Predicting Athlete Ground Reaction Forces and Moments From Spatio-Temporal Driven CNN Models

Markerless motion capture provides accurate predictions of ground reaction forces across a range of movement tasks

Measuring or estimating the forces acting on the human body during movement is critical for determining the biomechanical aspects relating to injury, disease and healthy ageing. In this study we examined whether quantifying whole-body motion (segmental accelerations) using a commercial markerless motion capture system could accurately predict three-dimensional ground reaction force during a diverse range of human movements: walking, running, jumping and cutting. We synchronously recorded 3D ground reaction forces (force instrumented treadmill or in-ground plates) with high-resolution video from eight cameras that were spatially calibrated relative to a common coordinate system. We used a commercially available software to reconstruct whole body motion, along with a geometric skeletal model to calculate the acceleration of each segment and hence the whole-body centre of mass and ground reaction force across each movement task. The average root mean square difference (RMSD) across all three dimensions and all tasks was 0.75 N/kg, with the maximum average RMSD being 1.85 N/kg for running vertical force (7.89 % of maximum). There was very strong agreement between peak forces across tasks, with R2 values indicating that the markerless prediction algorithm was able to predict approximately 95-99 % of the variance in peak force across all axes and movements. The results were comparable to previous reports using whole-body marker-based approaches and hence this provides strong proof-of-principle evidence that markerless motion capture can be used to predict ground reaction forces and therefore potentially assess movement kinetics with limited requirements for participant preparation.

Strategies to optimise machine learning classification performance when using biomechanical features

Building prediction models using biomechanical features is challenging because such models may require large sample sizes. However, collecting biomechanical data on large sample sizes is logistically very challenging. This study aims to investigate if modern machine learning algorithms can help overcome the issue of limited sample sizes on developing prediction models. This was a secondary data analysis two biomechanical datasets - a walking dataset on 2295 participants, and a countermovement jump dataset on 31 participants. The input features were the three-dimensional ground reaction forces (GRFs) of the lower limbs. The outcome was the orthopaedic disease category (healthy, calcaneus, ankle, knee, hip) in the walking dataset, and healthy vs people with patellofemoral pain syndrome in the jump dataset. Different algorithms were compared: multinomial/LASSO regression, XGBoost, various deep learning time-series algorithms with augmented data, and with transfer learning. For the outcome of weighted multiclass area under the receiver operating curve (AUC) in the walking dataset, the three models with the best performance were InceptionTime with x12 augmented data (0.810), XGBoost (0.804), and multinomial logistic regression (0.800). For the jump dataset, the top three models with the highest AUC were the LASSO (1.00), InceptionTime with x8 augmentation (0.750), and transfer learning (0.653). Machine-learning based strategies for managing the challenging issue of limited sample size for biomechanical ML-based problems, could benefit the development of alternative prediction models in healthcare, especially when time-series data are involved.

Prediction of knee biomechanics with different tibial component malrotations after total knee arthroplasty: conventional machine learning vs. deep learning

The precise alignment of tibiofemoral components in total knee arthroplasty is a crucial factor in enhancing the longevity and functionality of the knee. However, it is a substantial challenge to quickly predict the biomechanical response to malrotation of tibiofemoral components after total knee arthroplasty using musculoskeletal multibody dynamics models. The objective of the present study was to conduct a comparative analysis between a deep learning method and four conventional machine learning methods for predicting knee biomechanics with different tibial component malrotation during a walking gait after total knee arthroplasty. First, the knee contact forces and kinematics with different tibial component malrotation in the range of ±5° in the three directions of anterior/posterior slope, internal/external rotation, and varus/valgus rotation during a walking gait after total knee arthroplasty were calculated based on the developed musculoskeletal multibody dynamics model. Subsequently, deep learning and four conventional machine learning methods were developed using the above 343 sets of biomechanical data as the dataset. Finally, the results predicted by the deep learning method were compared to the results predicted by four conventional machine learning methods. The findings indicated that the deep learning method was more accurate than four conventional machine learning methods in predicting knee contact forces and kinematics with different tibial component malrotation during a walking gait after total knee arthroplasty. The deep learning method developed in this study enabled quickly determine the biomechanical response with different tibial component malrotation during a walking gait after total knee arthroplasty. The proposed method offered surgeons and surgical robots the ability to establish a calibration safety zone, which was essential for achieving precise alignment in both preoperative surgical planning and intraoperative robotic-assisted surgical navigation.

Predictions of thumb, hand, and arm muscle parameters derived using force measurements of varying complexity and neural networks

Subject-specific musculoskeletal models are a promising avenue for personalized healthcare. However, current methods for producing personalized models require dense, biomechanical datasets that include expensive and time-consuming physiological measurements. For personalized models to be clinically useful, we must be able to rapidly generate models from simple, easy to collect data. In this context, the objective of this paper is to evaluate if and how simple data, namely height/weight and pinch force data, can be used to achieve model personalization via machine learning. Using simulated lateral pinch force measurements from a synthetic population of 40,000 randomly generated subjects, we train neural networks to estimate four Hill-type muscle model parameters and bone density. We compare parameter estimates to the true parameters of 10,000 additional synthetic subjects. We also generate new personalized models using the parameter estimates and perform new lateral pinch simulations to compare predicted forces using these personalized models to those generated using a baseline model. We demonstrate that increasing force measurement complexity reduces the root-mean-square error in the majority of parameter estimates. Additionally, musculoskeletal models using neural network-based parameter estimates provide up to an 80% reduction in absolute error in simulated forces when compared to a generic model. Thus, easily obtained force measurements may be suitable for personalizing models of the thumb, although extending the method to more tasks and models involving other joints likely requires additional measurements.

Performance of multiple neural networks in predicting lower limb joint moments using wearable sensors

Joint moment measurements represent an objective biomechemical parameter in joint health assessment. Inverse dynamics based on 3D motion capture data is the current 'gold standard' to estimate joint moments. Recently, machine learning combined with data measured by wearable technologies such electromyography (EMG), inertial measurement units (IMU), and electrogoniometers (GON) has been used to enable fast, easy, and low-cost measurements of joint moments. This study investigates the ability of various deep neural networks to predict lower limb joint moments merely from IMU sensors. The performance of five different deep neural networks (InceptionTimePlus, eXplainable convolutional neural network (XCM), XCMplus, Recurrent neural network (RNNplus), and Time Series Transformer (TSTPlus)) were tested to predict hip, knee, ankle, and subtalar moments using acceleration and gyroscope measurements of four IMU sensors at the trunk, thigh, shank, and foot. Multiple locomotion modes were considered including level-ground walking, treadmill walking, stair ascent, stair descent, ramp ascent, and ramp descent. We show that XCM can accurately predict lower limb joint moments using data of only four IMUs with RMSE of 0.046 ± 0.013 Nm/kg compared to 0.064 ± 0.003 Nm/kg on average for the other architectures. We found that hip, knee, and ankle joint moments predictions had a comparable RMSE with an average of 0.069 Nm/kg, while subtalar joint moments had the lowest RMSE of 0.033 Nm/kg. The real-time feedback that can be derived from the proposed method can be highly valuable for sports scientists and physiotherapists to gain insights into biomechanics, technique, and form to develop personalized training and rehabilitation programs.

Smooth and accurate predictions of joint contact force time-series in gait using over parameterised deep neural networks

Alterations in joint contact forces (JCFs) are thought to be important mechanisms for the onset and progression of many musculoskeletal and orthopaedic pain disorders. Computational approaches to JCFs assessment represent the only non-invasive means of estimating in-vivo forces; but this cannot be undertaken in free-living environments. Here, we used deep neural networks to train models to predict JCFs, using only joint angles as predictors. Our neural network models were generally able to predict JCFs with errors within published minimal detectable change values. The errors ranged from the lowest value of 0.03 bodyweight (BW) (ankle medial-lateral JCF in walking) to a maximum of 0.65BW (knee VT JCF in running). Interestingly, we also found that over parametrised neural networks by training on longer epochs (>100) resulted in better and smoother waveform predictions. Our methods for predicting JCFs using only joint kinematics hold a lot of promise in allowing clinicians and coaches to continuously monitor tissue loading in free-living environments.

Predicting vertical ground reaction force in rearfoot running: A wavelet neural network model and factor loading

This study proposed a simple method for selecting input variables by factor loading and inputting these variables into a wavelet neural network (WNN) model to predict vertical ground reaction force (vGRF). The kinematic data and vGRF of 9 rearfoot strikers at 12, 14, and 16 km/h were collected using a motion capture system and an instrumented treadmill. The input variables were screened by factor loading and utilized to predict vGRF with the WNN. Nine kinematic variables were selected, corresponding to nine principal components, mainly focusing on the knee and ankle joints. The prediction results of vGRF were effective and accurate at different speeds, namely, the coefficient of multiple correlation (CMC) > 0.98 (0.984-0.988), the normalized root means square error (NRMSE) < 15% (9.34-11.51%). The NRMSEs of impact force (8.18-10.01%), active force (4.92-7.42%), and peak time (7.16-12.52%) were less than 15%. There was a small number (peak, 4.12-6.18%; time, 4.71-6.76%) exceeding the 95% confidence interval (CI) using the Bland-Altman method. The knee joint was the optimal location for estimating vGRF, followed by the ankle. There were high accuracy and agreement for predicting vGRF with the peak and peak time at 12, 14, and 16 km/h. Therefore, factor loading could be a valid method to screen kinematic variables in artificial neural networks.

Maintaining soldier musculoskeletal health using personalised digital humans, wearables and/or computer vision

OBJECTIVES

The physical demands of military service place soldiers at risk of musculoskeletal injuries and are major concerns for military capability. This paper outlines the development new training technologies to prevent and manage these injuries.

DESIGN

Narrative review.

METHODS

Technologies suitable for integration into next-generation training devices were examined. We considered the capability of technologies to target tissue level mechanics, provide appropriate real-time feedback, and their useability in-the-field.

RESULTS

Musculoskeletal tissues' health depends on their functional mechanical environment experienced in military activities, training and rehabilitation. These environments result from the interactions between tissue motion, loading, biology, and morphology. Maintaining health of and/or repairing joint tissues requires targeting the "ideal" in vivo tissue mechanics (i.e., loading and strain), which may be enabled by real-time biofeedback. Recent research has shown that these biofeedback technologies are possible by integrating a patient's personalised digital twin and wireless wearable devices. Personalised digital twins are personalised neuromusculoskeletal rigid body and finite element models that work in real-time by code optimisation and artificial intelligence. Model personalisation is crucial in obtaining physically and physiologically valid predictions.

CONCLUSIONS

Recent work has shown that laboratory-quality biomechanical measurements and modelling can be performed outside the laboratory with a small number of wearable sensors or computer vision methods. The next stage is to combine these technologies into well-designed easy to use products.

Developing AI enabled sensors and decision support for military operators in the field

Wearable sensors enable down range data collection of physiological and cognitive performance of the warfighter. However, autonomous teams may find the sensor data impractical to interpret and hence influence real-time decisions without the support of subject matter experts. Decision support tools can reduce the burden of interpreting physiological data in the field and incorporate a systems perspective where noisy field data can contain useful additional signals. We present a methodology of how artificial intelligence can be used for modeling human performance with decision-making to achieve actionable decision support. We provide a framework for systems design and advancing from the laboratory to real world environments. The result is a validated measure of down-range human performance with a low burden of operation.

Real-world measurements of ground reaction forces of normal gait of young adults wearing various footwear

For years, researchers have been recognizing patterns in gait for purposes of medical diagnostics, rehabilitation, and biometrics. A method for observing gait is to measure ground reaction forces (GRFs) between the foot and solid plate with tension sensors. The presented dataset consists of 13,702 measurements of bipedal GRFs of one step of normal gait of 324 students wearing shoes of various types. Each measurement includes raw digital signals of two force plates. A signal comprises stance-related samples but also preceding and following ones, in which one can observe noise, interferences, and artifacts caused by imperfections of devices and walkway. Such real-world time series can be used to study methods for detecting foot-strike and foot-off events, and for coping with artifacts. For user convenience, processed data are also available, which describe only the stance phase of gait and form ready-to-use patterns suitable for experiments in GRF-based recognition of persons and footwear, and for generating synthetic GRF waveforms. The dataset is accompanied by Matlab and Python programs for organizing and validating data.

Estimating Ground Reaction Forces from Two-Dimensional Pose Data: A Biomechanics-Based Comparison of AlphaPose, BlazePose, and OpenPose

The adoption of computer vision pose estimation approaches, used to identify keypoint locations which are intended to reflect the necessary anatomical landmarks relied upon by biomechanists for musculoskeletal modelling, has gained increasing traction in recent years. This uptake has been further accelerated by keypoint use as inputs into machine learning models used to estimate biomechanical parameters such as ground reaction forces (GRFs) in the absence of instrumentation required for direct measurement. This study first aimed to investigate the keypoint detection rate of three open-source pose estimation models (AlphaPose, BlazePose, and OpenPose) across varying movements, camera views, and trial lengths. Second, this study aimed to assess the suitability and interchangeability of keypoints detected by each pose estimation model when used as inputs into machine learning models for the estimation of GRFs. The keypoint detection rate of BlazePose was distinctly lower than that of AlphaPose and OpenPose. All pose estimation models achieved a high keypoint detection rate at the centre of an image frame and a lower detection rate in the true sagittal plane camera field of view, compared with slightly anteriorly or posteriorly located quasi-sagittal plane camera views. The three-dimensional ground reaction force, instantaneous loading rate, and peak force for running could be estimated using the keypoints of all three pose estimation models. However, only AlphaPose and OpenPose keypoints could be used interchangeably with a machine learning model trained to estimate GRFs based on AlphaPose keypoints resulting in a high estimation accuracy when OpenPose keypoints were used as inputs and vice versa. The findings of this study highlight the need for further evaluation of computer vision-based pose estimation models for application in biomechanical human modelling, and the limitations of machine learning-based GRF estimation models that rely on 2D keypoints. This is of particular relevance given that machine learning models informing athlete monitoring guidelines are being developed for application related to athlete well-being.

Synthesising 2D Video from 3D Motion Data for Machine Learning Applications

To increase the utility of legacy, gold-standard, three-dimensional (3D) motion capture datasets for computer vision-based machine learning applications, this study proposed and validated a method to synthesise two-dimensional (2D) video image frames from historic 3D motion data. We applied the video-based human pose estimation model OpenPose to real (in situ) and synthesised 2D videos and compared anatomical landmark keypoint outputs, with trivial observed differences (2.11−3.49 mm). We further demonstrated the utility of the method in a downstream machine learning use-case in which we trained and then tested the validity of an artificial neural network (ANN) to estimate ground reaction forces (GRFs) using synthesised and real 2D videos. Training an ANN to estimate GRFs using eight OpenPose keypoints derived from synthesised 2D videos resulted in accurate waveform GRF estimations (r > 0.9; nRMSE < 14%). When compared with using the smaller number of real videos only, accuracy was improved by adding the synthetic views and enlarging the dataset. The results highlight the utility of the developed approach to enlarge small 2D video datasets, or to create 2D video images to accompany 3D motion capture datasets to make them accessible for machine learning applications.

Motion-Based Ground Reaction Forces and Moments Prediction Method for Interaction with a Moving And/Or Non-Horizontal Structure

Inverse dynamics methods are commonly used for the biomechanical analysis of human motion. External forces applied on the subject are required as an input data to solve the dynamic equilibrium of the subject. Force platforms measure ground reactions forces and moments (GRF&Ms) but they limit the ecological aspect of experimental conditions. Motion-based GRF&Ms prediction may circumvent this limitation. The current study aims at evaluating the accuracy of an optimization-based GRF&Ms prediction method modified to be applied to the interaction with a moving and/or non horizontal structure. The main improvement of the method deals with the contact detection in such a moving and/or non horizontal frame. To evaluate the accuracy of the method, 20 subjects performed squats and steps on an instrumented moving structure, measuring both motion and GRF&Ms. The comparison of the root mean square error between the predicted and measured GFR&Ms divided by the subjects mass showed a similar order of magnitude than those from the method without the studied modification (0.14 N/kg for antero-posterior forces, 0.29 N/kg for medio lateral forces, 0.61 N/kg for longitudinal forces, 0.06 Nm/kg for frontal moments, 0.13 Nm/kg for sagittal moments, and 0.03 Nm/kg for transverse moments). The results showed the suitability of the method to study human motions for tasks performed on a moving and/or non-horizontal structure.

A Study of Athlete Pose Estimation Techniques in Sports Game Videos Combining Multiresidual Module Convolutional Neural Networks

In this paper, we propose a multiresidual module convolutional neural network-based method for athlete pose estimation in sports game videos. The network firstly designs an improved residual module based on the traditional residual module. Firstly, a large perceptual field residual module is designed to learn the correlation between the athlete components in the sports game video within a large perceptual field. A multiscale residual module is designed in the paper to better solve the inaccuracy of the pose estimation due to the problem of scale change of the athlete components in the sports game video. Secondly, these three residual modules are used as the building blocks of the convolutional neural network. When the resolution is high, the large perceptual field residual module and the multiscale residual module are used to capture information in a larger range as well as at each scale, and when the resolution is low, only the improved residual module is used. Finally, four multiresidual module convolutional neural networks are used to form the final multiresidual module stacked convolutional neural network. The neural network model proposed in this paper achieves high accuracy of 89.5% and 88.2% on the upper arm and lower arm, respectively, so the method in this paper reduces the influence of occlusion on the athlete's posture estimation to a certain extent. Through the experiments, it can be seen that the proposed multiresidual module stacked convolutional neural network-based method for athlete pose estimation in sports game videos further improves the accuracy of athlete pose estimation in sports game videos.

Comparing shallow, deep, and transfer learning in predicting joint moments in running

Joint moments are commonly calculated in biomechanics research and provide an indirect measure of muscular behaviors and joint loads. However, joint moments cannot be easily quantified clinically or in the field, primarily due to challenges measuring ground reaction forces outside the laboratory. The present study aimed to compare the accuracy of three different machine learning (ML) techniques - functional regression [ ML_fregress ], a deep neural network (DNN) built from scratch [ ML_DNN ], and transfer learning [ ML_TL ], in predicting joint moments during running. Data for this study came from an open-source dataset and two studies on running with and without external loads. Three-dimensional (3D) joint moments of the hip, knee, and ankle, were derived using inverse dynamics. 3D joint angle, velocity, and acceleration of the three joints served as predictors for each of the three ML techniques. Prediction performance was generally the best using ML_DNN, and the worse using ML_fregress. Absolute predictive performance was the best for sagittal plane moments, which ranged from a RMSE of 0.16 Nm/kg at the ankle using ML_DNN, to a RMSE of 0.49Nm/kg at the knee using ML_fregress. ML_DNN resulted in the greatest improvement in relative prediction performance (relRMSE) by 20% compared to ML_fregress for the ankle adduction-abduction moment. DNN with or without transfer learning was superior in predicting joint moments using kinematic inputs compared to functional regression. Synergizing ML with kinematic inputs has the potential to solve the constraints of obtaining high fidelity biomechanics data normally only possible during laboratory studies.

The future of in-field sports biomechanics: wearables plus modelling compute real-time in vivo tissue loading to prevent and repair musculoskeletal injuries

This paper explores the use of biomechanics in identifying the mechanistic causes of musculoskeletal tissue injury and degeneration. It appraises how biomechanics has been used to develop training programmes aiming to maintain or recover tissue health. Tissue health depends on the functional mechanical environment experienced by tissues during daily and rehabilitation activities. These environments are the result of the interactions between tissue motion, loading, biology, and morphology. Maintaining health of and/or repairing musculoskeletal tissues requires targeting the "ideal" in vivo tissue mechanics (i.e., loading and deformation), which may be enabled by appropriate real-time biofeedback. Recent research shows that biofeedback technologies may increase their quality and effectiveness by integrating a personalised neuromusculoskeletal modelling driven by real-time motion capture and medical imaging. Model personalisation is crucial in obtaining physically and physiologically valid predictions of tissue biomechanics. Model real-time execution is crucial and achieved by code optimisation and artificial intelligence methods. Furthermore, recent work has also shown that laboratory-based motion capture biomechanical measurements and modelling can be performed outside the laboratory with wearable sensors and artificial intelligence. The next stage is to combine these technologies into well-designed easy to use products to guide training to maintain or recover tissue health in the real-world.

A Comparison of Three Neural Network Approaches for Estimating Joint Angles and Moments from Inertial Measurement Units

The application of artificial intelligence techniques to wearable sensor data may facilitate accurate analysis outside of controlled laboratory settings—the holy grail for gait clinicians and sports scientists looking to bridge the lab to field divide. Using these techniques, parameters that are difficult to directly measure in-the-wild, may be predicted using surrogate lower resolution inputs. One example is the prediction of joint kinematics and kinetics based on inputs from inertial measurement unit (IMU) sensors. Despite increased research, there is a paucity of information examining the most suitable artificial neural network (ANN) for predicting gait kinematics and kinetics from IMUs. This paper compares the performance of three commonly employed ANNs used to predict gait kinematics and kinetics: multilayer perceptron (MLP); long short-term memory (LSTM); and convolutional neural networks (CNN). Overall high correlations between ground truth and predicted kinematic and kinetic data were found across all investigated ANNs. However, the optimal ANN should be based on the prediction task and the intended use-case application. For the prediction of joint angles, CNNs appear favourable, however these ANNs do not show an advantage over an MLP network for the prediction of joint moments. If real-time joint angle and joint moment prediction is desirable an LSTM network should be utilised.

Machine learning for rapid estimation of lower extremity muscle and joint loading during activities of daily living

Joint contact and muscle forces estimated with musculoskeletal modeling techniques offer useful metrics describing movement quality that benefit multiple research and clinical applications. The expensive processing of laboratory data associated with generating these outputs presents challenges to researchers and clinicians, including significant time and expertise requirements that limit the number of subjects typically evaluated. The objective of the current study was to develop and compare machine learning techniques for rapid, data-driven estimation of musculoskeletal metrics from derived gait lab data. OpenSim estimates of patient joint and muscle forces during activities of daily living were simulated using laboratory data from 70 total knee replacement patients and used to develop 4 different machine learning algorithms. Trained machine learning models predicted both trend and magnitude of estimated joint contact (mean correlation coefficients ranging from 0.93 to 0.94 during gait) and muscle forces (mean correlation coefficients ranging from 0.83 to 0.91 during gait) based on anthropometrics, ground reaction forces, and joint angle data. Patient mechanics were accurately predicted by recurrent neural networks, even after removing dependence on key subsets of predictor features. The ability to quickly estimate patient mechanics from derived measurements of movement has the potential to broaden the impact of musculoskeletal modeling by enabling faster assessment in both clinical and research settings.

Moving the Lab into the Mountains: A Pilot Study of Human Activity Recognition in Unstructured Environments

Goal: To develop and validate a field-based data collection and assessment method for human activity recognition in the mountains with variations in terrain and fatigue using a single accelerometer and a deep learning model. Methods: The protocol generated an unsupervised labelled dataset of various long-term field-based activities including run, walk, stand, lay and obstacle climb. Activity was voluntary so transitions could not be determined a priori. Terrain variations included slope, crossing rivers, obstacles and surfaces including road, gravel, clay, mud, long grass and rough track. Fatigue levels were modulated between rested to physical exhaustion. The dataset was used to train a deep learning convolutional neural network (CNN) capable of being deployed on battery powered devices. The human activity recognition results were compared to a lab-based dataset with 1,098,204 samples and six features, uniform smooth surfaces, non-fatigued supervised participants and activity labelling defined by the protocol. Results: The trail run dataset had 3,829,759 samples with five features. The repetitive activities and single instance activities required hyper parameter tuning to reach an overall accuracy 0.978 with a minimum class precision for the one-off activity (climbing gate) of 0.802. Conclusion: The experimental results showed that the CNN deep learning model performed well with terrain and fatigue variations compared to the lab equivalents (accuracy 97.8% vs. 97.7% for trail vs. lab). Significance: To the authors knowledge this study demonstrated the first successful human activity recognition (HAR) in a mountain environment. A robust and repeatable protocol was developed to generate a validated trail running dataset when there were no observers present and activity types changed on a voluntary basis across variations in terrain surface and both cognitive and physical fatigue levels.

Causal relationships between immediate pre-impact kinematics and post-impact kinetics during drop landing using a simple three dimensional multibody model

This study aimed to validate a simple dynamic model of single-leg drop-landing to develop a methodological foundation for investigating mechanistic causes of anterior cruciate ligament (ACL) injury and to explore mechanical associations between knee valgus torque and landing kinematics that are considered clinically as a high-risk landing posture for the injury. A triple-inverted-pendulum model in three-dimensional space, composed of rigid-links of head-arms-trunk (HAT), thigh and shank, was employed. We derived causal relationships that can predict post-impact kinetics, including impact ground reaction forces (GRFs) and corresponding knee joint torques from a given body-kinematics immediately before impact, based on an assumption of a completely inelastic collision between a landing foot (the distal end-point of the shank in the model) and the ground. The concordance correlation coefficient (CCC) analysis revealed that our model can achieve an acceptable agreement between experimentally measured and model-predicted impact GRFs and corresponding knee joint torques. The 95% one-tailed lower confidence limit of CCC of vertical, mediolateral GRFs and the varus/valgus torque were 0.665>ρ_c,a=0.643,0.786>ρ_c,a=0.758 and 0.531>ρ_c,a=0.508, respectively, for the least acceptable values ρ_c,a. Using this model, effects of three types of hypothetical pre-impact kinematics with modulated (i) medial/lateral leaning HAT angle, (ii) forward/backward HAT tilt-angle, and (iii) knee flexion/extension angle on the impact GRF and corresponding knee joint torque were evaluated. We showed that the smaller knee flexion and the greater HAT leaning toward the landing-limb-side, the larger the knee valgus torque is generated, as a mechanical consequence between the specific pre-impact kinematics and the knee loading associated with the risk of ACL injury. Further exploration of hypothetical kinematics using the model in the future work might contribute to identifying the risky landing kinematics beyond experimental limitations.

Towards the Monitoring of Functional Status in a Free-Living Environment for People with Hip or Knee Osteoarthritis: Design and Evaluation of the JOLO Blended Care App

(1) Background: Joint loading is an important parameter in patients with osteoarthritis (OA). However, calculating joint loading relies on the performance of an extensive biomechanical analysis, which is not possible to do in a free-living situation. We propose the concept and design of a novel blended-care app called JOLO (Joint Load) that combines free-living information on activity with lab-based measures of joint loading in order to estimate a subject’s functional status. (2) Method: We used an iterative design process to evaluate the usability of the JOLO app through questionnaires. The user interfaces that resulted from the iterations are described and provide a concept for feedback on functional status. (3) Results: In total, 44 people (20 people with OA and 24 health-care providers) participated in the testing of the JOLO app. OA patients rated the latest version of the JOLO app as moderately useful. Therapists were predominantly positive; however, their intention to use JOLO was low due to technological issues. (4) Conclusion: We can conclude that JOLO is promising, but further technological improvements concerning activity recognition, the development of personalized joint loading predictions and a more comfortable means to carry the device are needed to facilitate its integration as a blended-care program.

In Silico-Enhanced Treatment and Rehabilitation Planning for Patients with Musculoskeletal Disorders: Can Musculoskeletal Modelling and Dynamic Simulations Really Impact Current Clinical Practice?

Over the past decades, the use of computational physics-based models representative of the musculoskeletal (MSK) system has become increasingly popular in many fields of clinically driven research, locomotor rehabilitation in particular. These models have been applied to various functional impairments given their ability to estimate parameters which cannot be readily measured in vivo but are of interest to clinicians. The use of MSK modelling and simulations allows analysis of relevant MSK biomarkers such as muscle and joint contact loading at a number of different stages in the clinical treatment pathway in order to benefit patient functional outcome. Applications of these methods include optimisation of rehabilitation programs, patient stratification, disease characterisation, surgical pre-planning, and assistive device and exoskeleton design and optimisation. This review provides an overview of current approaches, the components of standard MSK models, applications, limitations, and assumptions of these modelling and simulation methods, and finally proposes a future direction.

Targeted Achilles Tendon Training and Rehabilitation Using Personalized and Real-Time Multiscale Models of the Neuromusculoskeletal System

Musculoskeletal tissues, including tendons, are sensitive to their mechanical environment, with both excessive and insufficient loading resulting in reduced tissue strength. Tendons appear to be particularly sensitive to mechanical strain magnitude, and there appears to be an optimal range of tendon strain that results in the greatest positive tendon adaptation. At present, there are no tools that allow localized tendon strain to be measured or estimated in training or a clinical environment. In this paper, we first review the current literature regarding Achilles tendon adaptation, providing an overview of the individual technologies that so far have been used in isolation to understand in vivo Achilles tendon mechanics, including 3D tendon imaging, motion capture, personalized neuromusculoskeletal rigid body models, and finite element models. We then describe how these technologies can be integrated in a novel framework to provide real-time feedback of localized Achilles tendon strain during dynamic motor tasks. In a proof of concept application, Achilles tendon localized strains were calculated in real-time for a single subject during walking, single leg hopping, and eccentric heel drop. Data was processed at 250 Hz and streamed on a smartphone for visualization. Achilles tendon peak localized strains ranged from ∼3 to ∼11% for walking, ∼5 to ∼15% during single leg hop, and ∼2 to ∼9% during single eccentric leg heel drop, overall showing large strain variation within the tendon. Our integrated framework connects, across size scales, knowledge from isolated tendons and whole-body biomechanics, and offers a new approach to Achilles tendon rehabilitation and training. A key feature is personalization of model components, such as tendon geometry, material properties, muscle geometry, muscle-tendon paths, moment arms, muscle activation, and movement patterns, all of which have the potential to affect tendon strain estimates. Model personalization is important because tendon strain can differ substantially between individuals performing the same exercise due to inter-individual differences in these model components.

Deep learning approach for prediction of impact peak appearance at ground reaction force signal of running activity

Protruding impact peak is one of the features of vertical ground reaction force (GRF) that is related to injury risk while running. The present research is dedicated to predicting GRF impact peak appearance by setting a binary classification problem. Kinematic data, namely a number of raw signals in the sagittal plane, collected by the Vicon motion capture system (Oxford Metrics Group, UK) were employed as predictors. Therefore, the input data for the predictive model are presented as a multi-channel time series. Deep learning techniques, namely five convolutional neural network (CNN) models were applied to the binary classification analysis, based on a Multi-Layer Perceptron (MLP) classifier, support vector machine (SVM), logistic regression, k-nearest neighbors (kNN), and random forest algorithms. SVM, logistic regression, and random forest classifiers demonstrated performances that do not statistically significantly differ. The best classification accuracy achieved is 81.09% ± 2.58%. Due to good performance of the models, this study serves as groundwork for further application of deep learning approaches to predicting kinetic information based on this kind of input data.

Adaptive predictive systems applied to gait analysis: A systematic review

BACKGROUND

Due to the high susceptivity of the walking pattern to be affected by several disorders, accurate analysis methods are necessary. Given the complexity and relevance of such assessment, the utilization of methods to facilitate it plays a significant role, provided that they do not compromise the outcomes.

RESEARCH QUESTIONS

This paper aimed at identifying the standards for the application of adaptive predictive systems to gait analysis, given the extensive research on this field. Furthermore, we also intended to check whether such methods can effectively support clinicians in determining the number of physiotherapy sessions necessary to recover gait-related dysfunctions.

METHODS

Through a screening process of scientific databases, we considered studies encompassed from 1968 to April 2019. Within these 50 years, we found 24 papers that met our inclusion criteria. They were analyzed according to their data acquisition and processing methods via ad hoc questionnaires. Additionally, we examined quantitatively the adaptive approaches.

RESULTS

Concerning data acquisition, the included papers presented a mean score of 6.1 SD 1.0, most of them applying optoelectronic systems, and the ground reaction force (GRF) was the most used parameter. The AI quality assessment showed an above-average rate of 7.8 SD 1.0, and artificial neural networks (ANN) being the paradigm most frequently utilized. Our systematic review identified only one study that addressed therapeutics including a predictive method.

SIGNIFICANCE

While much progress has been identified to predict assessment aspects, there is little effort to assist healthcare professionals in establishing the rehabilitation duration and prognostics. Therefore, future studies should focus on accomplishing the production of applications of predictive methods to therapeutics and prognosis, not lingering extremely on the analysis of gait features.

Estimation of Gait Mechanics Based on Simulated and Measured IMU Data Using an Artificial Neural Network

Enhancement of activity is one major topic related to the aging society. Therefore, it is necessary to understand people's motion and identify possible risk factors during activity. Technology can be used to monitor motion patterns during daily life. Especially the use of artificial intelligence combined with wearable sensors can simplify measurement systems and might at some point replace the standard motion capturing using optical measurement technologies. Therefore, this study aims to analyze the estimation of 3D joint angles and joint moments of the lower limbs based on IMU data using a feedforward neural network. The dataset summarizes optical motion capture data of former studies and additional newly collected IMU data. Based on the optical data, the acceleration and angular rate of inertial sensors was simulated. The data was augmented by simulating different sensor positions and orientations. In this study, gait analysis was undertaken with 30 participants using a conventional motion capture set-up based on an optoelectronic system and force plates in parallel with a custom IMU system consisting of five sensors. A mean correlation coefficient of 0.85 for the joint angles and 0.95 for the joint moments was achieved. The RMSE for the joint angle prediction was smaller than 4.8° and the nRMSE for the joint moment prediction was below 13.0%. Especially in the sagittal motion plane good results could be achieved. As the measured dataset is rather small, data was synthesized to complement the measured data. The enlargement of the dataset improved the prediction of the joint angles. While size did not affect the joint moment prediction, the addition of noise to the dataset resulted in an improved prediction accuracy. This indicates that research on appropriate augmentation techniques for biomechanical data is useful to further improve machine learning applications.

Establishing outcome measures in early knee osteoarthritis

The classification and monitoring of individuals with early knee osteoarthritis (OA) are important considerations for the design and evaluation of therapeutic interventions and require the identification of appropriate outcome measures. Potential outcome domains to assess for early OA include patient-reported outcomes (such as pain, function and quality of life), features of clinical examination (such as joint line tenderness and crepitus), objective measures of physical function, levels of physical activity, features of imaging modalities (such as of magnetic resonance imaging) and biochemical markers in body fluid. Patient characteristics such as adiposity and biomechanics of the knee could also have relevance to the assessment of early OA. Importantly, research is needed to enable the selection of outcome measures that are feasible, reliable and validated in individuals at risk of knee OA or with early knee OA. In this Perspectives article, potential outcome measures for early symptomatic knee OA are discussed, including those measures that could be of use in clinical practice and/or the research setting.