On-Field Performance of an Instrumented Mouthguard for Detecting Head Impacts in American Football

When to Pull the Trigger: Conceptual Considerations for Approximating Head Acceleration Events Using Instrumented Mouthguards

Head acceleration events (HAEs) are acceleration responses of the head following external short-duration collisions. The potential risk of brain injury from a single high-magnitude HAE or repeated occurrences makes them a significant concern in sport. Instrumented mouthguards (iMGs) can approximate HAEs. The distinction between sensor acceleration events, the iMG datum for approximating HAEs and HAEs themselves, which have been defined as the in vivo event, is made to highlight limitations of approximating HAEs using iMGs. This article explores the technical limitations of iMGs that constrain the approximation of HAEs and discusses important conceptual considerations for stakeholders interpreting iMG data. The approximation of HAEs by sensor acceleration events is constrained by false positives and false negatives. False positives occur when a sensor acceleration event is recorded despite no (in vivo) HAE occurring, while false negatives occur when a sensor acceleration event is not recorded after an (in vivo) HAE has occurred. Various mechanisms contribute to false positives and false negatives. Video verification and post-processing algorithms offer effective means for eradicating most false positives, but mitigation for false negatives is less comprehensive. Consequently, current iMG research is likely to underestimate HAE exposures, especially at lower magnitudes. Future research should aim to mitigate false negatives, while current iMG datasets should be interpreted with consideration for false negatives when inferring athlete HAE exposure.

Capturing Head Impacts in Boxing: A Video-Based Comparison of Three Wearable Sensors

Wearable sensors are used to quantify head impacts in athletes, but recent work has shown that the number of events recorded may not be accurate. This study aimed to compare the number of head acceleration events recorded by three wearable sensors during boxing and assess how impact type and location affect the triggering of acceleration events. Seven boxers were equipped with an instrumented mouthguard, a skin patch, and a headgear patch. Contacts to participants' heads were identified via three video cameras over 115 sparring rounds. The resulting 5168 video-identified events were used as reference to quantify the sensitivity, specificity, and positive predictive value (PPV) of the sensors. The mouthguard, skin patch, and headgear patch recorded 695, 1579, and 1690 events, respectively, yielding sensitivities of 35%, 86%, and 78%, respectively, and specificities of 90%, 76%, and 75%, respectively. The mouthguard, skin patch, and headgear patch yielded 693, 1571, and 1681 true-positive events, respectively, leading to PPVs for head impacts over 96%. All three sensors were more likely to be triggered by punches landing near the sensor and cleanly on the head, although the mouthguard's sensitivity to impact location varied less than the patches. While the use of head impact sensors for assessing injury risks remains uncertain, this study provides valuable insights into the capabilities and limitations of these sensors in capturing video-verified head impact events.

Identifying relevant diffusion MRI microstructure biomarkers relating to exposure to repeated head impacts in contact sport athletes

PURPOSE

Repeated head impacts (RHI) without concussion may cause long-term sequelae. A growing array of diffusion MRI metrics exist, both empiric and modeled and it is hard to know which are potentially important biomarkers. Common conventional statistical methods fail to consider interactions between metrics and rely on group-level comparisons. This study uses a classification pipeline as a means towards identifying important diffusion metrics associated with subconcussive RHI.

METHODS

36 collegiate contact sport athletes and 45 non-contact sport controls from FITBIR CARE were included. Regional/whole brain WM statistics were computed from 7 diffusion metrics. Wrapper-based feature selection was applied to 5 classifiers representing a range of learning capacities. Best 2 classifiers were interpreted to identify the most RHI-related diffusion metrics.

RESULTS

Mean diffusivity (MD) and mean kurtosis (MK) are found to be the most important metrics for discriminating between athletes with and without RHI exposure history. Regional features outperformed global statistics. Linear approaches outperformed non-linear approaches with good generalizability (test AUC 0.80-0.81).

CONCLUSION

Feature selection and classification identifies diffusion metrics that characterize subconcussive RHI. Linear classifiers yield the best performance and mean diffusion, tissue microstructure complexity, and radial extra-axonal compartment diffusion (MD, MK, De,⊥) are found to be the most influential metrics. This work provides proof of concept that applying such approach to small, multidimensional dataset can be successful given attention to optimizing learning capacity without overfitting and serves an example of methods that lead to better understanding of the myriad of diffusion metrics as they relate to injury and disease.

A sensor-enabled cloud-based computing platform for computational brain biomechanics

BACKGROUND AND OBJECTIVES

Driven by the risk of repetitive head trauma, sensors have been integrated into mouthguards to measure head impacts in contact sports and military activities. These wearable devices, referred to as "instrumented" or "smart" mouthguards are being actively developed by various research groups and organizations. These instrumented mouthguards provide an opportunity to further study and understand the brain biomechanics due to impact. In this study, we present a brain modeling service that can use information from these sensors to predict brain injury metrics in an automated fashion.

METHODS

We have built a brain modeling platform using several of Amazon's Web Services (AWS) to enable cloud computing and scalability. We use a custom-built cloud-based finite element modeling code to compute the physics-based nonlinear response of the intracranial brain tissue and provide a frontend web application and an application programming interface for groups working on head impact sensor technology to include simulated injury predictions into their research pipeline.

RESULTS

The platform results have been validated against experimental data available in literature for brain-skull relative displacements, brain strains and intracranial pressure. The parallel processing capability of the platform has also been tested and verified. We also studied the accuracy of the custom head surfaces generated by Avatar 3D.

CONCLUSION

We present a validated cloud-based computational brain modeling platform that uses sensor data as input for numerical brain models and outputs a quantitative description of brain tissue strains and injury metrics. The platform is expected to generate transparent, reproducible, and traceable brain computing results.

Sports mouthguard overview: Materials, fabrication techniques, existing standards, and future research needs

Sports mouthguards are proven devices that reduce both the probability of and damage to orofacial tissues. While commonly used, clinicians may be unaware of the different sports mouthguard materials, proposed fabrication techniques, design recommendations, and newer digital fabrication methods. An overview of existing sports mouthguard standards is presented. It identifies that identify that the present requirements, while historically chosen in good faith, appear to be arbitrarily selected and not from clinical evidence-based derived data. In addition, identified sports mouthguard heterogeneous testing and data acquisition methods distinguishes that little possibility is afforded for the correlation of results. Furthermore, updated evidence with concussion prevention and/or alleviation is presented with evidence provided by sports mouthguard imbedded technology. The need for continued research is stressed to provide evidence-based data for concussion alleviation/prevention, digital fabrication methods and materials, and clinically based information for the revision of existing standards.

Physiological and Biomechanical Monitoring in American Football Players: A Scoping Review

American football is the sport with the highest rates of concussion injuries. Biomedical engineering applications may support athletes in monitoring their injuries, evaluating the effectiveness of their equipment, and leading industrial research in this sport. This literature review aims to report on the applications of biomedical engineering research in American football, highlighting the main trends and gaps. The review followed the PRISMA guidelines and gathered a total of 1629 records from PubMed (n = 368), Web of Science (n = 665), and Scopus (n = 596). The records were analyzed, tabulated, and clustered in topics. In total, 112 studies were selected and divided by topic in the biomechanics of concussion (n = 55), biomechanics of footwear (n = 6), biomechanics of sport-related movements (n = 6), the aerodynamics of football and catch (n = 3), injury prediction (n = 8), heat monitoring of physiological parameters (n = 8), and monitoring of the training load (n = 25). The safety of players has fueled most of the research that has led to innovations in helmet and footwear design, as well as improvements in the understanding and prevention of injuries and heat monitoring. The other important motivator for research is the improvement of performance, which has led to the monitoring of training loads and catches, and studies on the aerodynamics of football. The main gaps found in the literature were regarding the monitoring of internal loads and the innovation of shoulder pads.

Development of a Head Acceleration Event Classification Algorithm for Female Rugby Union

Instrumented mouthguards have been used to detect head accelerations and record kinematic data in numerous sports. Each recording requires validation through time-consuming video verification. Classification algorithms have been posed to automatically categorise head acceleration events and spurious events. However, classification algorithms must be designed and/or validated for each combination of sport, sex and mouthguard system. This study provides the first algorithm to classify head acceleration data from exclusively female rugby union players. Mouthguards instrumented with kinematic sensors were given to 25 participants for six competitive rugby union matches in an inter-university league. Across all instrumented players, 214 impacts were recorded from 460 match-minutes. Matches were video recorded to enable retrospective labelling of genuine and spurious events. Four machine learning algorithms were trained on five matches to predict these labels, then tested on the sixth match. Of the four classifiers, the support vector machine achieved the best results, with area under the receiver operator curve (AUROC) and area under the precision recall curve (AUPRC) scores of 0.92 and 0.85 respectively, on the test data. These findings represent an important development for head impact telemetry in female sport, contributing to the safer participation and improving the reliability of head impact data collection within female contact sport.

Performance of Oral Cavity Sensors: A Systematic Review

Technological advancements are enabling new applications within biomedical engineering. As a connection point between the outer environment and the human system, the oral cavity offers unique opportunities for sensing technologies. This paper systematically reviews the performance of measurement systems tested in the human oral cavity. Performance was defined by metrics related to accuracy and agreement estimation. A comprehensive search identifying human studies that reported on the accuracy or agreement of intraoral sensors found 85 research papers. Most of the literature (62%) was in dentistry, followed by neurology (21%), and physical medicine and rehabilitation (12%). The remaining papers were on internal medicine, obstetrics, and aerospace medicine. Most of the studies applied force or pressure sensors (32%), while optical and image sensors were applied most widely across fields. The main challenges for future adoption include the lack of large human trials, the maturity of emerging technologies (e.g., biochemical sensors), and the absence of standardization of evaluation in specific fields. New research should aim to employ robust performance metrics to evaluate their systems and incorporate real-world evidence as part of the evaluation process. Oral cavity sensors offer the potential for applications in healthcare and wellbeing, but for many technologies, more research is needed.

A neural network for the detection of soccer headers from wearable sensor data

To investigate the proposed association between soccer heading and deleterious brain changes, an accurate quantification of heading exposure is crucial. While wearable sensors constitute a popular means for this task, available systems typically overestimate the number of headers by poorly discriminating true impacts from spurious recordings. This study investigated the utility of a neural network for automatically detecting soccer headers from kinematic time series data obtained by wearable sensors. During 26 matches, 27 female soccer players wore head impacts sensors to register on-field impact events (> 8 g), which were labelled as valid headers (VH) or non-headers (NH) upon video review. Of these ground truth data, subsets of 49% and 21% each were used to train and validate a Long Short-Term Memory (LSTM) neural network in order to classify sensor recordings as either VH or NH based on their characteristic linear acceleration features. When tested on a balanced dataset comprising 271 VHs and NHs (which corresponds to 30% and 1.4% of ground truth VHs and NHs, respectively), the network showed very good overall classification performance by reaching scores of more than 90% across all metrics. When testing was performed on an unbalanced dataset comprising 271 VHs and 5743 NHs (i.e., 30% of ground truth VHs and NHs, respectively), as typically obtained in real-life settings, the model still achieved over 90% sensitivity and specificity, but only 42% precision, which would result in an overestimation of soccer players' true heading exposure. Although classification performance suffered from the considerable class imbalance between actual headers and non-headers, this study demonstrates the general ability of a data-driven deep learning network to automatically classify soccer headers based on their linear acceleration profiles.

Finding the Spatial Co-Variation of Brain Deformation With Principal Component Analysis

OBJECTIVE

Strain and strain rate are effective traumatic brain injury metrics. In finite element (FE) head model, thousands of elements were used to represent the spatial distribution of these metrics. Owing that these metrics are resulted from brain inertia, their spatial distribution can be represented in more concise pattern. Since head kinematic features and brain deformation vary largely across head impact types (Zhan et al., 2021), we applied principal component analysis (PCA) to find the spatial co-variation of injury metrics (maximum principal strain (MPS), MPS rate (MPSR) and MPS × MPSR) in four impact types: simulation, football, mixed martial arts and car crashes, and used the PCA to find patterns in these metrics and improve the machine learning head model (MLHM).

METHODS

We applied PCA to decompose the injury metrics for all impacts in each impact type, and investigate the spatial co-variation using the first principal component (PC1). Furthermore, we developed a MLHM to predict PC1 and then inverse-transform to predict for all brain elements. The accuracy, the model complexity and the size of training dataset of PCA-MLHM are compared with previous MLHM (Zhan et al., 2021).

RESULTS

PC1 explained variance on the datasets. Based on PC1 coefficients, the corpus callosum and midbrain exhibit high variance on all datasets. Finally, the PCA-MLHM reduced model parameters by 74% with a similar MPS estimation accuracy.

CONCLUSION

The brain injury metric in a dataset can be decomposed into mean components and PC1 with high explained variance.

SIGNIFICANCE

The spatial co-variation analysis enables better interpretation of the patterns in brain injury metrics. It also improves the efficiency of MLHM.

Concussion Prone Scenarios: A Multi-Dimensional Exploration in Impact Directions, Brain Morphology, and Network Architectures Using Computational Models

While individual susceptibility to traumatic brain injury (TBI) has been speculated, past work does not provide an analysis considering how physical features of an individual's brain (e.g., brain size, shape), impact direction, and brain network features can holistically contribute to the risk of suffering a TBI from an impact. This work investigated each of these features simultaneously using computational modeling and analyses of simulated functional connectivity. Unlike the past studies that assess the severity of TBI based on the quantification of brain tissue damage (e.g., principal strain), we approached the brain as a complex network in which neuronal oscillations orchestrate to produce normal brain function (estimated by functional connectivity) and, to this end, both the anatomical damage location and its topological characteristics within the brain network contribute to the severity of brain function disruption and injury. To represent the variations in the population, we analyzed a publicly available database of brain imaging data and selected five distinct network architectures, seven different brain sizes, and three uniaxial head rotational conditions to study the consequences of 74 virtual impact scenarios. Results show impact direction produces the most significant change in connections across brain areas (structural connectome) and the functional coupling of activity across these brain areas (functional connectivity). Axial rotations were more injurious than those with sagittal and coronal rotations when the head kinematics were the same for each condition. When the impact direction was held constant, brain network architecture showed a significantly different vulnerability across axial and sagittal, but not coronal rotations. As expected, brain size significantly affected the expected change in structural and functional connectivity after impact. Together, these results provided groupings of predicted vulnerability to impact-a subgroup of male brain architectures exposed to axial impacts were most vulnerable, while a subgroup of female brain architectures was the most tolerant to the sagittal impacts studied. These findings lay essential groundwork for subject-specific analyses of concussion and provide invaluable guidance for designing personalized protection equipment.

On-Field Deployment and Validation for Wearable Devices

Wearable sensors are an important tool in the study of head acceleration events and head impact injuries in sporting and military activities. Recent advances in sensor technology have improved our understanding of head kinematics during on-field activities; however, proper utilization and interpretation of data from wearable devices requires careful implementation of best practices. The objective of this paper is to summarize minimum requirements and best practices for on-field deployment of wearable devices for the measurement of head acceleration events in vivo to ensure data evaluated are representative of real events and limitations are accurately defined. Best practices covered in this document include the definition of a verified head acceleration event, data windowing, video verification, advanced post-processing techniques, and on-field logistics, as determined through review of the literature and expert opinion. Careful use of best practices, with accurate acknowledgement of limitations, will allow research teams to ensure data evaluated is representative of real events, will improve the robustness of head acceleration event exposure studies, and generally improve the quality and validity of research into head impact injuries.

Ready for impact? A validity and feasibility study of instrumented mouthguards (iMGs)

OBJECTIVES

Assess the validity and feasibility of current instrumented mouthguards (iMGs) and associated systems.

METHODS

Phase I; four iMG systems (Biocore-Football Research Inc (FRI), HitIQ, ORB, Prevent) were compared against dummy headform laboratory criterion standards (25, 50, 75, 100 g). Phase II; four iMG systems were evaluated for on-field validity of iMG-triggered events against video-verification to determine true-positives, false-positives and false-negatives (20±9 player matches per iMG). Phase III; four iMG systems were evaluated by 18 rugby players, for perceptions of fit, comfort and function. Phase IV; three iMG systems (Biocore-FRI, HitIQ, Prevent) were evaluated for practical feasibility (System Usability Scale (SUS)) by four practitioners.

RESULTS

Phase I; total concordance correlation coefficients were 0.986, 0.965, 0.525 and 0.984 for Biocore-FRI, HitIQ, ORB and Prevent. Phase II; different on-field kinematics were observed between iMGs. Positive predictive values were 0.98, 0.90, 0.53 and 0.94 for Biocore-FRI, HitIQ, ORB and Prevent. Sensitivity values were 0.51, 0.40, 0.71 and 0.75 for Biocore-FRI, HitIQ, ORB and Prevent. Phase III; player perceptions of fit, comfort and function were 77%, 6/10, 55% for Biocore-FRI, 88%, 8/10, 61% for HitIQ, 65%, 5/10, 43% for ORB and 85%, 8/10, 67% for Prevent. Phase IV; SUS (preparation-management) was 51.3-50.6/100, 71.3-78.8/100 and 83.8-80.0/100 for Biocore-FRI, HitIQ and Prevent.

CONCLUSION

This study shows differences between current iMG systems exist. Sporting organisations can use these findings when evaluating which iMG system is most appropriate to monitor head acceleration events in athletes, supporting player welfare initiatives related to concussion and head acceleration exposure.

Automatic Detection Algorithm of Football Events in Videos

The purpose is to effectively solve the problems of high time cost, low detection accuracy, and difficult standard training samples in video processing. Based on previous investigations, football game videos are taken as research objects, and their shots are segmented to extract the keyframes. The football game videos are divided into different semantic shots using the semantic annotation method. The key events and data in the football videos are analyzed and processed using a combination of artificial rules and a genetic algorithm. Finally, the performance of the proposed model is evaluated and analyzed by using concrete example videos as data sets. Results demonstrate that adding simple artificial rules based on the classic semantic annotation algorithms can save a lot of time and costs while ensuring accuracy. The target events can be extracted and located initially using a unique lens. The model constructed by the genetic algorithm can provide higher accuracy when the training samples are insufficient. The recall and precision of events using the text detection method can reach 96.62% and 98.81%, respectively. Therefore, the proposed model has high video recognition accuracy, which can provide certain research ideas and practical experience for extracting and processing affective information in subsequent videos.

Deep learning methodology for predicting time history of head angular kinematics from simulated crash videos

Head kinematics information is important as it is used to measure brain injury risk. Currently, head kinematics are measured using wearable devices or instrumentation mounted on the head. This paper evaluates the deep learning approach in predicting time history of head angular kinematics directly from videos without any instrumentation. To prove the concept, a deep learning model was developed for predicting time history of head angular velocities using finite element (FE) based crash simulation videos. This FE dataset was split into training, validation, and test datasets. A combined convolutional neural network and recurrent neural network based deep learning model was developed using the training and validations sets. The test (unseen) dataset was used to evaluate the predictive capability of the deep learning model. On the test dataset, correlation coefficient obtained between the actual and predicted peak angular velocities was 0.73, 0.85, and 0.92 for X, Y, and Z components respectively.

Safeguarding Athletes Against Head Injuries Through Advances in Technology: A Scoping Review of the Uses of Machine Learning in the Management of Sports-Related Concussion

Sports injury prevention is an important part of the athlete welfare and safeguarding research field. In sports injury prevention, sport-related concussion (SRC) has proved to be one of the most difficult and complex injuries to manage in terms of prevention, diagnosis, classification, treatment and rehabilitation. SRC can cause long-term health issues and is a commonly reported injury in both adult and youth athletes around the world. Despite increased knowledge of the prevalence of SRC, very few tools are available for diagnosing SRC in athletic settings. Recent technological innovations have resulted in different machine learning and deep learning methodologies being tested to improve the management of this complex sports injury. The purpose of this article is to summarize and map the existing research literature on the use of machine learning in the management of SRC, ascertain where there are gaps in the existing research and identify recommendations for future research. This is explored through a scoping review. A systematic search in the three electronic databases SPORTDiscus, PubMed and Scopus identified an initial 522 studies, of which 24 were included in the final review, the majority of which focused on machine learning for the prediction and prevention of SRC (N = 10), or machine learning for the diagnosis and classification of SRC (N = 11). Only 3 studies explored machine learning approaches for the treatment and rehabilitation of SRC. A main finding is that current research highlights promising practical uses (e.g., more accurate and rapid injury assessment or return-to-sport participation criteria) of machine learning in the management of SRC. The review also revealed a narrow research focus in the existing literature. As current research is primarily conducted on male adolescents or adults from team sports in North America there is an urgent need to include wider demographics in more diverse samples and sports contexts in the machine learning algorithms. If research datasets continue to be based on narrow samples of athletes, the development of any new diagnostic and predictive tools for SRC emerging from this research will be at risk. Today, these risks appear to mainly affect the health and safety of female athletes.

Physics-Informed Machine Learning Improves Detection of Head Impacts

In this work we present a new physics-informed machine learning model that can be used to analyze kinematic data from an instrumented mouthguard and detect impacts to the head. Monitoring player impacts is vitally important to understanding and protecting from injuries like concussion. Typically, to analyze this data, a combination of video analysis and sensor data is used to ascertain the recorded events are true impacts and not false positives. In fact, due to the nature of using wearable devices in sports, false positives vastly outnumber the true positives. Yet, manual video analysis is time-consuming. This imbalance leads traditional machine learning approaches to exhibit poor performance in both detecting true positives and preventing false negatives. Here, we show that by simulating head impacts numerically using a standard Finite Element head-neck model, a large dataset of synthetic impacts can be created to augment the gathered, verified, impact data from mouthguards. This combined physics-informed machine learning impact detector reported improved performance on test datasets compared to traditional impact detectors with negative predictive value and positive predictive values of 88 and 87% respectively. Consequently, this model reported the best results to date for an impact detection algorithm for American football, achieving an F₁ score of 0.95. In addition, this physics-informed machine learning impact detector was able to accurately detect true and false impacts from a test dataset at a rate of 90% and 100% relative to a purely manual video analysis workflow. Saving over 12 h of manual video analysis for a modest dataset, at an overall accuracy of 92%, these results indicate that this model could be used in place of, or alongside, traditional video analysis to allow for larger scale and more efficient impact detection in sports such as American Football.

Head Impact Exposure and Biomechanics in University Varsity Women's Soccer

Soccer is a unique sport where players purposefully and voluntarily use their unprotected heads to manipulate the direction of the ball. There are limited soccer head impact exposure data to further study brain injury risks. The objective of the current study was to combine validated mouthpiece sensors with comprehensive video analysis methods to characterize head impact exposure and biomechanics in university varsity women’s soccer. Thirteen female soccer athletes were instrumented with mouthpiece sensors to record on-field head impacts during practices, scrimmages, and games. Multi-angle video was obtained and reviewed for all on-field activity to verify mouthpiece impacts and identify contact scenarios. We recorded 1307 video-identified intentional heading impacts and 1011 video-verified sensor impacts. On average, athletes experienced 1.83 impacts per athlete-exposure, with higher exposure in practices than games/scrimmages. Median and 95th percentile peak linear and peak angular accelerations were 10.0, 22.2 g, and 765, 2296 rad/s², respectively. Long kicks, top of the head impacts and jumping headers resulted in the highest impact kinematics. Our results demonstrate the importance of investigating and monitoring head impact exposure during soccer practices, as well as the opportunity to limit high-kinematics impact exposure through heading technique training and reducing certain contact scenarios.

Development of a Machine-Learning-Based Classifier for the Identification of Head and Body Impacts in Elite Level Australian Rules Football Players

Background: Exposure to thousands of head and body impacts during a career in contact and collision sports may contribute to current or later life issues related to brain health. Wearable technology enables the measurement of impact exposure. The validation of impact detection is required for accurate exposure monitoring. In this study, we present a method of automatic identification (classification) of head and body impacts using an instrumented mouthguard, video-verified impacts, and machine-learning algorithms.

Methods: Time series data were collected via the Nexus A9 mouthguard from 60 elite level men (mean age = 26.33; SD = 3.79) and four women (mean age = 25.50; SD = 5.91) from the Australian Rules Football players from eight clubs, participating in 119 games during the 2020 season. Ground truth data labeling on the captures used in this machine learning study was performed through the analysis of game footage by two expert video reviewers using SportCode and Catapult Vision. The visual labeling process occurred independently of the mouthguard time series data. True positive captures (captures where the reviewer directly observed contact between the mouthguard wearer and another player, the ball, or the ground) were defined as hits. Spectral and convolutional kernel based features were extracted from time series data. Performances of untuned classification algorithms from scikit-learn in addition to XGBoost were assessed to select the best performing baseline method for tuning.

Results: Based on performance, XGBoost was selected as the classifier algorithm for tuning. A total of 13,712 video verified captures were collected and used to train and validate the classifier. True positive detection ranged from 94.67% in the Test set to 100% in the hold out set. True negatives ranged from 95.65 to 96.83% in the test and rest sets, respectively.

Discussion and conclusion: This study suggests the potential for high performing impact classification models to be used for Australian Rules Football and highlights the importance of frequencies <150 Hz for the identification of these impacts.

Head Impact Sensor Triggering Bias Introduced by Linear Acceleration Thresholding

Contact sports players frequently sustain head impacts, most of which are mild impacts exhibiting 10-30 g peak head center-of-gravity (CG) linear acceleration. Wearable head impact sensors are commonly used to measure exposure and typically detect impacts using a linear acceleration threshold. However, linear acceleration across the head can substantially vary during 6-degree-of-freedom motion, leading to triggering biases that depend on sensor location and impact condition. We conducted an analytical investigation with impact characteristics extracted from on-field American football and soccer data. We assumed typical mouthguard sensor locations and evaluated whether simulated multi-directional impacts would trigger recording based on per-axis or resultant acceleration thresholding. Across 1387 impact directions, a 10g peak CG linear acceleration impact would trigger at only 24.7% and 31.8% of directions based on a 10 g per-axis and resultant acceleration threshold, respectively. Anterior impact locations had lower trigger rates and even a 30 g impact would not trigger recording in some directions. Such triggering biases also varied by sensor location and linear-rotational head kinematics coupling. Our results show that linear acceleration-based impact triggering could lead to considerable bias in head impact exposure measurements. We propose a set of recommendations to consider for sensor manufacturers and researchers to mitigate this potential exposure measurement bias.

Identifying Factors Associated with Head Impact Kinematics and Brain Strain in High School American Football via Instrumented Mouthguards

Repeated head impact exposure and concussions are common in American football. Identifying the factors associated with high magnitude impacts aids in informing sport policy changes, improvements to protective equipment, and better understanding of the brain's response to mechanical loading. Recently, the Stanford Instrumented Mouthguard (MiG2.0) has seen several improvements in its accuracy in measuring head kinematics and its ability to correctly differentiate between true head impact events and false positives. Using this device, the present study sought to identify factors (e.g., player position, helmet model, direction of head acceleration, etc.) that are associated with head impact kinematics and brain strain in high school American football athletes. 116 athletes were monitored over a total of 888 athlete exposures. 602 total impacts were captured and verified by the MiG2.0's validated impact detection algorithm. Peak values of linear acceleration, angular velocity, and angular acceleration were obtained from the mouthguard kinematics. The kinematics were also entered into a previously developed finite element model of the human brain to compute the 95th percentile maximum principal strain. Overall, impacts were (mean ± SD) 34.0 ± 24.3 g for peak linear acceleration, 22.2 ± 15.4 rad/s for peak angular velocity, 2979.4 ± 3030.4 rad/s² for peak angular acceleration, and 0.262 ± 0.241 for 95th percentile maximum principal strain. Statistical analyses revealed that impacts resulting in Forward head accelerations had higher magnitudes of peak kinematics and brain strain than Lateral or Rearward impacts and that athletes in skill positions sustained impacts of greater magnitude than athletes in line positions. 95th percentile maximum principal strain was significantly lower in the observed cohort of high school football athletes than previous reports of collegiate football athletes. No differences in impact magnitude were observed in athletes with or without previous concussion history, in athletes wearing different helmet models, or in junior varsity or varsity athletes. This study presents novel information on head acceleration events and their resulting brain strain in high school American football from our advanced, validated method of measuring head kinematics via instrumented mouthguard technology.

Time Window of Head Impact Kinematics Measurement for Calculation of Brain Strain and Strain Rate in American Football

Wearable devices have been shown to effectively measure the head's movement during impacts in sports like American football. When a head impact occurs, the device is triggered to collect and save the kinematic measurements during a predefined time window. Then, based on the collected kinematics, finite element (FE) head models can calculate brain strain and strain rate, which are used to evaluate the risk of mild traumatic brain injury. To find a time window that can provide a sufficient duration of kinematics for FE analysis, we investigated 118 on-field video-confirmed football head impacts collected by the Stanford Instrumented Mouthguard. The simulation results based on the kinematics truncated to a shorter time window were compared with the original to determine the minimum time window needed for football. Because the individual differences in brain geometry influence these calculations, we included six representative brain geometries and found that larger brains need a longer time window of kinematics for accurate calculation. Among the different sizes of brains, a pre-trigger time of 40 ms and a post-trigger time of 70 ms were found to yield calculations of brain strain and strain rate that were not significantly different from calculations using the original 200 ms time window recorded by the mouthguard. Therefore, approximately 110 ms is recommended for complete modeling of impacts for football.

An Experimental Platform Generating Simulated Blunt Impacts to the Head Due to Rearward Falls

Impacts to the back of the head due to rearward falls, also referred to as "backfall" events, represent a common source of TBI for athletes and soldiers. A new experimental apparatus is described for replicating the linear and rotational kinematics of the head during backfall events. An anthropomorphic test device (ATD) with a head-borne sensor suite was configured to fall backwards from a standing height, inducing contact between the rear of the head and a ground surface simulant. A pivoting swing arm and release strap were used to generate consistent and realistic head kinematics. Backfall experiments were performed with the ATD fitted with an American football helmet and the resulting linear and rotational head kinematics, as well as calculated injury metrics, compared favorably with those of football players undergoing similar impacts during games or play reconstructions. This test method complements existing blunt impact helmet performance experiments, such as drop tower and pneumatic ram test methods, which may not be able to fully reproduce head-neck-torso kinematics during a backfall event.

Rapid Estimation of Entire Brain Strain Using Deep Learning Models

OBJECTIVE

Many recent studies have suggested that brain deformation resulting from a head impact is linked to the corresponding clinical outcome, such as mild traumatic brain injury (mTBI). Even though several finite element (FE) head models have been developed and validated to calculate brain deformation based on impact kinematics, the clinical application of these FE head models is limited due to the time-consuming nature of FE simulations. This work aims to accelerate the process of brain deformation calculation and thus improve the potential for clinical applications.

METHODS

We propose a deep learning head model with a five-layer deep neural network and feature engineering, and trained and tested the model on 2511 total head impacts from a combination of head model simulations and on-field college football and mixed martial arts impacts.

RESULTS

The proposed deep learning head model can calculate the maximum principal strain (Green Lagrange) for every element in the entire brain in less than 0.001s with an average root mean squared error of 0.022, and with a standard deviation of 0.001 over twenty repeats with random data partition and model initialization.

CONCLUSION

Trained and tested using the dataset of 2511 head impacts, this model can be applied to various sports in the calculation of brain strain with accuracy, and its applicability can even further be extended by incorporating data from other types of head impacts.

SIGNIFICANCE

In addition to the potential clinical application in real-time brain deformation monitoring, this model will help researchers estimate the brain strain from a large number of head impacts more efficiently than using FE models.