Personalized machine learning approach to injury monitoring in elite volleyball players

Non-contact lower limb injuries in Rugby Union: A two-year pattern recognition analysis of injury risk factors

The cause of sport injuries are multifactorial and necessitate sophisticated statistical approaches for accurate identification of risk factors predisposing athletes to injury. Pattern recognition analyses have been adopted across sporting disciplines due to their ability to account for repeated measures and non-linear interactions of datasets, however there are limited examples of their use in injury risk prediction. This study incorporated two-years of rigorous monitoring of athletes with 1740 individual weekly data points across domains of training load, performance testing, musculoskeletal screening, and injury history parameters, to be one of the first to employ a pattern recognition approach to predict the risk factors of specific non-contact lower limb injuries in Rugby Union. Predictive models (injured vs. non-injured) were generated for non-contact lower limb, non-contact ankle, and severe non-contact injuries using Bayesian pattern recognition from a pool of 36 Senior Academy Rugby Union athletes. Predictors for non-contact lower limb injuries included dorsiflexion angle, adductor strength, and previous injury history (area under the receiver operating characteristic (ROC) = 0.70) Dorsiflexion angle parameters were also predictive of non-contact ankle injuries, along with slower sprint times, greater body mass, previous concussion, and previous ankle injury (ROC = 0.76). Predictors of severe non-contact lower limb injuries included greater differences in mean training load, slower sprint times, reduced hamstring and adductor strength, reduced dorsiflexion angle, greater perceived muscle soreness, and playing as a forward (ROC = 0.72). The identification of specific injury risk factors and useable thresholds for non-contact injury risk detection in sport holds great potential for coaches and medical staff to modify training prescriptions and inform injury prevention strategies, ultimately increasing player availability, a key indicator of team success.

A New Training Load Quantification Method at Supramaximal Intensity and Its Application in Injuries Among Members of an International Volleyball Team

ABSTRACT

Bouzigues, T, Maurelli, O, Imbach, F, Prioux, J, and Candau, R. A new training load quantification method at supramaximal intensity and its application in injuries among members of an international volleyball team. J Strength Cond Res 38(8): 1453-1463, 2024-The quantification of training loads (TLs) is essential for optimizing jump performance and reducing the occurrence of injuries. This study aimed to (a) propose a new method for quantifying TLs in explosive exercises, (b) determine the nature of the relationship between TLs dynamics and injury occurrence, and (c) assess a TL critical for training schedule purposes, above which the risk of injury occurrence becomes unacceptable. This study was conducted with 11 male volleyball players on a national team during a 5-month international competitive period. The proposed new method for quantifying TLs is based on a weighting factor applied to relative jumping intensities, determined by the number of sustainable jumps and their intensities measured by G-Vert accelerometer. The relationship between TLs dynamics and injury occurrence was assessed using a variable dose-response model. A high coefficient of determination was found between the maximum number of jumps possible and their intensities ( r2 = 0.94 ± 0.14, p < 0.001), indicating a strong physiological relationship between jumping intensities and the constraints imposed. The occurrence of injury was dependent on TLs dynamics for 2 players ( r2 = 0.26 ± 0.01; p < 0.001). The TL critical corresponded to 11 jumps over 80% of maximum jump height during games and approximately 130 jumps at <80% of maximal jump height. The present study proposes a new approach for quantifying supramaximal exercises and provides tools for training schedules and the prevention of volleyball injuries.

Health problems among elite Dutch youth long track speed skaters: a one-season prospective study

OBJECTIVES

To describe the frequency, type, and severity of health problems in long-track speed skating to inform injury prevention strategies.

METHODS

We prospectively collected weekly health and sport exposure data on 84 highly trained Dutch athletes aged 15-21 years during the 2019/2020 season using the Oslo Sports Trauma Research Centre questionnaire on Health Problems and the trainers' documentation. We categorised health problems into acute or repetitive mechanisms of injury or illness and calculated incidences (per 1000 sports exposure hours), weekly prevalence and burden (days of time loss per 1000 sports exposure hours) related to the affected body region.

RESULTS

We registered 283 health problems (187 injuries, 96 illnesses), yielding an average weekly prevalence of health problems of 30.5% (95% CI 28.7% to 32.2%). Incidence rates were 2.0/1000 hours for acute mechanism injuries (95% CI 1.5 to 2.5) and 3.2/1000 hours for illnesses (95% CI 2.6 to 3.9). For acute mechanism injuries the head, shoulder and lumbosacral region had the highest injury burden of 5.6 (95% CI 4.8 to 6.5), 2.9 (95% CI 2.3 to 3.5) and 2.2 (95% CI 1.7 to 2.8) days of time loss/1000 hours, respectively. For repetitive mechanism injuries, the knee, thoracic spine, lower leg and lumbosacral region had the highest injury burden, with 11.0 (95% CI 9.8 to 12.2), 6.8 (95% CI 5.9 to 7.7), 3.9 (95% CI 3.2 to 4.6) and 2.5 (95% CI 1.9 to 3.1) days of time loss/1000 hours, respectively.

CONCLUSION

Our study demonstrated a high prevalence of acute and repetitive mechanism injuries in speed skating. These results can guide future research and priorities for injury prevention.

Real-time sports injury monitoring system based on the deep learning algorithm

In response to the low real-time performance and accuracy of traditional sports injury monitoring, this article conducts research on a real-time injury monitoring system using the SVM model as an example. Video detection is performed to capture human movements, followed by human joint detection. Polynomial fitting analysis is used to extract joint motion patterns, and the average of training data is calculated as a reference point. The raw data is then normalized to adjust position and direction, and dimensionality reduction is achieved through singular value decomposition to enhance processing efficiency and model training speed. A support vector machine classifier is used to classify and identify the processed data. The experimental section monitors sports injuries and investigates the accuracy of the system's monitoring. Compared to mainstream models such as Random Forest and Naive Bayes, the SVM utilized demonstrates good performance in accuracy, sensitivity, and specificity, reaching 94.2%, 92.5%, and 96.0% respectively.

Differences in training load, jump performance and injury occurrence in elite youth volleyball players

BACKGROUND

External and internal training load are used to monitor training effects in volleyball. Occurrence of injuries in volleyball is dependent of training loads and state of fitness but also playing positions and gender. This study aims to investigate the impact of gender and playing positions on injury occurrence among young volleyball players, considering both training loads and fitness levels.

METHODS

Conducted from September 2021 to May 2022, this study involved 37 elite young volleyball players, comprising 16 female (176.8±3.6 cm; 65.3±5.7 kg; 13.9±1.1 years old) and 21 males (189.6±7.3 cm; 77.4±9.5 kg; 14.7±1.2 years old). G-Vert accelerometer was used to quantify training load. During these sessions, RPE, state of fitness and occurrence of injuries, were collected using a daily questionnaire.

RESULTS

The primary findings indicate that males demonstrated a higher number of jumps, mean intensity, mean training load per session, and reported higher fitness levels compared to females (P<0.001). However, females were more injured than males (P<0.001). Setters were identified as the players with the highest jump frequency, albeit at lower heights and intensities than their counterparts (P<0.001). Among males, middle blockers exhibited the highest mean intensity and training load per session (P<0.01).

CONCLUSIONS

The elevated frequency of injuries and a worse reported fitness levels among females, despite lower training loads, suggests a potential deficiency in physical preparation among young women, particularly in terms of their ability to perform repeated high-intensity jumps.

Causal inference did not detect any effect of jump load on knee complaints in elite men's volleyball

The aim was to determine how jump load affects knee complaints in elite men's volleyball. We collected data from four men's premier league volleyball teams through three seasons in a prospective cohort study (65 players, 102 player-seasons). Vert inertial measurement devices captured the jump load (jump frequency and jump height) from 21 088 daily player sessions, and knee complaints were reported in 3568 weekly OSTRC-O questionnaires. Mixed complementary log-log regression models described the probability of (i) experiencing symptoms if players were currently asymptomatic, (ii) worsening symptoms if players had symptoms, and (iii) recovery from knee complaints. Based on our causal assumptions, weekly jump load was modeled as the independent variable, adjusted for age (years), weight (kg), position on volleyball team, and past jump load. No certain evidence of an association was found between weekly jump load and probability of (i) knee complaints (p from 0.10 to 0.32 for three restricted cubic splines of load), (ii) worsening symptoms if the player already had symptoms (p from 0.11 to 0.97), (iii) recovery (p from 0.36 to 0.63). The probability of knee complaints was highest for above-average weekly jump load (~1.2% for an outside hitter with mean age and height) compared with low loads (~1%) and very high loads (→ ~ 0%). The association between jump load and knee complaints risk remains unclear. Small differences in risk across observed jump load levels were observed. It would likely require substantially increased sample sizes to detect this association with certainty.

Performance and healthcare analysis in elite sports teams using artificial intelligence: a scoping review

Introduction

In competitive sports, teams are increasingly relying on advanced systems for improved performance and results. This study reviews the literature on the role of artificial intelligence (AI) in managing these complexities and encouraging a system thinking shift. It found various AI applications, including performance enhancement, healthcare, technical and tactical support, talent identification, game prediction, business growth, and AI testing innovations. The main goal of the study was to assess research supporting performance and healthcare.

Methods

Systematic searches were conducted on databases such as Pubmed, Web of Sciences, and Scopus to find articles using AI to understand or improve sports team performance. Thirty-two studies were selected for review.

Results

The analysis shows that, of the thirty-two articles reviewed, fifteen focused on performance and seventeen on healthcare. Football (Soccer) was the most researched sport, making up 67% of studies. The revised studies comprised 2,823 professional athletes, with a gender split of 65.36% male and 34.64% female. Identified AI and non-AI methods mainly included Tree-based techniques (36%), Ada/XGBoost (19%), Neural Networks (9%), K-Nearest Neighbours (9%), Classical Regression Techniques (9%), and Support Vector Machines (6%).

Conclusions

This study highlights the increasing use of AI in managing sports-related healthcare and performance complexities. These findings aim to assist researchers, practitioners, and policymakers in developing practical applications and exploring future complex systems dynamics.

Beyond the Jump: A Scoping Review of External Training Load Metrics in Volleyball

CONTEXT

Volleyball is a complex sport involving multifaceted movements and high-velocity actions, leading to diverse external training loads (ETLs) that have profound implications for player performance and injury risk.

OBJECTIVE

To provide a comprehensive overview of the measurement of ETL in volleyball, identify gaps in current understanding, and offer valuable insights for stakeholders in the field.

DATA SOURCES

The literature search was conducted across the following electronic databases: PubMed/Medline, Scopus, Web of Science, and SPORTDiscus.

STUDY SELECTION

Studies were selected based on their relevance to the measurement of ETL in volleyball.

STUDY DESIGN

A scoping review methodology was chosen to map and summarize the broad body of literature related to ETL measurement in volleyball.

LEVEL OF EVIDENCE

Level 4.

DATA EXTRACTION

Data related to ETL measurements in volleyball were extracted and analyzed from the selected studies, focusing on metrics utilized, player positions examined, and technologies employed.

RESULTS

A total of 18 studies related to ETL in volleyball were identified and examined for this review. Despite the importance of sagittal plane movements in volleyball, the review identified a substantial research gap regarding ETL measurements beyond this plane, as well as a lack of focus on the unique demands of different player positions like the liberos. The use of technologies such as inertial measurement units was prevalent, but more comprehensive measurement methods are needed.

CONCLUSION

There is a critical need for diversified ETL metrics in volleyball, extending beyond the conventional sagittal plane measurements. The findings highlight a substantial research gap in addressing the unique demands of different player positions, notably the liberos. This study underscores the importance of incorporating multiplanar movement data, player-specific roles, and advanced measurement technologies to develop more tailored training programs and injury prevention strategies.

The Push Forward in Rehabilitation: Validation of a Machine Learning Method for Detection of Wheelchair Propulsion Type

Within rehabilitation, there is a great need for a simple method to monitor wheelchair use, especially whether it is active or passive. For this purpose, an existing measurement technique was extended with a method for detecting self- or attendant-pushed wheelchair propulsion. The aim of this study was to validate this new detection method by comparison with manual annotation of wheelchair use. Twenty-four amputation and stroke patients completed a semi-structured course of active and passive wheelchair use. Based on a machine learning approach, a method was developed that detected the type of movement. The machine learning method was trained based on the data of a single-wheel sensor as well as a setup using an additional sensor on the frame. The method showed high accuracy (F1 = 0.886, frame and wheel sensor) even if only a single wheel sensor was used (F1 = 0.827). The developed and validated measurement method is ideally suited to easily determine wheelchair use and the corresponding activity level of patients in rehabilitation.

A novel approach for sports injury risk prediction: based on time-series image encoding and deep learning

The rapid development of big data technology and artificial intelligence has provided a new perspective on sports injury prevention. Although data-driven algorithms have achieved some valuable results in the field of sports injury risk assessment, the lack of sufficient generalization of models and the inability to automate feature extraction have made it challenging to deploy research results in the real world. Therefore, this study attempts to build an injury risk prediction model using a combination of time-series image encoding and deep learning algorithms to address this issue better. This study used the time-series image encoding approach for feature construction to represent relationships between values at different moments, including Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF), Markov Transition Field (MTF), and Recurrence Plot (RP). Deep Convolutional Auto-Encoder (DCAE) learned the image-encoded data for representation to obtain features with good discrimination, and the classifier was performed using Deep Neural Network (DNN). The results from five repeated experiments show that the GASF-DCAE-DNN model is overall better in the training (AUC: 0.985 ± 0.001, Gmean: 0.930 ± 0.007, Sensitivity: 0.997 ± 0.003, Specificity: 0.868 ± 0.013) and test sets (AUC: 0.891 ± 0.026, Gmean: 0.830 ± 0.027, Sensitivity: 0.816 ± 0.039, Specificity: 0.845 ± 0.022), with good discriminative power, robustness, and generalization ability. Compared with the best model reported in the literature, the AUC, Gmean, Sensitivity, and Specificity of the GASF-DCAE-DNN model were higher by 23.9%, 27.5%, 39.7%, and 16.2%, respectively, which confirmed the validity and practicability of the model in injury risk prediction. In addition, differences in injury risk patterns between the training and test sets were identified through shapley additivity interpretation. It was also found that the training volume was an essential factor that affected injury risk prediction. The model proposed in this study provides a powerful injury risk prediction tool for future sports injury prevention practice.

Optimization of sports effect evaluation technology from random forest algorithm and elastic network algorithm

This study leverages advanced data mining and machine learning techniques to delve deeper into the impact of sports activities on physical health and provide a scientific foundation for informed sports selection and health promotion. Guided by the Elastic Net algorithm, a sports performance assessment model is meticulously constructed. In contrast to the conventional Least Absolute Shrinkage and Selection Operator (Lasso) algorithm, this model seeks to elucidate the factors influencing physical health indicators due to sports activities. Additionally, the incorporation of the Random Forest algorithm facilitates a comprehensive evaluation of sports performance across distinct dimensions: wrestling-type sports, soccer-type sports, skill-based sports, and school physical education. Employing the Top-K criterion for evaluation and juxtaposing it with the high-performance Support Vector Machine (SVM) algorithm, the accuracy is scrutinized under three distinct criteria: Top-3, Top-5, and Top-10. The pivotal innovation of this study resides in the amalgamation of the Elastic Net and Random Forest algorithms, permitting a holistic contemplation of the influencing factors of diverse sports activities on physical health indicators. Through this integrated methodology, the research achieves a more precise assessment of the effects of sports activities, unveiling a range of impacts various sports have on physical health. Consequently, a more refined assessment tool for sports performance detection and health development is established. Capitalizing on the Elastic Net algorithm, this research optimizes model construction during the pivotal feature selection phase, effectively capturing the crucial influencing factors associated with different sports activities. Concurrently, the integration of the Random Forest algorithm augments the predictive prowess of the model, enabling the sports performance assessment model to comprehensively unveil the extent of impact stemming from various sports activities. This study stands as a noteworthy contribution to the arena of sports performance assessment, offering substantial insights and advancements to both sports health and research methodologies.

Development of an algorithm-based approach using neuromuscular test results to indicate an increased risk for non-contact lower limb injuries in elite football players

Objectives

This retrospective cohort study explored an algorithm-based approach using neuromuscular test results to indicate an increased risk for non-contact lower limb injuries in elite football players.

Methods

Neuromuscular data (eccentric hamstring strength, isometric adduction and abduction strength and countermovement jump) of 77 professional male football players were assessed at the start of the season (baseline) and, respectively, at 4, 3, 2 and 1 weeks before the injury. We included 278 cases (92 injuries; 186 healthy) and applied a subgroup discovery algorithm.

Results

More injuries occurred when between-limb abduction imbalance 3 weeks before injury neared or exceeded baseline values (threshold≥0.97), or adduction muscle strength of the right leg 1 week before injury remained the same or decreased compared with baseline values (threshold≤1.01). Moreover, in 50% of the cases, an injury occurred if abduction strength imbalance before the injury is over 97% of the baseline values and peak landing force in the left leg 4 weeks before the injury is lower than 124% compared with baseline.

Conclusions

This exploratory analysis provides a proof of concept demonstrating that a subgroup discovery algorithm using neuromuscular tests has potential use for injury prevention in football.

Capturing the Complex Relationship Between Internal and External Training Load: A Data-Driven Approach

BACKGROUND

Training load is typically described in terms of internal and external load. Investigating the coupling of internal and external training load is relevant to many sports. Here, continuous kernel-density estimation (KDE) may be a valuable tool to capture and visualize this coupling.

AIM

Using training load data in speed skating, we evaluated how well bivariate KDE plots describe the coupling of internal and external load and differentiate between specific training sessions, compared to training impulse scores or intensity distribution into training zones.

METHODS

On-ice training sessions of 18 young (sub)elite speed skaters were monitored for velocity and heart rate during 2 consecutive seasons. Training session types were obtained from the coach's training scheme, including endurance, interval, tempo, and sprint sessions. Differences in training load between session types were assessed using Kruskal-Wallis or Kolmogorov-Smirnov tests for training impulse and KDE scores, respectively.

RESULTS

Training impulse scores were not different between training session types, except for extensive endurance sessions. However, all training session types differed when comparing KDEs for heart rate and velocity (both P < .001). In addition, 2D KDE plots of heart rate and velocity provide detailed insights into the (subtle differences in) coupling of internal and external training load that could not be obtained by 2D plots using training zones.

CONCLUSION

2D KDE plots provide a valuable tool to visualize and inform coaches on the (subtle differences in) coupling of internal and external training load for training sessions. This will help coaches design better training schemes aiming at desired training adaptations.

Use, Validity and Reliability of Inertial Movement Units in Volleyball: Systematic Review of the Scientific Literature

The use of inertial devices in sport has become increasingly common. The aim of this study was to examine the validity and reliability of multiple devices for measuring jump height in volleyball. The search was carried out in four databases (PubMed, Scopus, Web of Sciences and SPORTDiscus) using keywords and Boolean operators. Twenty-one studies were selected that met the established selection criteria. The studies focused on determining the validity and reliability of IMUs (52.38%), on controlling and quantifying external load (28.57%) and on describing differences between playing positions (19.05%). Indoor volleyball was the modality in which IMUs have been used the most. The most evaluated population was elite, adult and senior athletes. The IMUs were used both in training and in competition, evaluating mainly the amount of jump, the height of the jumps and some biomechanical aspects. Criteria and good validity values for jump counting are established. The reliability of the devices and the evidence is contradictory. IMUs are devices used in volleyball to count and measure vertical displacements and/or compare these measurements with the playing position, training or to determine the external load of the athletes. It has good validity measures, although inter-measurement reliability needs to be improved. Further studies are suggested to position IMUs as measuring instruments to analyze jumping and sport performance of players and teams.

Validity and Reliability of Facial Rating of Perceived Exertion Scales for Training Load Monitoring

ABSTRACT

van der Zwaard, S, Hooft Graafland, F, van Middelkoop, C, and Lintmeijer, LL. Validity and reliability of facial rating of perceived exertion scales for training load monitoring. J Strength Cond Res XX(X): 000-000, 2022-Rating of perceived exertion (RPE) is often used by coaches and athletes to indicate exercise intensity, which facilitates training load monitoring and prescription. Although RPE is typically measured using the Borg's category-ratio 10-point scale (CR10), digital sports platforms have recently started to incorporate facial RPE scales, which potentially have a better user experience. The aim of this study was to evaluate the validity and reliability of a 5-point facial RPE scale (FCR5) and a 10-point facial RPE scale (FCR10), using the CR10 as a golden standard and to assess their use for training load monitoring. Forty-nine subjects were grouped into 17 untrained (UT), 19 recreationally trained (RT), and 13 trained (T) individuals Subjects completed 9 randomly ordered home-based workout sessions (3 intensities × 3 RPE scales) on the Fitchannel.com platform. Heart rate was monitored throughout the workouts. Subjects performed 3 additional workouts to assess reliability. Validity and reliability of both facial RPE scales were low in UT subjects (intraclass correlation [ICC] ≤ 0.44, p ≤ 0.06 and ICC ≤ 0.43, p ≥ 0.09). In RT and T subjects, validity was moderate for FCR5 (ICC ≥ 0.72, p < 0.001) and good for FCR10 (ICC ≥ 0.80, p < 0.001). Reliability for these groups was rather poor for FCR5 (ICC = 0.51, p = 0.006) and moderate for FCR10 (ICC = 0.74, p < 0.001), but it was excellent for CR10 (ICC = 0.92, p < 0.001). In RT and T subjects, session RPE scores were also strongly related to Edward's training impulse scores ( r ≥ 0.70, p < 0.001). User experience was best supported by the FCR10 scale. In conclusion, researchers, coaches, strength and conditioning professionals, and digital sports platforms are encouraged to incorporate the valid and reliable FCR10 and not FCR5 to assess perceived exertion and internal training load of recreationally trained and trained individuals.

Modeling Match Performance in Elite Volleyball Players: Importance of Jump Load and Strength Training Characteristics

In this study, we investigated the relationships between training load, perceived wellness and match performance in professional volleyball by applying the machine learning techniques XGBoost, random forest regression and subgroup discovery. Physical load data were obtained by manually logging all physical activities and using wearable sensors. Daily wellness of players was monitored using questionnaires. Match performance was derived from annotated actions by a video scout during matches. We identified conditions of predictor variables that related to attack and pass performance (p < 0.05). Better attack performance is related to heavy weights of lower-body strength training exercises in the preceding four weeks. However, worse attack performance is linked to large variations in weights of full-body strength training exercises, excessively heavy upper-body strength training, low jump heights and small variations in the number of high jumps in the four weeks prior to competition. Lower passing performance was associated with small variations in the number of high jumps in the preceding week and an excessive amount of high jumps performed, on average, in the two weeks prior to competition. Differences in findings with respect to passing and attack performance suggest that elite volleyball players can improve their performance if training schedules are adapted to the position of a player.

Influence of Surveillance Methods in the Detection of Sports Injuries and Illnesses

Background

Epidemiological data on sports injuries and illnesses depend on the surveillance methodology and the definition of the health problems. The effect of different surveillance methods on the data collection has been investigated for overuse injuries, but not for other health problems such as traumatic injuries and illnesses.

Purpose

The purpose of this study was to investigate the new surveillance method developed by the Oslo Sports Trauma Research Center (OSTRC), which is based on any complaint definition (new method), to identify health problems compared with the traditional surveillance method, which is based on time loss definition.

Study design

Descriptive epidemiology study.

Methods

A total of 62 Japanese athletes were prospectively followed-up for 18 weeks to assess differences in health problems identified by both new and traditional methods. Every week, the athletes completed the Japanese version of the OSTRC questionnaire (OSTRC-H2.​JP), whereas the teams' athletic trainers registered health problems with a time loss definition. The numbers of health problems identified via each surveillance method were calculated and compared with each other to assess any differences between their results.

Results

The average weekly response rate to the OSTRC-H2.​JP was 82.1% (95% CI, 79.8-84.3). This new method recorded 3.1 times more health problems (3.1 times more injuries and 2.8 times more illnesses) than the traditional method. The difference between both surveillance methods' counts was greater for overuse injuries (5.3 times) than for traumatic injuries (2.5 times).

Conclusions

This study found that the new method captured more than three times as many health problems as the traditional method. In particular, the difference between both methods' counts was greater for overuse injuries than for traumatic injuries.

Level of evidence

2b.

A novel lower extremity non-contact injury risk prediction model based on multimodal fusion and interpretable machine learning

The application of machine learning algorithms in studying injury assessment methods based on data analysis has recently provided a new research insight for sports injury prevention. However, the data used in these studies are primarily multi-source and multimodal (i.e., longitudinal repeated-measures data and cross-sectional data), resulting in the models not fully utilising the information in the data to reveal specific injury risk patterns. Therefore, this study proposed an injury risk prediction model based on a multi-modal strategy and machine learning algorithms to handle multi-source data better and predict injury risk. This study retrospectively analysed the routine monitoring data of sixteen young female basketball players. These data included training load, perceived well-being status, physiological response, physical performance and lower extremity non-contact injury registration. This study partitions the original dataset based on the frequency of data collection. Extreme gradient boosting (XGBoost) was used to construct unimodal submodels to obtain decision scores for each category of indicators. Ultimately, the decision scores from each submodel were fused using the random forest (RF) to generate a lower extremity non-contact injury risk prediction model at the decision-level. The 10-fold cross-validation results showed that the fusion model was effective in classifying non-injured (mean Precision: 0.9932, mean Recall: 0.9976, mean F2-score: 0.9967), minimal lower extremity non-contact injuries risk (mean Precision: 0.9317, mean Recall: 0.9167, mean F2-score: 0.9171), and mild lower extremity non-contact injuries risk (mean Precision: 0.9000, mean Recall: 0.9000, mean F2-score: 0.9000). The model performed significantly more optimal than the submodel. Comparing the fusion model proposed with a traditional data integration scheme, the average Precision and Recall improved by 8.2 and 20.3%, respectively. The decision curves analysis showed that the proposed fusion model provided a higher net benefit to athletes with potential lower extremity non-contact injury risk. The validity, feasibility and practicality of the proposed model have been confirmed. In addition, the shapley additive explanation (SHAP) and network visualisation revealed differences in lower extremity non-contact injury risk patterns across severity levels. The model proposed in this study provided a fresh perspective on injury prevention in future research.

The Use of Wearable Sensors for Preventing, Assessing, and Informing Recovery from Sport-Related Musculoskeletal Injuries: A Systematic Scoping Review

Wearable technologies are often indicated as tools that can enable the in-field collection of quantitative biomechanical data, unobtrusively, for extended periods of time, and with few spatial limitations. Despite many claims about their potential for impact in the area of injury prevention and management, there seems to be little attention to grounding this potential in biomechanical research linking quantities from wearables to musculoskeletal injuries, and to assessing the readiness of these biomechanical approaches for being implemented in real practice. We performed a systematic scoping review to characterise and critically analyse the state of the art of research using wearable technologies to study musculoskeletal injuries in sport from a biomechanical perspective. A total of 4952 articles were retrieved from the Web of Science, Scopus, and PubMed databases; 165 were included. Multiple study features-such as research design, scope, experimental settings, and applied context-were summarised and assessed. We also proposed an injury-research readiness classification tool to gauge the maturity of biomechanical approaches using wearables. Five main conclusions emerged from this review, which we used as a springboard to propose guidelines and good practices for future research and dissemination in the field.

Resilience in sports: a multidisciplinary, dynamic, and personalized perspective

Athletes are exposed to various psychological and physiological stressors, such as losing matches and high training loads. Understanding and improving the resilience of athletes is therefore crucial to prevent performance decrements and psychological or physical problems. In this review, resilience is conceptualized as a dynamic process of bouncing back to normal functioning following stressors. This process has been of wide interest in psychology, but also in the physiology and sports science literature (e.g. load and recovery). To improve our understanding of the process of resilience, we argue for a collaborative synthesis of knowledge from the domains of psychology, physiology, sports science, and data science. Accordingly, we propose a multidisciplinary, dynamic, and personalized research agenda on resilience. We explain how new technologies and data science applications are important future trends (1) to detect warning signals for resilience losses in (combinations of) psychological and physiological changes, and (2) to provide athletes and their coaches with personalized feedback about athletes' resilience.