid surrogate measure of tibial load in response to stride length manipulation

PURPOSE

This study aimed to evaluate the relationship between peak tibial acceleration and peak ankle joint contact forces in response to stride length manipulation during level-ground running.

METHODS

Twenty-seven physically active participants ran 10 trials at preferred speed in each of 5 stride length conditions: preferred, ±5 %, and ±10 % of preferred stride length. Motion capture, force platform, and tibial acceleration data were directly measured, and ankle joint contact forces were estimated using an inverse-dynamics-based static optimization routine.

RESULTS

In general, peak axial tibial accelerations (p < 0.001) as well as axial (p < 0.001) and resultant (p < 0.001) ankle joint contact forces increased with stride length. When averaged within the 10 strides of each stride condition, moderate positive correlations were observed between peak axial acceleration and joint contact force (r = 0.49) as well as peak resultant acceleration and joint contact force (r = 0.51). However, 37% of participants illustrated either no relationship or negative correlations. Only weak correlations across participants existed between peak axial acceleration and joint contact force (r = 0.12) as well as peak resultant acceleration and ankle joint contact force (r = 0.18) when examined on a step-by-step basis.

CONCLUSION

These results suggest that tibial acceleration should not be used as a surrogate for ankle joint contact force on a step-by-step basis in response to stride length manipulations during level-ground running. A 10-step averaged tibial acceleration metric may be useful for some runners, but an initial laboratory assessment would be required to identify these individuals.

Improving Biological Joint Moment Estimation During Real-World Tasks With EMG and Instrumented Insoles

OBJECTIVE

Real-time measurement of biological joint moment could enhance clinical assessments and generalize exoskeleton control. Accessing joint moments outside clinical and laboratory settings requires harnessing non-invasive wearable sensor data for indirect estimation. Previous approaches have been primarily validated during cyclic tasks, such as walking, but these methods are likely limited when translating to non-cyclic tasks where the mapping from kinematics to moments is not unique.

METHODS

We trained deep learning models to estimate hip and knee joint moments from kinematic sensors, electromyography (EMG), and simulated pressure insoles from a dataset including 10 cyclic and 18 non-cyclic activities. We assessed estimation error on combinations of sensor modalities during both activity types.

RESULTS

Compared to the kinematics-only baseline, adding EMG reduced RMSE by 16.9% at the hip and 30.4% at the knee (p < 0.05) and adding insoles reduced RMSE by 21.7% at the hip and 33.9% at the knee (p < 0.05). Adding both modalities reduced RMSE by 32.5% at the hip and 41.2% at the knee (p < 0.05) which was significantly higher than either modality individually (p < 0.05). All sensor additions improved model performance on non-cyclic tasks more than cyclic tasks (p < 0.05).

CONCLUSION

These results demonstrate that adding kinetic sensor information through EMG or insoles improves joint moment estimation both individually and jointly. These additional modalities are most important during non-cyclic tasks, tasks that reflect the variable and sporadic nature of the real-world.

SIGNIFICANCE

Improved joint moment estimation and task generalization is pivotal to developing wearable robotic systems capable of enhancing mobility in everyday life.

Consumer-priced wearable sensors combined with deep learning can be used to accurately predict ground reaction forces during various treadmill running conditions

Ground reaction force (GRF) data is often collected for the biomechanical analysis of running, due to the performance and injury risk insights that GRF analysis can provide. Traditional methods typically limit GRF collection to controlled lab environments, recent studies have looked to combine the ease of use of wearable sensors with the statistical power of machine learning to estimate continuous GRF data outside of these restrictions. Before such systems can be deployed with confidence outside of the lab they must be shown to be a valid and accurate tool for a wide range of users. The aim of this study was to evaluate how accurately a consumer-priced sensor system could estimate GRFs whilst a heterogeneous group of runners completed a treadmill protocol with three different personalised running speeds and three gradients. Fifty runners (25 female, 25 male) wearing pressure insoles made up of 16 resistive sensors and an inertial measurement unit ran at various speeds and gradients on an instrumented treadmill. A long short term memory (LSTM) neural network was trained to estimate both vertical ( G R F v ) and anteroposterior ( G R F a p ) force traces using leave one subject out validation. The average relative root mean squared error (rRMSE) was 3.2% and 3.1%, respectively. The mean ( G R F v ) rRMSE across the evaluated participants ranged from 0.8% to 8.8% and from 1.3% to 17.3% in the ( G R F a p ) estimation. The findings from this study suggest that current consumer-priced sensors could be used to accurately estimate two-dimensional GRFs for a wide range of runners at a variety of running intensities. The estimated kinetics could be used to provide runners with individualised feedback as well as form the basis of data collection for running injury risk factor studies on a much larger scale than is currently possible with lab based methods.

A Review of the Validity and Reliability of Accelerometer-Based Metrics From Upper Back-Mounted GNSS Player Tracking Systems for Athlete Training Load Monitoring

ABSTRACT

Dawson, L, Beato, M, Devereux, G, and McErlain-Naylor, SA. A review of the validity and reliability of accelerometer-based metrics from upper back-mounted GNSS player tracking systems for athlete training load monitoring. J Strength Cond Res 38(8): e459-e474, 2024-Athlete load monitoring using upper back-mounted global navigation satellite system (GNSS) player tracking is common within many team sports. However, accelerometer-based load monitoring may provide information that cannot be achieved with GNSS alone. This review focuses on the accelerometer-based metrics quantifying the accumulation of accelerations as an estimation of athlete training load, appraising the validity and reliability of accelerometer use in upper back-mounted GNSS player tracking systems, the accelerometer-based metrics, and their potential for application within athlete monitoring. Reliability of GNSS-housed accelerometers and accelerometer-based metrics are dependent on the equipment model, signal processing methods, and the activity being monitored. Furthermore, GNSS unit placement on the upper back may be suboptimal for accelerometer-based estimation of mechanical load. Because there are currently no feasible gold standard comparisons for field-based whole-body biomechanical load, the validity of accelerometer-based load metrics has largely been considered in relation to other measures of training load and exercise intensity. In terms of convergent validity, accelerometer-based metrics (e.g., PlayerLoad, Dynamic Stress Load, Body Load) have correlated, albeit with varying magnitudes and certainty, with measures of internal physiological load, exercise intensity, total distance, collisions and impacts, fatigue, and injury risk and incidence. Currently, comparisons of these metrics should not be made between athletes because of mass or technique differences or between manufacturers because of processing variations. Notable areas for further study include the associations between accelerometer-based metrics and other parts of biomechanical load-adaptation pathways of interest, such as internal biomechanical loads or methods of manipulating these metrics through effective training design.

Athletic Injury Research: Frameworks, Models and the Need for Causal Knowledge

Within applied sports science and medicine research, many challenges hinder the establishment and detailed understanding of athletic injury causality as well as the development and implementation of appropriate athletic injury prevention strategies. Applied research efforts are faced with a lack of variable control, while the capacity to compensate for this lack of control through the application of randomised controlled trials is often confronted by a number of obstacles relating to ethical or practical constraints. Such difficulties have led to a large reliance upon observational research to guide applied practice in this area. However, the reliance upon observational research, in conjunction with the general absence of supporting causal inference tools and structures, has hindered both the acquisition of causal knowledge in relation to athletic injury and the development of appropriate injury prevention strategies. Indeed, much of athletic injury research functions on a (causal) model-blind observational approach primarily driven by the existence and availability of various technologies and data, with little regard for how these technologies and their associated metrics can conceptually relate to athletic injury causality and mechanisms. In this article, a potential solution to these issues is proposed and a new model for investigating athletic injury aetiology and mechanisms, and for developing and evaluating injury prevention strategies, is presented. This solution is centred on the construction and utilisation of various causal diagrams, such as frameworks, models and causal directed acyclic graphs (DAGs), to help guide athletic injury research and prevention efforts. This approach will alleviate many of the challenges facing athletic injury research by facilitating the investigation of specific causal links, mechanisms and assumptions with appropriate scientific methods, aiding the translation of lab-based research into the applied sporting world, and guiding causal inferences from applied research efforts by establishing appropriate supporting causal structures. Further, this approach will also help guide the development and adoption of both relevant metrics (and technologies) and injury prevention strategies, as well as encourage the construction of appropriate theoretical and conceptual foundations prior to the commencement of applied injury research studies. This will help minimise the risk of resource wastage, data fishing, p-hacking and hypothesising after the results are known (HARK-ing) in athletic injury research.

Are Gait Patterns during In-Lab Running Representative of Gait Patterns during Real-World Training? An Experimental Study

Biomechanical assessments of running typically take place inside motion capture laboratories. However, it is unclear whether data from these in-lab gait assessments are representative of gait during real-world running. This study sought to test how well real-world gait patterns are represented by in-lab gait data in two cohorts of runners equipped with consumer-grade wearable sensors measuring speed, step length, vertical oscillation, stance time, and leg stiffness. Cohort 1 (N = 49) completed an in-lab treadmill run plus five real-world runs of self-selected distances on self-selected courses. Cohort 2 (N = 19) completed a 2.4 km outdoor run on a known course plus five real-world runs of self-selected distances on self-selected courses. The degree to which in-lab gait reflected real-world gait was quantified using univariate overlap and multivariate depth overlap statistics, both for all real-world running and for real-world running on flat, straight segments only. When comparing in-lab and real-world data from the same subject, univariate overlap ranged from 65.7% (leg stiffness) to 95.2% (speed). When considering all gait metrics together, only 32.5% of real-world data were well-represented by in-lab data from the same subject. Pooling in-lab gait data across multiple subjects led to greater distributional overlap between in-lab and real-world data (depth overlap 89.3-90.3%) due to the broader variability in gait seen across (as opposed to within) subjects. Stratifying real-world running to only include flat, straight segments did not meaningfully increase the overlap between in-lab and real-world running (changes of <1%). Individual gait patterns during real-world running, as characterized by consumer-grade wearable sensors, are not well-represented by the same runner's in-lab data. Researchers and clinicians should consider "borrowing" information from a pool of many runners to predict individual gait behavior when using biomechanical data to make clinical or sports performance decisions.

Rethinking running biomechanics: a critical review of ground reaction forces, tibial bone loading, and the role of wearable sensors

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.

Integrating an LSTM framework for predicting ankle joint biomechanics during gait using inertial sensors

The ankle joint plays a crucial role in gait, facilitating the articulation of the lower limb, maintaining foot-ground contact, balancing the body, and transmitting the center of gravity. This study aimed to implement long short-term memory (LSTM) networks for predicting ankle joint angles, torques, and contact forces using inertial measurement unit (IMU) sensors. Twenty-five healthy participants were recruited. Two IMU sensors were attached to the foot dorsum and the vertical axis of the distal anteromedial tibia in the right lower limb to record acceleration and angular velocity during running. We proposed a LSTM-MLP (multilayer perceptron) model for training time-series data from IMU sensors and predicting ankle joint biomechanics. The model underwent validation and testing using a custom nested k-fold cross-validation process. The average values of the coefficient of determination (R2), mean absolute error (MAE), and mean squared error (MSE) for ankle dorsiflexion joint and moment, subtalar inversion joint and moment, and ankle joint contact forces were 0.89 ± 0.04, 0.75 ± 1.04, and 2.96 ± 4.96 for walking, and 0.87 ± 0.07, 0.88 ± 1.26, and 4.1 ± 7.17 for running, respectively. This study demonstrates that IMU sensors, combined with LSTM neural networks, are invaluable tools for evaluating ankle joint biomechanics in lower limb pathological diagnosis and rehabilitation, offering a cost-effective and versatile alternative to traditional experimental settings.

E-Textiles for Sports and Fitness Sensing: Current State, Challenges, and Future Opportunities

E-textiles have emerged as a fast-growing area in wearable technology for sports and fitness due to the soft and comfortable nature of textile materials and the capability for smart functionality to be integrated into familiar sports clothing. This review paper presents the roles of wearable technologies in sport and fitness in monitoring movement and biosignals used to assess performance, reduce injury risk, and motivate training/exercise. The drivers of research in e-textiles are discussed after reviewing existing non-textile and textile-based commercial wearable products. Different sensing components/materials (e.g., inertial measurement units, electrodes for biosignals, piezoresistive sensors), manufacturing processes, and their applications in sports and fitness published in the literature were reviewed and discussed. Finally, the paper presents the current challenges of e-textiles to achieve practical applications at scale and future perspectives in e-textiles research and development.

3D Tibial Acceleration and Consideration of 3D Angular Motion Using IMUs on Peak Tibial Acceleration and Impulse in Running

PURPOSE

Peak tibial acceleration (PTA) is defined as the peak acceleration occurring shortly after initial contact, often used as an indirect measure of tibial load. As the tibia is a rotating segment around the ankle, angular velocity and angular acceleration should be included in PTA. This study aimed to quantify three-dimensional tibial acceleration components over two different sensor locations and three running speeds, to get a better understanding of the influence of centripetal and tangential accelerations on PTA typically measured in running. Furthermore, it explores tibial impulse as an alternative surrogate measure for tibial load.

METHODS

Fifteen participants ran 90 s on a treadmill at 2.8, 3.3, and 3.9 m·s -1 , with inertial measurement units (IMUs) located distally and proximally on the tibia.

RESULTS

Without the inclusion of rotational accelerations and gravity, no significant difference was found between axial PTA between both IMU locations, whereas in the tangential sagittal plane axis, there was a significant difference. Inclusion of rotational accelerations and gravity resulted in similar PTA estimates at the ankle for both IMU locations and caused a significant difference between PTA based on the distal IMU and PTA at the ankle. The impulse showed more consistent results between the proximal and distal IMU locations compared with axial PTA.

CONCLUSIONS

Rotational acceleration of the tibia during stance differently impacted PTA measured proximally and distally at the tibia, indicating that rotational acceleration and gravity should be included in PTA estimates. Furthermore, peak acceleration values (such as PTA) are not always reliable when using IMUs because of inconsistent PTA proximally compared with distally on an individual level. Instead, impulse seems to be a more consistent surrogate measure for the tibial load.

A Dynamic Ankle Orthosis Reduces Tibial Compressive Force and Increases Ankle Motion Compared With a Walking Boot

PURPOSE

Tibial bone stress injuries are a common overuse injury among runners and military cadets. Current treatment involves wearing an orthopedic walking boot for 3 to 12 wk, which limits ankle motion and leads to lower limb muscle atrophy. A dynamic ankle orthosis (DAO) was designed to provide a distractive force that offloads in-shoe vertical force and retains sagittal ankle motion during walking. It remains unclear how tibial compressive force is altered by the DAO. This study compared tibial compressive force and ankle motion during walking between the DAO and an orthopedic walking boot.

METHODS

Twenty young adults walked on an instrumented treadmill at 1.0 m·s -1 in two brace conditions: DAO and walking boot. Three-dimensional kinematic, ground reaction forces, and in-shoe vertical force data were collected to calculate peak tibial compressive force. Paired t -tests and Cohen's d effect sizes were used to assess mean differences between conditions.

RESULTS

Peak tibial compressive force ( P = 0.023; d = 0.5) and Achilles tendon force ( P = 0.017; d = 0.5) were moderately lower in the DAO compared with the walking boot. Sagittal ankle excursion was 54.9% greater in the DAO compared with the walking boot ( P = 0.05; d = 3.1).

CONCLUSIONS

The findings from this study indicated that the DAO moderately reduced tibial compressive force and Achilles tendon force and allowed more sagittal ankle excursion during treadmill walking compared with an orthopedic walking boot.

Wearable sensor and machine learning estimate tendon load and walking speed during immobilizing boot ambulation

The purpose of this study is to develop a wearable paradigm to accurately monitor Achilles tendon loading and walking speed using wearable sensors that reduce subject burden. Ten healthy adults walked in an immobilizing boot under various heel wedge conditions (30°, 5°, 0°) and walking speeds. Three-dimensional motion capture, ground reaction force, and 6-axis inertial measurement unit (IMU) signals were collected. We used a Least Absolute Shrinkage and Selection Operator (LASSO) regression to predict peak Achilles tendon load and walking speed. The effects of altering sensor parameters were also explored. Walking speed models (mean absolute percentage error (MAPE): 8.81 ± 4.29%) outperformed tendon load models (MAPE: 34.93 ± 26.3%). Models trained with subject-specific data performed better than models trained without subject-specific data. Removing the gyroscope, decreasing the sampling frequency, and using combinations of sensors did not change the usability of the models, having inconsequential effects on model performance. We developed a simple monitoring paradigm that uses LASSO regression and wearable sensors to accurately predict (MAPE ≤ 12.6%) Achilles tendon loading and walking speed while ambulating in an immobilizing boot. This paradigm provides a clinically implementable strategy to longitudinally monitor patient loading and activity while recovering from Achilles tendon injuries.

A Wearable Biofeedback Device for Monitoring Tibial Load During Partial Weight-Bearing Walking

Patients with tibial fractures are usually advised to follow a partial weight-bearing gait rehabilitation program after surgery to promote bone healing and lower limb functional recovery. Currently, the biofeedback devices used for gait rehabilitation training in fracture patients use ground reaction force (GRF) as the indicator of tibial load. However, an increasing body of research has shown that monitoring GRF alone cannot objectively reflect the load on the lower limb bones during human movement. In this study, a novel biofeedback system was developed utilizing inertial measurement units and custom instrumented insoles. Based on the data collected from experiments, a hybrid approach combining a physics-based model and neural network architectures was used to predict tibial force. Compared to the traditional physics-based algorithm, the physical guided neural networks method showed better predictive performance. The study also found that regardless of the type of weight-bearing walking, the peak tibial force was significantly higher than the peak tibial GRF, and the time at which the peak tibial compression force occurs may not be consistent with the time at which the peak vertical GRF occurs. This further supports the idea that during gait rehabilitation training for patients with tibial fractures, monitoring and providing feedback on the actual tibial force rather than just the GRF is necessary. The developed device is a non-invasive and reliable portable device that can provide audio feedback, providing a viable solution for gait rehabilitation training outside laboratory and helping to optimize patients' rehabilitation treatment strategies.

Intelligent prediction of lower extremity loadings during badminton lunge footwork in a lab-simulated court

Introduction: Playing badminton has been reported with extensive health benefits, while main injuries were documented in the lower extremity. This study was aimed to investigate and predict the knee- and ankle-joint loadings of athletes who play badminton, with "gold standard" facilities. The axial impact acceleration from wearables would be used to predict joint moments and contact forces during sub-maximal and maximal lunge footwork. Methods: A total of 25 badminton athletes participated in this study, following a previously established protocol of motion capture and musculoskeletal modelling techniques with the integration of a wearable inertial magnetic unit (IMU). We developed a principal component analysis (PCA) statistical model to extract features in the loading parameters and a multivariate partial least square regression (PLSR) machine learning model to correlate easily collected variables, such as the stance time, approaching velocity, and peak accelerations, with knee and ankle loading parameters (moments and contact forces). Results: The key variances of joint loadings were observed from statistical principal component analysis modelling. The promising accuracy of the partial least square regression model using input parameters was observed with a prediction accuracy of 94.52%, while further sensitivity analysis found a single variable from the ankle inertial magnetic unit that could predict an acceptable range (93%) of patterns and magnitudes of the knee and ankle loadings. Conclusion: The attachment of this single inertial magnetic unit sensor could be used to record and predict loading accumulation and distribution, and placement would exhibit less influence on the motions of the lower extremity. The intelligent prediction of loading patterns and accumulation could be integrated to design training and competition schemes in badminton or other court sports in a scientific manner, thus preventing fatigue, reducing loading-accumulation-related injury, and maximizing athletic performance.

A trained neural network model accurately predicts Achilles tendon stress during walking and running based on shear wave propagation

Shear wave tensiometry is a noninvasive technique for measuring tendon loading during activity based on the speed of a shear wave traveling along the tendon. Shear wave speed has been shown to modulate with axial stress, but calibration is required to obtain absolute measures of tendon loading. However, the current technique only makes use of wave speed, whereas other characteristics of the wave (e.g., amplitude, frequency content) may also vary with tendon loading. It is possible that these data could be used in addition to wave speed to circumvent the need for calibration. Given the potential complex relationships to tendon loading, and the lack of an analytical model to guide the use of these data, it is sensible to use a machine learning approach. Here, we used an ensemble neural network approach to predict inverse dynamics estimates of Achilles tendon stress from shear wave tensiometry data collected in a prior study. Neural network-predicted stresses were highly correlated with stance phase inverse dynamics estimates for walking (R2 = 0.89 ± 0.06) and running (R2 = 0.87 ± 0.11) data reserved for neural network model testing and not included in model training. Additionally, error between neural network-predicted and inverse dynamics-estimated stress was reasonable (walking: RMSD = 11 ± 2% of peak load; running: 25 ± 14%). Results of this pilot analysis suggest that a machine learning approach could reduce the reliance of shear wave tensiometry on calibration and expand its usability in many settings.

Wearable sensor and machine learning accurately estimate tendon load and walking speed during immobilizing boot ambulation

Achilles tendon injuries are treated with progressive weight bearing to promote tendon healing and restore function. Patient rehabilitation progression are typically studied in controlled, lab settings and do not represent the long-term loading experienced during daily living. The purpose of this study is to develop a wearable paradigm to accurately monitor Achilles tendon loading and walking speed using low-cost sensors that reduce subject burden. Ten healthy adults walked in an immobilizing boot under various heel wedge conditions (30°, 5°, 0°) and walking speeds. Three-dimensional motion capture, ground reaction force, and 6-axis inertial measurement unit (IMU) signals were collected per trial. We used Least Absolute Shrinkage and Selection Operator (LASSO) regression to predict peak Achilles tendon load and walking speed. The effects of using only accelerometer data, different sampling frequency, and multiple sensors to train the model were also explored. Walking speed models outperformed (mean absolute percentage error (MAPE): 8.41 ± 4.08%) tendon load models (MAPE: 33.93 ± 23.9%). Models trained with subject-specific data performed significantly better than generalized models. For example, our personalized model that was trained with only subject-specific data predicted tendon load with a 11.5 ± 4.41% MAPE and walking speed with a 4.50 ± 0.91% MAPE. Removing gyroscope channels, decreasing sampling frequency, and using combinations of sensors had inconsequential effects on models performance (changes in MAPE < 6.09%). We developed a simple monitoring paradigm that uses LASSO regression and wearable sensors to accurately predict Achilles tendon loading and walking speed while ambulating in an immobilizing boot. This paradigm provides a clinically implementable strategy to longitudinally monitor patient loading and activity while recovering from Achilles tendon injuries.

A Wearable Real-time Kinematic and Kinetic Measurement Sensor Setup for Human Locomotion

Current laboratory-based setups (optical marker cameras + force plates) for human motion measurement require participants to stay in a constrained capture region which forbids rich movement types. This study established a fully wearable system, based on commercially available sensors (inertial measurement units + pressure insoles) that can measure both kinematic and kinetic motion data simultaneously and support wireless frame-by-frame streaming. In addition, its capability and accuracy were tested against a conventional laboratory-based setup. An experiment was conducted, with 9 participants wearing the wearable measurement system and performing 13 daily motion activities, from slow walking to fast running, together with vertical jump, squat, lunge and single-leg landing, inside the capture space of the laboratory-based motion capture system. The recorded sensor data were post-processed to obtain joint angles, ground reaction forces (GRFs), and joint torques (via multi-body inverse dynamics). Compared to the laboratory-based system, the established wearable measurement system can measure accurate information of all lower limb joint angles (Pearson's r = 0.929), vertical GRFs (Pearson's r = 0.954), and ankle joint torques (Pearson's r = 0.917). Center of pressure (CoP) in the anterior-posterior direction and knee joint torques were fairly matched (Pearson's r = 0.683 and 0.612, respectively). Calculated hip joint torques and measured medial-lateral CoP did not match with the laboratory-based system (Pearson's r = 0.21 and 0.47, respectively). Furthermore, both raw and processed datasets are openly accessible (https://doi.org/10.5281/zenodo.6457662). Documentation, data processing codes, and guidelines to establish the real-time wearable kinetic measurement system are also shared (https://github.com/HuaweiWang/WearableMeasurementSystem).

Estimation of ground reaction force waveforms during fixed pace running outside the laboratory

In laboratory experiments, biomechanical data collections with wearable technologies and machine learning have been promising. Despite the development of lightweight portable sensors and algorithms for the identification of gait events and estimation of kinetic waveforms, machine learning models have yet to be used to full potential. We propose the use of a Long Short Term Memory network to map inertial data to ground reaction force data gathered in a semi-uncontrolled environment. Fifteen healthy runners were recruited for this study, with varied running experience: novice to highly trained runners (<15 min 5 km race), and ages ranging from 18 to 64 years old. Force sensing insoles were used to measure normal foot-shoe forces, providing the standard for identification of gait events and measurement of kinetic waveforms. Three inertial measurement units (IMUs) were mounted to each participant, two bilaterally on the dorsal aspect of the foot and one clipped to the back of each participant's waistband, approximating their sacrum. Data input into the Long Short Term Memory network were from the three IMUs and output were estimated kinetic waveforms, compared against the standard of the force sensing insoles. The range of RMSE for each stance phase was from 0.189-0.288 BW, which is similar to multiple previous studies. Estimation of foot contact had an r ² = 0.795. Estimation of kinetic variables varied, with peak force presenting the best output with an r ² = 0.614. In conclusion, we have shown that at controlled paces over level ground a Long Short Term Memory network can estimate 4 s temporal windows of ground reaction force data across a range of running speeds.

How Accurately Can Wearable Sensors Assess Low Back Disorder Risks during Material Handling? Exploring the Fundamental Capabilities and Limitations of Different Sensor Signals

Low back disorders (LBDs) are a leading occupational health issue. Wearable sensors, such as inertial measurement units (IMUs) and/or pressure insoles, could automate and enhance the ergonomic assessment of LBD risks during material handling. However, much remains unknown about which sensor signals to use and how accurately sensors can estimate injury risk. The objective of this study was to address two open questions: (1) How accurately can we estimate LBD risk when combining trunk motion and under-the-foot force data (simulating a trunk IMU and pressure insoles used together)? (2) How much greater is this risk assessment accuracy than using only trunk motion (simulating a trunk IMU alone)? We developed a data-driven simulation using randomized lifting tasks, machine learning algorithms, and a validated ergonomic assessment tool. We found that trunk motion-based estimates of LBD risk were not strongly correlated (r range: 0.20-0.56) with ground truth LBD risk, but adding under-the-foot force data yielded strongly correlated LBD risk estimates (r range: 0.93-0.98). These results raise questions about the adequacy of a single IMU for LBD risk assessment during material handling but suggest that combining an IMU on the trunk and pressure insoles with trained algorithms may be able to accurately assess risks.

Peak tibial acceleration should not be used as indicator of tibial bone loading during running

Peak tibial acceleration (PTA) is a widely used indicator of tibial bone loading. Indirect bone loading measures are of interest to reduce the risk of stress fractures during running. However, tibial compressive forces are caused by both internal muscle forces and external ground reaction forces. PTA might reflect forces from outside the body, but likely not the compressive force from muscles on the tibial bone. Hence, the strength of the relationship between PTA and maximum tibial compression forces in rearfoot-striking runners was investigated. Twelve runners ran on an instrumented treadmill while tibial acceleration was captured with accelerometers. Force plate and inertial measurement unit data were spatially aligned with a novel method based on the centre of pressure crossing a virtual toe marker. The correlation coefficient between maximum tibial compression forces and PTA was 0.04 ± 0.14 with a range of -0.15 to +0.28. This study showed a very weak and non-significant correlation between PTA and maximum tibial compression forces while running on a level treadmill at a single speed. Hence, PTA as an indicator for tibial bone loading should be reconsidered, as PTA does not provide a complete picture of both internal and external compressive forces on the tibial bone.  .

Comparison of different machine learning models to enhance sacral acceleration-based estimations of running stride temporal variables and peak vertical ground reaction force

Machine learning (ML) was used to predict contact (tc) and flight (tf) time, duty factor (DF) and peak vertical force (Fv,max) from IMU-based estimations. One hundred runners ran on an instrumented treadmill (9-13 km/h) while wearing a sacral-mounted IMU. Linear regression (LR), support vector regression and two-layer neural-network were trained (80 participants) using IMU-based estimations, running speed, stride frequency and body mass. Predictions (remaining 20 participants) were compared to gold standard (kinetic data collected using the force plate) by calculating the mean absolute percentage error (MAPE). MAPEs of Fv,max did not significantly differ among its estimation and predictions (P = 0.37), while prediction MAPEs for tc, tf and DF were significantly smaller than corresponding estimation MAPEs (P ≤ 0.003). There were no significant differences among prediction MAPEs obtained from the three ML models (P ≥ 0.80). Errors of the ML models were equal to or smaller than (≤32%) the smallest real difference for the four variables, while errors of the estimations were not (15-45%), indicating that ML models were sufficiently accurate to detect a clinically important difference. The simplest ML model (LR) should be used to improve the accuracy of the IMU-based estimations. These improvements may be beneficial when monitoring running-related injury risk factors in real-world settings.

Wearables for Running Gait Analysis: A Systematic Review

BACKGROUND

Running gait assessment has traditionally been performed using subjective observation or expensive laboratory-based objective technologies, such as three-dimensional motion capture or force plates. However, recent developments in wearable devices allow for continuous monitoring and analysis of running mechanics in any environment. Objective measurement of running gait is an important (clinical) tool for injury assessment and provides measures that can be used to enhance performance.

OBJECTIVES

We aimed to systematically review the available literature investigating how wearable technology is being used for running gait analysis in adults.

METHODS

A systematic search of the literature was conducted in the following scientific databases: PubMed, Scopus, Web of Science and SPORTDiscus. Information was extracted from each included article regarding the type of study, participants, protocol, wearable device(s), main outcomes/measures, analysis and key findings.

RESULTS

A total of 131 articles were reviewed: 56 investigated the validity of wearable technology, 22 examined the reliability and 77 focused on applied use. Most studies used inertial measurement units (n = 62) [i.e. a combination of accelerometers, gyroscopes and magnetometers in a single unit] or solely accelerometers (n = 40), with one using gyroscopes alone and 31 using pressure sensors. On average, studies used one wearable device to examine running gait. Wearable locations were distributed among the shank, shoe and waist. The mean number of participants was 26 (± 27), with an average age of 28.3 (± 7.0) years. Most studies took place indoors (n = 93), using a treadmill (n = 62), with the main aims seeking to identify running gait outcomes or investigate the effects of injury, fatigue, intrinsic factors (e.g. age, sex, morphology) or footwear on running gait outcomes. Generally, wearables were found to be valid and reliable tools for assessing running gait compared to reference standards.

CONCLUSIONS

This comprehensive review highlighted that most studies that have examined running gait using wearable sensors have done so with young adult recreational runners, using one inertial measurement unit sensor, with participants running on a treadmill and reporting outcomes of ground contact time, stride length, stride frequency and tibial acceleration. Future studies are required to obtain consensus regarding terminology, protocols for testing validity and the reliability of devices and suitability of gait outcomes.

CLINICAL TRIAL REGISTRATION

CRD42021235527.

Effect of pressure insole sampling frequency on insole-measured peak force accuracy during running

Pressure sensing insoles enable us to estimate forces under the feet during activities such as running, which can provide valuable insight into human movement. Pressure insoles also afford the opportunity to collect more data in more representative environments than can be achieved in laboratory studies. One key challenge with real-world use of pressure insoles is limited battery life which restricts the amount of data that can be collected on a single charge. Reducing sampling frequency is one way to prolong battery life, at the cost of decreased measurement accuracy, but this trade-off has not been quantified, which hinders decision-making by researchers and developers. Therefore, we characterized the effect of decreasing sampling frequency on peak force estimates from pressure insoles (Novel Pedar, 100 Hz) across a range of running speeds and slopes. Data were downsampled to 50, 33, 25, 20, 16 and 10 Hz. Force peaks were extracted due to their importance in biomechanical algorithms trained to estimate musculoskeletal forces and were compared with the reference sampling frequency of 100 Hz to compute relative errors. Peak force errors increased exponentially from 0.7% (50 Hz) to 9% (10 Hz). However, peak force errors were < 3% for all sampling frequencies down to 20 Hz. For some pressure insoles, sampling rate is inversely proportional to battery life. Therefore, these findings suggest that battery life could be increased up to 5x at the expense of 3% errors. These results are encouraging for researchers aiming to deploy pressure insoles for remote monitoring or in longitudinal studies.

Ubiquitous Computing in Sports and Physical Activity-Recent Trends and Developments

The use of small, interconnected and intelligent tools within the broad framework of pervasive computing for analysis and assessments in sport and physical activity is not a trend in itself but defines a way for information to be handled, processed and utilised: everywhere, at any time. The demand for objective data to support decision making prompted the adoption of wearables that evolve to fulfil the aims of assessing athletes and practitioners as closely as possible with their performance environments. In the present paper, we mention and discuss the advancements in ubiquitous computing in sports and physical activity in the past 5 years. Thus, recent developments in wearable sensors, cloud computing and artificial intelligence tools have been the pillars for a major change in the ways sport-related analyses are performed. The focus of our analysis is wearable technology, computer vision solutions for markerless tracking and their major contribution to the process of acquiring more representative data from uninhibited actions in realistic ecological conditions. We selected relevant literature on the applications of such approaches in various areas of sports and physical activity while outlining some limitations of the present-day data acquisition and data processing practices and the resulting sensors' functionalities, as well as the limitations to the data-driven informed decision making in the current technological and scientific framework. Finally, we hypothesise that a continuous merger of measurement, processing and analysis will lead to the development of more reliable models utilising the advantages of open computing and unrestricted data access and allow for the development of personalised-medicine-type approaches to sport training and performance.

Tibial bone forces can be monitored using shoe-worn wearable sensors during running

Tibial bone stress injury is a common overuse injury experienced by runners, which results from repetitive tissue forces. Wearable sensor systems (wearables) that monitor tibial forces could help understand and reduce injury incidence. However, there are currently no validated wearables that monitor tibial bone forces. Previous work using simulated wearables demonstrated accurate tibial force estimates by combining a shoe-worn inertial measurement unit (IMU) and pressure insole with a trained algorithm. This study aimed assessed how accurately tibial bone forces could be estimated with existing wearables. Nine recreational runners ran at a series of different speeds and slopes, and with various stride patterns. Shoe-worn IMU and insole data were input into a trained algorithm to estimate peak tibial force. We found an average error of 5.7% in peak tibial force estimates compared with lab-based estimates calculated using motion capture and a force instrumented treadmill. Insole calibration procedures were essential to achieving accurate tibial force estimates. We concluded that a shoe-worn, multi-sensor system is a promising approach to monitoring tibial bone forces in running. This study adds to the literature demonstrating the potential of wearables to monitor musculoskeletal forces, which could positively impact injury prevention, and scientific understanding.

Acute Effects of Gait Interventions on Tibial Loads During Running: A Systematic Review and Meta-analysis

Introduction

Changing running technique or equipment can alter tibial loads. The efficacy of interventions to modify tibial loads during running is yet to be synthesised and evaluated. This article reviewed the effect of running technique and footwear interventions on tibial loading during running.

Methods

Electronic databases were searched using terms relevant to tibial load and running. Interventions were categorised according to their approach (i.e., footwear; barefoot running; speed; surface; overground versus treadmill; orthotics, insoles and taping; and technique); if necessary, further subgrouping was applied to these categories. Standardised mean differences (SMDs) with 95% confidence intervals (CIs) for changes in tibial loading were calculated and meta-analyses performed where possible.

Results

Database searches yielded 1617 articles, with 36 meeting the inclusion criteria. Tibial loading increased with (1) barefoot running (SMD 1.16; 95% CI 0.50, 1.82); (2) minimalist shoe use by non-habitual users (SMD 0.89; 95% CI 0.40, 1.39); (3) motion control shoe use (SMD 0.46; 95% CI 0.07, 0.84); (4) increased stride length (SMD 0.86; 95% CI 0.18, 1.55); and (5) increased running speed (SMD 1.03; 95% CI 0.74, 1.32). Tibial loading decreased when (1) individuals ran on a treadmill versus overground (SMD − 0.83; 95% CI − 1.53, − 0.12); and (2) targeted biofeedback was used (SMD − 0.93; 95% CI − 1.46, − 0.41).

Conclusions

Running barefoot, in motion control shoes or in unfamiliar minimalist shoes, and with an increased stride length increases tibial loads and may increase the risk of a tibial stress injury during periods of high training load. Adopting interventions such as running on a treadmill versus overground, and using targeted biofeedback during periods of high loads could reduce tibial stress injury.

Recent Machine Learning Progress in Lower Limb Running Biomechanics With Wearable Technology: A Systematic Review

With the emergence of wearable technology and machine learning approaches, gait monitoring in real-time is attracting interest from the sports biomechanics community. This study presents a systematic review of machine learning approaches in running biomechanics using wearable sensors. Electronic databases were retrieved in PubMed, Web of Science, SPORTDiscus, Scopus, IEEE Xplore, and ScienceDirect. A total of 4,068 articles were identified via electronic databases. Twenty-four articles that met the eligibility criteria after article screening were included in this systematic review. The range of quality scores of the included studies is from 0.78 to 1.00, with 40% of articles recruiting participant numbers between 20 and 50. The number of inertial measurement unit (IMU) placed on the lower limbs varied from 1 to 5, mainly in the pelvis, thigh, distal tibia, and foot. Deep learning algorithms occupied 57% of total machine learning approaches. Convolutional neural networks (CNN) were the most frequently used deep learning algorithm. However, the validation process for machine learning models was lacking in some studies and should be given more attention in future research. The deep learning model combining multiple CNN and recurrent neural networks (RNN) was observed to extract different running features from the wearable sensors and presents a growing trend in running biomechanics.

Bone stress injuries

Bone stress injuries, including stress fractures, are overuse injuries that lead to substantial morbidity in active individuals. These injuries occur when excessive repetitive loads are introduced to a generally normal skeleton. Although the precise mechanisms for bone stress injuries are not completely understood, the prevailing theory is that an imbalance in bone metabolism favours microdamage accumulation over its removal and replacement with new bone via targeted remodelling. Diagnosis is achieved by a combination of patient history and physical examination, with imaging used for confirmation. Management of bone stress injuries is guided by their location and consequent risk of healing complications. Bone stress injuries at low-risk sites typically heal with activity modification followed by progressive loading and return to activity. Additional treatment approaches include non-weight-bearing immobilization, medications or surgery, but these approaches are usually limited to managing bone stress injuries that occur at high-risk sites. A comprehensive strategy that integrates anatomical, biomechanical and biological risk factors has the potential to improve the understanding of these injuries and aid in their prevention and management.

Inertial Motion Capture-Based Wearable Systems for Estimation of Joint Kinetics: A Systematic Review

In biomechanics, joint kinetics has an important role in evaluating the mechanical load of the joint and understanding its motor function. Although an optical motion capture (OMC) system has mainly been used to evaluate joint kinetics in combination with force plates, inertial motion capture (IMC) systems have recently been emerging in joint kinetic analysis due to their wearability and ubiquitous measurement capability. In this regard, numerous studies have been conducted to estimate joint kinetics using IMC-based wearable systems. However, these have not been comprehensively addressed yet. Thus, the aim of this review is to explore the methodology of the current studies on estimating joint kinetic variables by means of an IMC system. From a systematic search of the literature, 48 studies were selected. This paper summarizes the content of the selected literature in terms of the (i) study characteristics, (ii) methodologies, and (iii) study results. The estimation methods of the selected studies are categorized into two types: the inverse dynamics-based method and the machine learning-based method. While these two methods presented different characteristics in estimating the kinetic variables, it was demonstrated in the literature that both methods could be applied with good performance for the kinetic analysis of joints in different daily activities.

Wearables for Biomechanical Performance Optimization and Risk Assessment in Industrial and Sports Applications

Wearable technologies are emerging as a useful tool with many different applications. While these devices are worn on the human body and can capture numerous data types, this literature review focuses specifically on wearable use for performance enhancement and risk assessment in industrial- and sports-related biomechanical applications. Wearable devices such as exoskeletons, inertial measurement units (IMUs), force sensors, and surface electromyography (EMG) were identified as key technologies that can be used to aid health and safety professionals, ergonomists, and human factors practitioners improve user performance and monitor risk. IMU-based solutions were the most used wearable types in both sectors. Industry largely used biomechanical wearables to assess tasks and risks wholistically, which sports often considered the individual components of movement and performance. Availability, cost, and adoption remain common limitation issues across both sports and industrial applications.

Experimental recommendations for estimating lower extremity loading based on joint and activity

Researchers often estimate joint loading using musculoskeletal models to solve the inverse dynamics problem. This approach is powerful because it can be done non-invasively, however, it relies on assumptions and physical measurements that are prone to measurement error. The purpose of this study was to determine the impact of these errors - specifically, segment mass and shear ground reaction force - have on analyzing joint loads during activities of daily living. We performed traditional marker-based motion capture analysis on 8 healthy adults while they completed a battery of exercises on 6 degree of freedom force plates. We then scaled the mass of each segment as well as the shear component of the ground reaction force in 5% increments between 0 and 200% and iteratively performed inverse dynamics calculations, resulting in 1681 mass-shear combinations per activity. We compared the peak joint moments of the ankle, knee, and hip at each mass-shear combination to the 100% mass and 100% shear combination to determine the percent error. We found that the ankle was most resistant to changes in both mass and shear and the knee was resistant to changes in mass while the hip was sensitive to changes in both mass and shear. These results can help guide researchers who are pursuing lower-cost or more convenient data collection setups.

Preventing Bone Stress Injuries in Runners with Optimal Workload

Bone stress injuries (BSIs) occur at inopportune times to invariably interrupt training. All BSIs in runners occur due to an "error" in workload wherein the interaction between the number and magnitude of bone tissue loading cycles exceeds the ability of the tissue to resist the repetitive loads. There is not a single optimal bone workload, rather a range which is influenced by the prevailing scenario. In prepubertal athletes, optimal bone workload consists of low-repetitions of fast, high-magnitude, multidirectional loads introduced a few times per day to induce bone adaptation. Premature sports specialization should be avoided so as to develop a robust skeleton that is structurally optimized to withstand multidirectional loading. In the mature skeleton, optimal workload enables gains in running performance but minimizes bone damage accumulation by sensibly progressing training, particularly training intensity. When indicated (e.g., following repeated BSIs), attempts to reduce bone loading magnitude should be considered, such as increasing running cadence. Determining the optimal bone workload for an individual athlete to prevent and manage BSIs requires consistent monitoring. In the future, it may be possible to clinically determine bone loads at the tissue level to facilitate workload progressions and prescriptions.

Ankle Angle Prediction Using a Footwear Pressure Sensor and a Machine Learning Technique

Ankle injuries may adversely increase the risk of injury to the joints of the lower extremity and can lead to various impairments in workplaces. The purpose of this study was to predict the ankle angles by developing a footwear pressure sensor and utilizing a machine learning technique. The footwear sensor was composed of six FSRs (force sensing resistors), a microcontroller and a Bluetooth LE chipset in a flexible substrate. Twenty-six subjects were tested in squat and stoop motions, which are common positions utilized when lifting objects from the floor and pose distinct risks to the lifter. The kNN (k-nearest neighbor) machine learning algorithm was used to create a representative model to predict the ankle angles. For the validation, a commercial IMU (inertial measurement unit) sensor system was used. The results showed that the proposed footwear pressure sensor could predict the ankle angles at more than 93% accuracy for squat and 87% accuracy for stoop motions. This study confirmed that the proposed plantar sensor system is a promising tool for the prediction of ankle angles and thus may be used to prevent potential injuries while lifting objects in workplaces.

A Promising Wearable Solution for the Practical and Accurate Monitoring of Low Back Loading in Manual Material Handling

(1) Background: Low back disorders are a leading cause of missed work and physical disability in manual material handling due to repetitive lumbar loading and overexertion. Ergonomic assessments are often performed to understand and mitigate the risk of musculoskeletal overexertion injuries. Wearable sensor solutions for monitoring low back loading have the potential to improve the quality, quantity, and efficiency of ergonomic assessments and to expand opportunities for the personalized, continuous monitoring of overexertion injury risk. However, existing wearable solutions using a single inertial measurement unit (IMU) are limited in how accurately they can estimate back loading when objects of varying mass are handled, and alternative solutions in the scientific literature require so many distributed sensors that they are impractical for widespread workplace implementation. We therefore explored new ways to accurately monitor low back loading using a small number of wearable sensors. (2) Methods: We synchronously collected data from laboratory instrumentation and wearable sensors to analyze 10 individuals each performing about 400 different material handling tasks. We explored dozens of candidate solutions that used IMUs on various body locations and/or pressure insoles. (3) Results: We found that the two key sensors for accurately monitoring low back loading are a trunk IMU and pressure insoles. Using signals from these two sensors together with a Gradient Boosted Decision Tree algorithm has the potential to provide a practical (relatively few sensors), accurate (up to r² = 0.89), and automated way (using wearables) to monitor time series lumbar moments across a broad range of material handling tasks. The trunk IMU could be replaced by thigh IMUs, or a pelvis IMU, without sacrificing much accuracy, but there was no practical substitute for the pressure insoles. The key to realizing accurate lumbar load estimates with this approach in the real world will be optimizing force estimates from pressure insoles. (4) Conclusions: Here, we present a promising wearable solution for the practical, automated, and accurate monitoring of low back loading during manual material handling.

Training Load and Injury: Causal Pathways and Future Directions

Causal pathways between training loads and the mechanisms of tissue damage and athletic injury are poorly understood. Here, the relation between specific training load measures and metrics, and causal pathways of gradual onset and traumatic injury are examined. Currently, a wide variety of internal and external training load measures and metrics exist, with many of these being commonly utilized to evaluate injury risk. These measures and metrics can conceptually be related to athletic injury through the mechanical load-response pathway, the psycho-physiological load-response pathway, or both. However, the contributions of these pathways to injury vary. Importantly, tissue fatigue damage and trauma through the mechanical load-response pathway is poorly understood. Furthermore, considerable challenges in quantifying this pathway exist within applied settings, evidenced by a notable absence of validation between current training load measures and tissue-level mechanical loads. Within this context, the accurate quantification of mechanical loads holds considerable importance for the estimation of tissue damage and the development of more thorough understandings of injury risk. Despite internal load measures of psycho-physiological load speculatively being conceptually linked to athletic injury through training intensity and the effects of psycho-physiological fatigue, these measures are likely too far removed from injury causation to provide meaningful, reliable relationships with injury. Finally, we used a common training load metric as a case study to show how the absence of a sound conceptual rationale and spurious links to causal mechanisms can disclose the weaknesses of candidate measures as tools for altering the likelihood of injuries, aiding the future development of more refined injury risk assessment methods.