Effective injury forecasting in soccer with GPS training data and machine learning

Enhancing Sports Injury Risk Assessment in Soccer Through Machine Learning and Training Load Analysis

Sports injuries pose significant challenges in athlete welfare and team dynamics, particularly in high-intensity sports like soccer. This study used machine learning algorithms to assess non-contact injury risk in professional male soccer players from physiological and mechanical load variables. Twenty-five professional male soccer players with a first-time, non-contact muscle injury were included in this study. Recordings of external load (speed, distance, and acceleration/deceleration data) and internal load (heart rate) were obtained during all training sessions and official matches over a 4-year period. Machine learning model training and evaluation features were calculated for each of nine different metrics for a 28-day period prior to the injury and an equal-length baseline epoch. The acute surge in the values of each workload metric was quantified by the deviation of maximum values from the average, while the variations of cumulative workload over the last four weeks preceding injury were also calculated. Seven features were selected by the model as prominent estimators of injury incidence. Three of the features concerned acute load deviations (number of sprints, training load score-incorporating heart rate and muscle load- and time of heart rate at the 90-100% of maximum). The four cumulative load features were (total distance, high speed and sprint running distance and training load score). The accuracy of the muscle injury risk assessment model was 0.78, with a sensitivity of 0.73 and specificity of 0.85. Our model achieved high performance in injury risk detection using a limited number of training load variables. The inclusion, for the first time, of heart rate related variables in an injury risk assessment model highlights the importance of physiological overload as a contributor to muscle injuries in soccer. By identifying the important parameters, coaches may prevent muscle injuries by controlling surges of training load during training and competition.

Bridging the Gap Between Training and Competition in Elite Rink Hockey: A Pilot Study

BACKGROUND

Monitoring training load and competition load is crucial for evaluating and improving athlete performance. This study proposes an applied approach to characterize and classify the training task specificity in relation to competition in a top-level rink hockey team, considering external and internal load from training tasks and competition.

HYPOTHESIS

Training tasks and game demands have significant dose-response differences, and exercises can be classified successfully based on their physiological and biomechanical demands.

STUDY DESIGN

Cross-sectional study.

LEVEL OF EVIDENCE

Level 5.

METHODS

Ten elite-level male rink hockey players participated in this study. Players were monitored on 6 different task categories during 8 training sessions and 2 official games. A linear mixed model with random intercepts was used to compare training tasks and competition load, accounting for individual repeated measures. A 2-step cluster analysis was performed to classify the training tasks and games based on physiological and biomechanical load, employing log-likelihood as the distance measure and Schwartz's Bayesian criterion.

RESULTS

Average heartrate , maximum heartrate, and high-speed skating (18.1-30 km/h) were the best physiological load predictors, while the most effective biomechanical load predictors were impacts [8-10] g(n), decelerations [-10 to -3]m/s²(n), and accelerations [3-10]m/s²(n). Different physiological and biomechanical responses were verified between training tasks and match demands. A 4-quadrant efforts assessment for each task category revealed that training tasks used by the team in the analysis presented lower biomechanical and physiological load demands than competition.

CONCLUSION

Training tasks failed to adequately replicate the specific demands of competition, especially regarding high mechanical stress, such as the absence of high-intensity impacts and decelerations.

CLINICAL RELEVANCE

This method of classification of training tasks may allow coaches to understand further the specificity and contribution of each task to competition demands, consequently improving the capacity of load management and the preparedness and readiness of players for competition.

A new approach to comparing the demands of small-sided games and soccer matches

To improve soccer performance, coaches should be able to replicate the match's physical efforts during the training sessions. For this goal, small-sided games (SSGs) are widely used. The main purpose of the current study was to develop similarity and overload scores to quantify the degree of similarity and the extent to which the SSG was able to replicate match intensity. GPSs were employed to collect external load and were grouped in three vectors (kinematic, metabolic, and mechanical). Euclidean distance was used to calculate the distance between training and match vectors, which was subsequently converted into a similarity score. The average of the pairwise difference between vectors was used to develop the overload scores. Three similarity (Simkin, Simmet, Simmec) and three overload scores (OVERkin, OVERmet, OVERmec) were defined for kinematic, metabolic, and mechanical vectors. Simmet and OVERmet were excluded from further analysis, showing a very large correlation (r > 0.7, p < 0.01) with Simkin and OVERkin. The scores were subsequently analysed considering teams' level (First team vs. U19 team) and SSGs' characteristics in the various playing roles. The independent-sample t-test showed (p < 0.01) that the First team presented greater Simkin (d = 0.91), OVERkin (d = 0.47), and OVERmec (d = 0.35) scores. Moreover, a generalized linear mixed model (GLMM) was employed to evaluate differences according to SSG characteristics. The results suggest that a specific SSG format could lead to different similarity and overload scores according to the playing position. This process could simplify data interpretation and categorize SSGs based on their scores.

Artificial intelligence applications in the football codes: A systematic review

Artificial Intelligence (AI) is increasingly being adopted across many domains such as transport, healthcare, defence and sport, with football codes no exception. Though there is a range of potential benefits of AI, concern has also been expressed regarding potential risks. An important first step in ensuring that AI applications in football are usable, beneficial, safe and ethical is to understand the current range of applications, the AI models adopted and their proposed functions. This systematic review aimed to identify different applications of AI across football codes to synthesise current knowledge and determine whether potential risks are being considered. The systematic review included 190 peer-reviewed articles. Nine areas of application were found ranging from athlete evaluation and event detection to match outcome prediction and injury detection and prediction. In total, 27 different AI models were identified, with artificial neural networks the most frequently applied. Five AI assessment metrics were identified including specificity, recall, precision, accuracy and F1-score. Four potential risks were identified, concerning data security, usability, data biases and inappropriate athlete load management. It is concluded that, though a wide range of AI applications currently exist, further work is required to develop AI for football and identify and manage potential risks.

A Data-Driven Approach to Predicting Recreational Activity Participation Using Machine Learning

Purpose: With the popularity of recreational activities, the study aimed to develop prediction models for recreational activity participation and explore the key factors affecting participation in recreational activities. Methods: A total of 12,712 participants, excluding individuals under 20, were selected from the National Health and Nutrition Examination Survey (NHANES) from 2011 to 2018. The mean age of the sample was 46.86 years (±16.97), with a gender distribution of 6,721 males and 5,991 females. The variables included demographic, physical-related variables, and lifestyle variables. This study developed 42 prediction models using six machine learning methods, including logistic regression, Support Vector Machine (SVM), decision tree, random forest, eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM). The relative importance of each variable was evaluated by permutation feature importance. Results: The results illustrated that the LightGBM was the most effective algorithm for predicting recreational activity participation (accuracy: .838, precision: .783, recall: .967, F1-score: .865, AUC: .826). In particular, prediction performance increased when the demographic and lifestyle datasets were used together. Next, as the result of the permutation feature importance based on the top models, education level and moderate-vigorous physical activity (MVPA) were found to be essential variables. Conclusion: These findings demonstrated the potential of a data-driven approach utilizing machine learning in a recreational discipline. Furthermore, this study interpreted the prediction model through feature importance analysis to overcome the limitation of machine learning interpretability.

Space and players' number constrains the external and internal load demands in youth futsal

Introduction

The aim of this study was to analyze the effects of space and number of players manipulation on the external and internal load demands of youth futsal athletes.

Methods

Forty-two male U17 players (age = 15.62 ± 0.58 years) from three futsal teams participated in the study. In this cross-sectional study that lasted 8-week, the player's sample practiced six futsal tasks (T1-T6) and a futsal game played under the official rules (T7). From T1-T6, two task constraints were manipulated: (i) the number of players and, (ii) the space of play. The WIMU PRO™ Ultra-Wideband (UWB) tracking system was used to measure the external and internal load during the futsal tasks. External load was quantified using kinematic and mechanical variables extracted from positional data and, the internal load was quantified using Heart rate (HR) and rating of perceived exertion (RPE). Repeated measures ANOVA was used for comparison purposes.

Results

In general, the results showed high external (total distance, distance 18.1-21, above 21 Km/h, and high intensity acceleration and deceleration, p < 0.001) and internal load (heart rate average and rating of perceived exertion, p < 0.001) in the tasks with low number of players and high area. In relation to the match, the tasks with small relative area per player (GK + 2 vs. 2 + GK and GK + 3 vs. 3 + GK in 20 × 20 m) promoted low external load.

Conclusion

It was concluded that increasing the relative area by reducing the number of players involved in the tasks in the form of small-sided games (GK + 2 vs. 2 + GK and GK + 3 vs. 3 + GK), in relation to the futsal game (GK + 4 vs. 4 + GK), can be considered a pedagogical strategy to increase the external and internal load demands of young futsal players.

The Future of Artificial Intelligence in Sports Medicine and Return to Play

Artificial intelligence (AI) has shown tremendous growth over the last decade, with the more recent development of clinical applications in health care. The ability of AI to synthesize large amounts of complex data automatically allows health care providers to access previously unavailable metrics and thus enhance and personalize patient care. These innovations include AI-assisted diagnostic tools, prediction models for each treatment pathway, and various tools for workflow optimization. The extension of AI into sports medicine is still early, but numerous AI-driven algorithms, devices, and research initiatives have delved into predicting and preventing athlete injury, aiding in injury assessment, optimizing recovery plans, monitoring rehabilitation progress, and predicting return to play.

Analyzing ECG signals in professional football players using machine learning techniques

Background

Football player's health is important, and preventing sudden cardiac arrest may be a critical issue. Professional football players have different ECG signals than the average population, yet there are considerable gaps in study whereas the general population has been extensively studied.

Objectives

(a) Generate a reference and innovative resting 12-lead ECG database from 54 UEFA PRO level male football players from La Liga. This is a novel approach to cope the ECG and possible arrythmias in athletes. (b) Manage each XML athlete ECG data and develop a free-use program to visualize, denoise and filter the signal with the capacity to automate the labelling of the waves and save the reports. (c) Study the ECG wave shape and generate models through ML to analyse its utility to automate basic diagnosis.

Methods

The dataset collection is based on a prospective observational cohort and includes 10 s, 12-lead ECGs and rhythm and condition labels for each athlete. Physiological sport arrhythmias, T-Wave shape and other findings were studied and labelled. ECG Visualizer was developed and used for 3 machine learning (ML) methods to automate sinus bradycardia arrhythmia diagnosis.

Results

A dataset with 163 ECGs in XML format was collected comprising the Pro Football 12-lead Resting Electrocardiogram Database (PF12RED). "ECG Visualizer" software was developed, and ML was shown to be useful in detecting sinus bradycardia.

Conclusions

The study demonstrates that AI and machine learning can detect simple arrhythmias with accuracy, also it provides a valuable dataset and a free software application.

Perceptions and beliefs on sports injury prediction as an injury risk reduction strategy: An online survey on elite athletics (track and field) athletes, coaches, and health professionals

OBJECTIVES

To explore perceptions and beliefs of elite athletics (track and field) athletes, coaches, and health professionals, towards the use of injury prediction as an injury risk reduction strategy.

DESIGN

Cross-sectional study.

METHOD

During the 2022 European Athletics Championships in Munich, registered athletes, coaches, and health professionals were asked to complete an online questionnaire on their perceptions and beliefs of injury prediction use as an injury risk reduction strategy. The perceived level of interest, intent to use, help, potential stress (psychological impact) and dissemination were assessed by a score from 0 to 100.

RESULTS

We collected 54 responses from 17 countries. Elite athletics stakeholders expressed a perceived level of interest, intent to use, and help of injury prediction of (mean ± SD) 85 ± 16, 84 ± 16, and 85 ± 15, respectively. The perceived level of potential stress was 41 ± 33 (range from 0 to 100), with an important inter-individual variability in each elite athletics stakeholder's category.

CONCLUSIONS

This was the first study investigating the perceptions and beliefs of elite athletics stakeholders regarding the use of injury prediction as an injury risk reduction strategy. Regardless of the stakeholders, there was a high perceived level of interest, intent to use and help reported in this potential strategy.

Predicting Soccer Players' Fitness Status Through a Machine-Learning Approach

PURPOSE

The study had 3 purposes: (1) to develop an index using machine-learning techniques to predict the fitness status of soccer players, (2) to explore the index's validity and its relationship with a submaximal run test (SMFT), and (3) to analyze the impact of weekly training load on the index and SMFT outcomes.

METHODS

The study involved 50 players from an Italian professional soccer club. External and internal loads were collected during training sessions. Various machine-learning algorithms were assessed for their ability to predict heart-rate responses during the training drills based on external load data. The fitness index, calculated as the difference between actual and predicted heart rates, was correlated with SMFT outcomes.

RESULTS

Random forest regression (mean absolute error = 3.8 [0.05]) outperformed the other machine-learning algorithms (extreme gradient boosting and linear regression). Average speed, minutes from the start of the training session, and the work:rest ratio were identified as the most important features. The fitness index displayed a very large correlation (r = .70) with SMFT outcomes, with the highest result observed during possession games and physical conditioning exercises. The study revealed that heart-rate responses from SMFT and the fitness index could diverge throughout the season, suggesting different aspects of fitness.

CONCLUSIONS

This study introduces an "invisible monitoring" approach to assess soccer player fitness in the training environment. The developed fitness index, in conjunction with traditional fitness tests, provides a comprehensive understanding of player readiness. This research paves the way for practical applications in soccer, enabling personalized training adjustments and injury prevention.

Predicting academic achievement from the collaborative influences of executive function, physical fitness, and demographic factors among primary school students in China: ensemble learning methods

BACKGROUND

Elevated levels of executive function and physical fitness play a pivotal role in shaping future quality of life. However, few studies have examined the collaborative influences of physical and mental health on academic achievement. This study aims to investigate the key factors that collaboratively influence primary school students' academic achievement from executive function, physical fitness, and demographic factors. Additionally, ensemble learning methods are employed to predict academic achievement, and their predictive performance is compared with individual learners.

METHODS

A cluster sampling method was utilized to select 353 primary school students from Huai'an, China, who underwent assessments for executive function, physical fitness, and academic achievement. The recursive feature elimination cross-validation method was employed to identify key factors that collaboratively influence academic achievement. Ensemble learning models, utilizing eXtreme Gradient Boosting and Random Forest algorithms, were constructed based on Bagging and Boosting methods. Individual learners were developed using Support Vector Machine, Decision Tree, Logistic Regression, and Linear Discriminant Analysis algorithms, followed by the establishment of a Stacking ensemble learning model.

RESULTS

Our findings revealed that sex, body mass index, muscle strength, cardiorespiratory function, inhibition, working memory, and shifting were key factors influencing the academic achievement of primary school students. Moreover, ensemble learning models demonstrated superior predictive performance compared to individual learners in predicting academic achievement among primary school students.

CONCLUSIONS

Our results suggest that recognizing sex differences and emphasizing the simultaneous development of cognition and physical well-being can positively impact the academic development of primary school students. Ensemble learning methods warrant further attention, as they enable the establishment of an accurate academic early warning system for primary school students.

Relationship between external and internal load indicators and injury using machine learning in professional soccer: a systematic review and meta-analysis

This study verified the relationship between internal load (IL) and external load (EL) and their association on injury risk (IR) prediction considering machine learning (ML) approaches. Studies were included if: (1) participants were male professional soccer players; (2) carried out for at least 2 sessions, exercises, or competitions; (3) correlated training load (TL) with non-contact injuries; (4) applied ML approaches to predict TL and non-contact injuries. TL included: IL indicators (Rating of Perceived Exertion, RPE; Session-RPE, Heart Rate, HR) and EL indicators (Global Positioning System, GPS variables); the relationship between EL and IL through index, ratio, formula; ML indicators included performance measures, predictive performance of ML methods, measure of feature importance, relevant predictors, outcome variable, predictor variable, data pre-processing, features selection, ML methods. Twenty-five studies were included. Eleven addressed the relationship between EL and IL. Five used EL/IL indexes. Five studies predicted IL indicators. Three studies investigated the association between EL and IL with IR. One study predicted IR using ML. Significant positive correlations were found between S-RPE and total distance (TD) (r = 0.73; 95% CI (0.64 to 0.82)) as well as between S-RPE and player load (PL) (r = 0.76; 95% CI (0.68 to 0.84)). Association between IL and EL and their relationship with injuries were found. RPE, S-RPE, and HR were associated with different EL indicators. A positive relationship between EL and IL indicators and IR was also observed. Moreover, new indexes or ratios (integrating EL and IL) to improve knowledge regarding TL and fitness status were also applied. ML can predict IL indicators (HR and RPE), and IR. The present systematic review was registered in PROSPERO (CRD42021245312).

From data to action: a scoping review of wearable technologies and biomechanical assessments informing injury prevention strategies in sport

BACKGROUND

The purpose of this scoping review was to evaluate the current use of technologies in sports settings for training adaptation and injury prevention. The review aimed to map the existing literature, identify key concepts and themes, and highlight gaps in research, thus offering guidance for future studies.

METHODS

This study followed the guidelines of the PRISMA extension for scoping reviews and a search in four major databases was conducted.

RESULTS

A total of 21 studies were included. The findings highlighted the widespread use of various technologies, including wearable devices and force plates, to monitor athletes' performance and inform evidence-based decision-making in training and injury prevention. Variables such as Player Load, changes of direction, and acute chronic workload ratio were identified as key metrics in injury prediction.

CONCLUSIONS

This review uncovers a dynamic field of research in athlete injury prevention, emphasizing the extensive use of varied technologies. A key finding is the pivotal role of Player Load data, which offers nuanced insights for customizing training loads according to sport-specific demands, player positions, and the physical requirements of various activities. Additionally, the review sheds light on the utility of tools like force plates in assessing fatigue, aiding recovery, and steering injury rehabilitation, particularly in sports prone to knee and ankle injuries. These insights not only enhance our understanding of injury prevention but also provide a strategic direction for future research, aiming to boost athlete safety, performance, and career longevity.

Exploring the interplay between metabolic power and equivalent distance in training games and official matches in soccer: a machine learning approach

Introduction: This study aimed to explore the interplay between metabolic power (MP) and equivalent distance (ED) and their respective roles in training games (TGs) and official soccer matches. Furthermore, the secondary objective was to investigate the connection between external training load (ETL), determined by the interplay of metabolic power and equivalent distance, and internal training load (ITL) assessed through HR-based methods, serving as a measure of criterion validity. Methods: Twenty-one elite professional male soccer players participated in the study. Players were monitored during 11 months of full training and overall official matches. The study used a dataset of 4269 training games and 380 official matches split into training and test sets. In terms of machine learning methods, the study applied several techniques, including K-Nearest Neighbors, Decision Tree, Random Forest, and Support-Vector Machine classifiers. The dataset was divided into two subsets: a training set used for model training and a test set used for evaluation. Results: Based on metabolic power and equivalent distance, the study successfully employed four machine learning methods to accurately distinguish between the two types of soccer activities: TGs and official matches. The area under the curve (AUC) values ranged from 0.90 to 0.96, demonstrating high discriminatory power, with accuracy levels ranging from 0.89 to 0.98. Furthermore, the significant correlations observed between Edwards' training load (TL) and TL calculated from metabolic power metrics confirm the validity of these variables in assessing external training load in soccer. The correlation coefficients (r values) ranged from 0.59 to 0.87, all reaching statistical significance at p < 0.001. Discussion: These results underscore the critical importance of investigating the interaction between metabolic power and equivalent distance in soccer. While the overall intensity may appear similar between TGs and official matches, it is evident that underlying factors contributing to this intensity differ significantly. This highlights the necessity for more comprehensive analyses of the specific elements influencing physical effort during these activities. By addressing this fundamental aspect, this study contributes valuable insights to the field of sports science, aiding in the development of tailored training programs and strategies that can optimize player performance and reduce the risk of injuries in elite soccer.

The Trade Secret Taboo: Open Science Methods are Required to Improve Prediction Models in Sports Medicine and Performance

Clinical prediction models in sports medicine that utilize regression or machine learning techniques have become more widely published, used, and disseminated. However, these models are typically characterized by poor methodology and incomplete reporting, and an inadequate evaluation of performance, leading to unreliable predictions and weak clinical utility within their intended sport population. Before implementation in practice, models require a thorough evaluation. Strong replicable methods and transparency reporting allow practitioners and researchers to make independent judgments as to the model's validity, performance, clinical usefulness, and confidence it will do no harm. However, this is not reflected in the sports medicine literature. As shown in a recent systematic review of models for predicting sports injury models, most were typically characterized by poor methodology, incomplete reporting, and inadequate performance evaluation. Because of constraints imposed by data from individual teams, the development of accurate, reliable, and useful models is highly reliant on external validation. However, a barrier to collaboration is a desire to maintain a competitive advantage; a team's proprietary information is often perceived as high value, and so these 'trade secrets' are frequently guarded. These 'trade secrets' also apply to commercially available models, as developers are unwilling to share proprietary (and potentially profitable) development and validation information. In this Current Opinion, we: (1) argue that open science is essential for improving sport prediction models and (2) critically examine sport prediction models for open science practices.

Predicting Injury and Illness with Machine Learning in Elite Youth Soccer: A Comprehensive Monitoring Approach over 3 Months

The search for monitoring tools that provide early indication of injury and illness could contribute to better player protection. The aim of the present study was to i) determine the feasibility of and adherence to our monitoring approach, and ii) identify variables associated with up-coming illness and injury. We incorporated a comprehensive set of monitoring tools consisting of external load and physical fitness data, questionnaires, blood, neuromuscular-, hamstring, hip abductor and hip adductor performance tests performed over a three-month period in elite under-18 academy soccer players. Twenty-five players (age: 16.6 ± 0.9 years, height: 178 ± 7 cm, weight: 74 ± 7 kg, VO2max: 59 ± 4 ml/min/kg) took part in the study. In addition to evaluating adherence to the monitoring approach, data were analyzed using a linear support vector machine (SVM) to predict illness and injuries. The approach was feasible, with no injuries or dropouts due to the monitoring process. Questionnaire adherence was high at the beginning and decreased steadily towards the end of the study. An SVM resulted in the best classification results for three classification tasks, i.e., illness prediction, illness determination and injury prediction. For injury prediction, one of four injuries present in the test data set was detected, with 96.3% of all data points (i.e., injuries and non-injuries) correctly detected. For both illness prediction and determination, there was only one illness in the test data set that was detected by the linear SVM. However, the model showed low precision for injury and illness prediction with a considerable number of false-positives. The results demonstrate the feasibility of a holistic monitoring approach with the possibility of predicting illness and injury. Additional data points are needed to improve the prediction models. In practical application, this may lead to overcautious recommendations on when players should be protected from injury and illness.

An Overview of Machine Learning Applications in Sports Injury Prediction

Use injuries, i.e., injuries caused by repetitive strain on the body, represent a serious problem in athletics that has traditionally relied on historic datasets and human experience for prevention. Existing methodologies have been frustratingly slow at developing higher precision prevention practices. Technological advancements have permitted the emergence of artificial intelligence and machine learning (ML) as promising toolsets to enhance both injury mitigation and rehabilitation protocols. This article provides a comprehensive overview of recent advances in ML techniques as they have been applied to sports injury prediction and prevention. A comprehensive literature review was conducted searching PubMed/Medline, Institute of Electrical and Electronics Engineers (IEEE)/Institute of Engineering and Technology (IET), and ScienceDirect. Ovid Discovery and Google Scholar were used to provide additional aggregate results and a grey literature search. A focus was placed on papers published from 2017 to 2022. Algorithms of interest were limited to K-Nearest Neighbor (KNN), K-means, decision tree, random forest, gradient boosting and AdaBoost, and neural networks. A total of 42 original research papers were included, and their results were summarized. We conclude that given the current lack of open source, uniform data sets, as well as a reliance on dated regression models, no strong conclusions about the real-world efficacy of ML as it applies to sports injury prediction can be made. However, it is suggested that addressing these two issues will allow powerful, novel ML architectures to be deployed, thus rapidly advancing the state of this field, and providing validated clinical tools.

Externally validated machine learning algorithm accurately predicts medial tibial stress syndrome in military trainees: a multicohort study

Objectives

Medial tibial stress syndrome (MTSS) is a common musculoskeletal injury in both sporting and military settings. No reliable treatments exist, and reoccurrence rates are high. Prevention of MTSS is critical to reducing operational burden. Therefore, this study aimed to build a decision-making model to predict the individual risk of MTSS within officer cadets and test the external validity of the model on a separate military population.

Design

Prospective cohort study.

Methods

This study collected a suite of key variables previously established for predicting MTSS. Data were obtained from 107 cadets (34 women and 73 men). A follow-up survey was conducted at 3 months to determine MTSS diagnoses. Six ensemble learning algorithms were deployed and trained five times on random stratified samples of 75% of the dataset. The resultant algorithms were tested on the remaining 25% of the dataset, with models then compared for accuracy. The most accurate new algorithm was tested on an unrelated data sample of 123 Australian Navy recruits to establish external validity of the model.

Results

Calibrated random forest modelling was the most accurate in identifying a diagnosis of MTSS; (area under curve (AUC)=98%, classification accuracy (CA)=96%). External validation on a sample of Navy recruits resulted in comparable accuracy; (AUC=95%, CA=94%). When the model was tested on the combined datasets, similar accuracy was achieved; (AUC=92%, CA=91%).

Conclusion

This model is highly accurate in predicting those who will develop MTSS. The model provides important preventive capacity which should be trialled as a risk management intervention.

Relationship between a daily injury risk estimation feedback (I-REF) based on machine learning techniques and actual injury risk in athletics (track and field): protocol for a prospective cohort study over an athletics season

INTRODUCTION

Two-thirds of athletes (65%) have at least one injury complaint leading to participation restriction (ICPR) in athletics (track and field) during one season. The emerging practice of medicine and public health supported by electronic processes and communication in sports medicine represents an opportunity for developing new injury risk reduction strategies. Modelling and predicting the risk of injury in real-time through artificial intelligence using machine learning techniques might represent an innovative injury risk reduction strategy. Thus, the primary aim of this study will be to analyse the relationship between the level of Injury Risk Estimation Feedback (I-REF) use (average score of athletes' self-declared level of I-REF consideration for their athletics activity) and the ICPR burden during an athletics season.

METHOD AND ANALYSIS

We will conduct a prospective cohort study, called Injury Prediction with Artificial Intelligence (IPredict-AI), over one 38-week athletics season (from September 2022 to July 2023) involving competitive athletics athletes licensed with the French Federation of Athletics. All athletes will be asked to complete daily questionnaires on their athletics activity, their psychological state, their sleep, the level of I-REF use and any ICPR. I-REF will present a daily estimation of the ICPR risk ranging from 0% (no risk for injury) to 100% (maximal risk for injury) for the following day. All athletes will be free to see I-REF and to adapt their athletics activity according to I-REF. The primary outcome will be the ICPR burden over the follow-up (over an athletics season), defined as the number of days lost from training and/or competition due to ICPR per 1000 hours of athletics activity. The relationship between ICPR burden and the level of I-REF use will be explored by using linear regression models.

ETHICS AND DISSEMINATION

This prospective cohort study was reviewed and approved by the Saint-Etienne University Hospital Ethical Committee (Institutional Review Board: IORG0007394, IRBN1062022/CHUSTE). Results of the study will be disseminated in peer-reviewed journals and in international scientific congresses, as well as to the included participants.

The impact of sport-specific physical fitness change patterns on lower limb non-contact injury risk in youth female basketball players: a pilot study based on field testing and machine learning

Background: In recent years, identifying players with injury risk through physical fitness assessment has become a hot topic in sports science research. Although practitioners have conducted many studies on the relationship between physical fitness and the likelihood of injury, the relationship between the two remains indeterminate. Consequently, this study utilized machine learning to preliminary investigate the relationship between individual physical fitness tests and injury risk, aiming to identify whether patterns of physical fitness change have an impact on injury risk. Methods: This study conducted a retrospective analysis by extracting the records of 17 young female basketball players from the sport-specific physical fitness monitoring and injury registration database in Fujian Province. Sports-specific physical fitness tests included physical performance, physiological, biochemical, and subjective perceived responses. The data for each player was standardized individually using Z-scores. Synthetic minority over-sampling techniques and edited nearest neighbor algorithms were used to sample the training set to address the negative impact of class imbalance on model performance. Feature extraction was performed on the dataset using linear discriminant analysis, and the prediction model was constructed using the cost-sensitive neural network. Results: The 10 replicate 5-fold stratified cross-validation showed that the lower limb non-contact injury prediction model based on the cost-sensitive neural network had achieved good discrimination and calibration (average Precision: 0.6360; average Recall: 0.8700; average F2-Score: 0.7980; average AUC: 0.8590; average Brier-score: 0.1020), which could be well applied in training practice. According to the attribution analysis, agility and speed were important physical attributes that affect youth female basketball players' non-contact lower limb injury risk. Specifically, there was enhance in the performance of the 1-min double under, accompanied by an increase in urinary ketone and urinary blood levels following the agility test. The 3/4 basketball court sprint performance improved, while urinary protein and RPE levels decreased after the speed test. Conclusion: The sport-specific physical fitness change pattern can impact the lower limb non-contact injury risk of young female basketball players in Fujian Province, specifically in terms of agility and speed. These findings will provide valuable insights for planning athletes' physical training programs, managing fatigue, and preventing injuries.

Association between internal load responses and recovery ability in U19 professional soccer players: A machine learning approach

Background

The objective of soccer training load (TL) is enhancing players' performance while minimizing the possible negative effects induced by fatigue. In this regard, monitoring workloads and recovery is necessary to avoid overload and injuries. Given the controversial results found in literature, this study aims to better understand the complex relationship between internal training load (IL) by using rating of perceived exertion (RPE), recovery, and availability (i.e., subjective players' readiness status).

Methods

In this cross-sectional study, twenty-two-professional soccer players (age: 18.5 ± 0.4 years, height: 177 ± 6 cm, weight: 67 ± 6.7 kg) competing in the U19 Italian Championship were monitored using RPE scale to assess IL, and TreS scale to detect information about recovery and training/match availability during an entire season (2021-2022).

Results

Autocorrelation analysis showed a repeated pattern with 7 days lag (weekly microcycle pattern) for all the variables considered (i.e., TL, recovery, and availability). For recovery (r = 0.64, p < 0.001) and availability (r = 0.63, p < 0.001) the best lag for both of them is 1 day. It indicates that recovery and availability are related to the past day value. Moreover, TL was found to be negatively affected by recovery and availability of the current day (lag = 0 day). Cross-correlation analysis indicates that TL is negatively affected by recovery (r = 0.46, p < 0.001) and availability (r = 0.42, p < 0.001) of the current day (lag = 0 day). In particular, lower recovery and availability will result in following lower TL. Furthermore, we found that TL negatively affects recovery (r = 0.52, p < 0.001) and availability (r = 0.39, p < 0.01) of the next day (lag = 1 day). In fact, the higher the TL in a current day is, the lower the recovery and availability in the next day will be.

Conclusion

In conclusion, this study highlights that there is a relationship between TL and recovery and that these components influence each other both on the same day and on the next one. The use of RPE and TreS scale to evaluate TL and recovery/availability of players allows practitioners to better adjust and schedule training within the microcycle to enhance performance while reducing injury risk.

Predicting Severity of Head Collision Events in Elite Soccer Using Preinjury Data: A Machine Learning Approach

OBJECTIVE

To develop machine learning (ML) models that predict severity of head collision events (HCEs) based on preinjury variables and to investigate which variables are important to predicting severity.

DESIGN

Data on HCEs were collected with respect to severity and 23 preinjury variables to create 2 datasets, a male dataset using men's tournaments and mixed dataset using men's and women's tournaments, to perform ML analysis. Machine learning analysis used a random forest classifier based on preinjury variables to predict HCE severity.

SETTING

Four elite international soccer tournaments.

PARTICIPANTS

Elite athletes participating in analyzed tournaments.

INDEPENDENT VARIABLES

The 23 preinjury variables collected for each HCE.

MAIN OUTCOME MEASURES

Predictive ability of the ML models and association of important variables.

RESULTS

The ML models had an average area under the receiver operating characteristic curve for predicting HCE severity of 0.73 and 0.70 for the male and mixed datasets, respectively. The most important variables for prediction were the mechanism of injury and the event before injury. In the male dataset, the mechanisms "head-to-head" and "knee-to-head" were together significantly associated ( P = 0.0244) with severity; they were not significant in the mixed dataset ( P = 0.1113). In both datasets, the events "corner kicks" and "throw-ins" were together significantly associated with severity (male, P = 0.0001; mixed, P = 0.0004).

CONCLUSIONS

ML models accurately predicted the severity of HCE. The mechanism and event preceding injury were most important for predicting severity of HCEs. These findings support the use of ML to inform preventative measures that will mitigate the impact of these preinjury factors on player health.

External load profile during different sport-specific activities in semi-professional soccer players

BACKGROUND

Global Positioning System (GPS) devices are widely used in soccer for monitoring external load (EL) indicators with the aim of maximizing sports performance.The aim of this study was to investigate the EL indicators differences in players of different playing positions (i.e., central backs, external strikers, fullbacks, midfielders, strikers, wide midfielder) between and within different sport-specific tasks and official matches.

METHODS

1932 observations from 28 semi-professional soccer players (age: 25 ± 6 years, height: 183 ± 6 cm, weight: 75.2 ± 7 kg) were collected through GPS devices (Qstarz BT-Q1000EX, 10 Hz) during the season 2019-2020. Participants were monitored during Official Match (OM), Friendly Matches (FM), Small Sided Games (SSG), and Match-Based Exercises (MBE). Metabolic (i.e., metabolic power, percentage of metabolic power > 35w, number of intense actions per minute, distance per minute, passive recovery time per minute) and neuromuscular indicators (i.e., percentage of intense accelerations, percentage of intense decelerations, change of direction per min > 30°) were recorded during each task.

RESULTS

Statistically significant differences were detected in EL indicators between playing positions within each task and between tasks. In particular, results from the two-way ANOVA tests showed significant interaction, but with small effect size, in all the EL indicators between playing positions for each task and within tasks. Moreover, statistical differences, but with small effect size, between playing positions were detected in each task and for each EL indicator. Finally, the strongest statistical differences (with large effect size) were detected between tasks for each EL indicator. Details of the Tukey post-hoc analysis reporting the pairwise comparisons within and between tasks with playing positions are also provided.

CONCLUSION

In semi-professional soccer players, different metabolic and neuromuscular performance were detected in different playing position between and within different tasks and official matches. Coaches should consider the different physical responses related to different physical tasks and playing position to design the most appropriate training program.

Match Load Physical Demands in U-19 Professional Soccer Players Assessed by a Wearable Inertial Sensor

BACKGROUND

Wearable inertial sensors are poorly used in soccer to monitor external load (EL) indicators. However, these devices could be useful for improving sports performance and potentially reducing the risk of injury. The aim of this study was to investigate the EL indicators (i.e., cinematic, mechanical, and metabolic) differences between playing positions (i.e., central backs, external strikers, fullbacks, midfielders, and wide midfielder) during the first half time of four official matches (OMs).

METHODS

13 young professional soccer players (Under-19; age: 18.5 ± 0.4 years; height: 177 ± 6 cm; weight: 67 ± 4.8 kg) were monitored through a wearable inertial sensor (TalentPlayers TPDev, firmware version 1.3) during the season 2021-2022. Participants' EL indicators were recorded during the first half time of four OMs.

RESULTS

significant differences were detected in all the EL indicators between playing positions except for two of them (i.e., distance traveled in the various metabolic power zones (<10 w) and the number of direction changes to the right >30° and with speed >2 m). Pairwise comparisons showed differences in EL indicators between playing positions.

CONCLUSIONS

Young professional soccer players showed different loads and performances during OMs in relation to playing positions. Coaches should consider the different physical demands related to playing positions in order to design the most appropriate training program.

The Influence of Physical Contact on Athlete Load in International Female Rugby Sevens

ABSTRACT

Epp-Stobbe, A, Tsai, M-C, Morris, C, and Klimstra, M. The influence of physical contact on athlete load in international female rugby sevens. J Strength Cond Res 37(2): 383-387, 2023-Although self-reported rate of perceived exertion (RPE) is a simple and popular metric for monitoring player loads, this holistic measure may not adequately represent the distinct contributing factors to athlete loading in team sports, such as contact load. The purpose of this investigation is to determine the relationship between the number of contacts experienced and playing time on RPE in elite women's rugby sevens athletes during competition. Additionally, we examine the contribution of the number of contacts and playing time to RPE. The data collected included RPE, playing time, and number of contacts from 1 team participating in 74 international women's sevens matches. The relationship was modeled using multiple linear regression. Results, including the coefficients for the number of contacts and playing time, were significant (p < 0.001), and R2adjusted was 0.3063. Because contacts are accounted for within the measure of RPE in the proposed model, this further supports the value of RPE as a global measure of athlete experience. However, this study has found a different relationship between RPE and playing time dependent on the number of contacts, such that the influence of playing time on RPE decreases as the number of contacts increase. Ultimately, this may mean that the weighting of individual salient factors affecting player loads, such as the number of contacts or playing time, depend on the levels of all known and potentially unknown factors experienced and may limit the use of RPE when contextualizing player load across athletes. Taken together, the findings suggest that the number of contacts, playing time, and RPE should be considered when monitoring athlete loads while further substantiating the need for more, and higher resolution, measures to better quantify competition loads in contact team sports.

Perspective on "in the wild" movement analysis using machine learning

Recent advances in wearable sensing and machine learning have created ample opportunities for "in the wild" movement analysis in sports, since the combination of both enables real-time feedback to be provided to athletes and coaches, as well as long-term monitoring of movements. The potential for real-time feedback is useful for performance enhancement or technique analysis, and can be achieved by training efficient models and implementing them on dedicated hardware. Long-term monitoring of movement can be used for injury prevention, among others. Such applications are often enabled by training a machine learned model from large datasets that have been collected using wearable sensors. Therefore, in this perspective paper, we provide an overview of approaches for studies that aim to analyze sports movement "in the wild" using wearable sensors and machine learning. First, we discuss how a measurement protocol can be set up by answering six questions. Then, we discuss the benefits and pitfalls and provide recommendations for effective training of machine learning models from movement data, focusing on data pre-processing, feature calculation, and model selection and tuning. Finally, we highlight two application domains where "in the wild" data recording was combined with machine learning for injury prevention and technique analysis, respectively.

Predicting Injuries in Football Based on Data Collected from GPS-Based Wearable Sensors

The growing intensity and frequency of matches in professional football leagues are related to the increasing physical player load. An incorrect training model results in over- or undertraining, which is related to a raised probability of an injury. This research focuses on predicting non-contact lower body injuries coming from over- or undertraining. The purpose of this analysis was to create decision-making models based on data collected during both training and match, which will enable the preparation of a tool to model the load and report the increased risk of injury for a given player in the upcoming microcycle. For this purpose, three decision-making methods were implemented. Rule-based and fuzzy rule-based methods were prepared based on expert understanding. As a machine learning baseline XGBoost algorithm was considered. Taking into account the dataset used containing parameters related to the external load of the player, it is possible to predict the risk of injury with a certain precision, depending on the method used. The most promising results were achieved by the machine learning method XGBoost algorithm (Precision 92.4%, Recall 96.5%, and F1-score 94.4%).

Weekly External Load Performance Effects on Sports Injuries of Male Professional Football Players

One of the most challenging issues professional football players face throughout their careers is injuries. Those injuries often result from suboptimal training programs that were not designed according to the players' individual needs. This prospective study aimed to examine in detail the effects of sports injuries on professional football players' weekly external load performances. Thirty-three male professional football players were monitored using 10-Hz Global Positioning System (GPS) units (Apex pro series, StatSports) during an entire season. The variables considered in the analysis were total distance (TD), high-speed running (HSR), accelerations (ACC), and decelerations (DEC). The comparisons were made between the four-week block before injury (-4T), four-week block after return (+4T), and players' season averages (S). Players displayed significantly higher values of TD, HSR, ACC, and DEC in the -4T, compared to the other two moments (+4T and S). Furthermore, the comparison between the +4T and S showed no significant variations in the GPS metrics. It was shown that a significant increase in players' weekly external load performance over a four-week period may have a negative effect on the occurrence of injuries from a professional football standpoint. Future research should consider the effects of injury severity on players' external load variations.

Relationships between RPE-derived internal training load parameters and GPS-based external training load variables in elite young soccer players

This study aimed to identify the GPS-based external training load variables that influence the internal training loads (RPE-derived parameters: RPE and session RPE - sRPE), and generate a model to predict GPS-based external load variables from RPE and perceived wellness values. Training load data for 21 elite young players were collected over 72 training sessions and 23 matches from the same competitive season, and 564 observations (training sessions, 462; matches, 102) were analysed. Considering all observations (training sessions and matches), significant moderate and large correlations (p < 0.01) were detected between RPE values and EL measures. The correlation between the GPS outcomes with both the RPE and sRPE values was higher during training sessions than during matches. Moreover, increased RPE and perceived wellness measures had a significant positive effect on external load variables (p < 0.001). The present work provides preliminary evidence of the utility of the RPE and sRPE method to quantify the training loads in young soccer players since most of the GPS-based EL indicators were moderate to highly correlated with the RPE-derived parameters. Additionally, EL variables may be estimated when combining perceived IL and subjective wellness indicators in young soccer players.

From 2D projections to the 3D rotation matrix: an attempt for finding a machine learning approach for the efficient evaluation of mechanical joining elements in X-ray computed tomography volume data

Destructive and predominantly manual procedures are commonly used in the automotive industry for the testing of mechanical joints, such as rivets or screws. Combining X-ray computed tomography (CT) and machine learning (ML) bears the potential of a non-destructive and largely automated methodology. Assuming the desired result is a comprehensible and documentable evaluation, three basic steps need to be automatized: First, a joint must be detected and identified as such in a CT scan of the joined parts. Second, the detected region containing the joint is rotated to a predefined orientation. Third, key measures in cross-sections from the newly oriented joint are dimensioned and documented. This work deals only with the second step, the rotation. On the one hand, we present a methodology for creating a well-curated data set for the contextual machine learning application. On the other, we evaluate its performance on the well-known ResNet50. More concretely, we investigate if it is possible for a deep convolutional neural network (CNN) to learn the respective rotation matrix from three volume projections that are perpendicular to each other. Two scenarios are investigated: In one scenario we assume that future data that is presented to the network has similar rivet demographics to historic data. We therefore do not employ hold-out sets for the network evaluation. In the other scenario we assume the opposite and therefore evaluating the networks performance with hold-out sets. We show that from a machine learning point of view, a CNN like ResNet50 is well able to learn this relationship with acceptable accuracy. In most cases the validation loss dropped below 0.1 after only a couple of epochs. In one particular case, we even reached both mean and median errors lower than 0.2 for approximately 80% of the entire test set of 1600 examples using our methodology. From an application point of view, however, these low test set errors should be treated with caution since small deviations from the intended rotation matrix can cause volume warping and translation. In another case, in which we used a hold-out set, only a fraction of the median errors were below 0.2.

Machine learning application in soccer: a systematic review

Due to the chaotic nature of soccer, the predictive statistical models have become in a current challenge to decision-making based on scientific evidence. The aim of the present study was to systematically identify original studies that applied machine learning (ML) to soccer data, highlighting current possibilities in ML and future applications. A systematic review of PubMed, SPORTDiscus, and FECYT (Web of Sciences, CCC, DIIDW, KJD, MEDLINE, RSCI, and SCIELO) was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. From the 145 studies initially identified, 32 were fully reviewed, and their outcome measures were extracted and analyzed. In summary, all articles were clustered into three groups: injury (n = 7); performance (n = 21), which was classified in match/league outcomes forecasting, physical/physiological forecasting, and technical/tactical forecasting; and the last group was about talent forecasting (n = 5). The development of technology, and subsequently the large amount of data available, has become ML in an important strategy to help team staff members in decision-making predicting dose-response relationship reducing the chaotic nature of this team sport. However, since ML models depend upon the amount of dataset, further studies should analyze the amount of data input needed make to a relevant predictive attempt which makes accurate predicting available.

Statistical injury prediction for professional sumo wrestlers: Modeling and perspectives

In sumo wrestling, a traditional sport in Japan, many wrestlers suffer from injuries through bouts. In 2019, an average of 5.2 out of 42 wrestlers in the top division of professional sumo wrestling were absent in each grand sumo tournament due to injury. As the number of injury occurrences increases, professional sumo wrestling becomes less interesting for sumo fans, requiring systems to prevent future occurrences. Statistical injury prediction is a useful way to communicate the risk of injuries for wrestlers and their coaches. However, the existing statistical methods of injury prediction are not always accurate because they do not consider the long-term effects of injuries. Here, we propose a statistical model of injury occurrences for sumo wrestlers. The proposed model provides the estimated probability of the next potential injury occurrence for a wrestler. In addition, it can support making a risk-based injury prevention scenario for wrestlers. While a previous study modeled injury occurrences by using the Poisson process, we model it by using the Hawkes process to consider the long-term effect of injuries. The proposed model can also be applied to injury prediction for athletes of other sports.

A review of machine learning applications in soccer with an emphasis on injury risk

This narrative review paper aimed to discuss the literature on machine learning applications in soccer with an emphasis on injury risk assessment. A secondary aim was to provide practical tips for the health and performance staff in soccer clubs on how machine learning can provide a competitive advantage. Performance analysis is the area with the majority of research so far. Other domains of soccer science and medicine with machine learning use are injury risk assessment, players' workload and wellness monitoring, movement analysis, players' career trajectory, club performance, and match attendance. Regarding injuries, which is a hot topic, machine learning does not seem to have a high predictive ability at the moment (models specificity ranged from 74.2%-97.7%. sensitivity from 15.2%-55.6% with area under the curve of 0.66-0.83). It seems, though, that machine learning can help to identify the early signs of elevated risk for a musculoskeletal injury. Future research should account for musculoskeletal injuries' dynamic nature for machine learning to provide more meaningful results for practitioners in soccer.

The effects of scheduling network models in predictive processes in sports

In many sports disciplines, the schedule of the competitions is undeniably an inherent yet crucial component. The present study modeled sports competitions schedules as networks and investigated the influence of network properties on the accuracy of predictive ratings and forecasting models in sports. Artificial networks were generated representing competition schedules with varying density, degree distribution and modularity and embedded in a full rating and forecasting process using ELO ratings and an ordered logistic regression model. Results showed that network properties should be considered when tuning predictive ratings and revealed several aspects for improvement. High density does not increase rating accuracy, so improved rating approaches should increasingly use indirect comparisons to profit from transitivity in dense networks. In networks with a high disparity in their degree distribution, inaccuracies are mainly driven by nodes with a low degree, which could be improved by relaxing the rating adjustment functions. Moreover, in terms of modularity, low connectivity between groups (i.e., leagues or divisions) challenges correctly assessing a single group’s overall rating. The present study aims to stimulate discussion on network properties as a neglected facet of sports forecasting and artificial data to improve predictive ratings.

Cloud-based deep learning-assisted system for diagnosis of sports injuries

At both clinical and diagnostic levels, machine learning technologies could help facilitate medical decision-making. Prediction of sports injuries, for instance, is a key component of avoiding and minimizing injury in motion. Despite significant attempts to forecast sports injuries, the present method is limited by its inability to identify predictors. When designing measures for the avoidance of work-related accidents and the reduction of associated risks, the risk of injury to athletes is a crucial consideration. Various indicators are being evaluated to identify injury risk factors in a number of different methods. Consequently, this paper proposes a Deep Learning-assisted System (DLS) for diagnosing sports injuries using the Internet of Things (IoT) and the concept of cloud computing. The IoT sensors that compose the body area network collect crucial data for the diagnosis of sports injuries, while cloud computing makes available flexible computer system resources and computing power. This research examines the brain injury monitoring framework, uses an optimal neural network to forecast brain injury, and enhances the medical rehabilitation system for sports. Using the metrics accuracy, precision, recall, and F1-score, the performance of the proposed model is assessed and compared with current models.

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.

Using global navigation satellite systems for modeling athletic performances in elite football players

This study aims to predict individual Acceleration-Velocity profiles (A-V) from Global Navigation Satellite System (GNSS) measurements in real-world situations. Data were collected from professional players in the Superleague division during a 1.5 season period (2019–2021). A baseline modeling performance was provided by time-series forecasting methods and compared with two multivariate modeling approaches using ridge regularisation and long short term memory neural networks. The multivariate models considered commercial features and new features extracted from GNSS raw data as predictor variables. A control condition in which profiles were predicted from predictors of the same session outlined the predictability of A-V profiles. Multivariate models were fitted either per player or over the group of players. Predictor variables were pooled according to the mean or an exponential weighting function. As expected, the control condition provided lower error rates than other models on average (p = 0.001). Reference and multivariate models did not show significant differences in error rates (p = 0.124), regardless of the nature of predictors (commercial features or extracted from signal processing methods) or the pooling method used. In addition, models built over a larger population did not provide significantly more accurate predictions. In conclusion, GNSS features seemed to be of limited relevance for predicting individual A-V profiles. However, new signal processing features open up new perspectives in athletic performance or injury occurrence modeling, mainly if higher sampling rate tracking systems are considered.

Machine-learned-based prediction of lower extremity overuse injuries using pressure plates

Although running has many benefits for both the physical and mental health, it also involves the risk of injuries which results in negative physical, psychological and economical consequences. Those injuries are often linked to specific running biomechanical parameters such as the pressure pattern of the foot while running, and they could potentially be indicative for future injuries. Previous studies focus solely on some specific type of running injury and are often only applicable to a gender or running-experience specific population. The purpose of this study is, for both male and female, first-year students, (i) to predict the development of a lower extremity overuse injury in the next 6 months based on foot pressure measurements from a pressure plate and (ii) to identify the predictive loading features. For the first objective, we developed a machine learning pipeline that analyzes foot pressure measurements and predicts whether a lower extremity overuse injury is likely to occur with an AUC of 0.639 and a Brier score of 0.201. For the second objective, we found that the higher pressures exerted on the forefoot are the most predictive for lower extremity overuse injuries and that foot areas from both the lateral and the medial side are needed. Furthermore, there are two kinds of predictive features: the angle of the FFT coefficients and the coefficients of the autoregressive AR process. However, these features are not interpretable in terms of the running biomechanics, limiting its practical use for injury prevention.

Predicting ACL Injury Using Machine Learning on Data From an Extensive Screening Test Battery of 880 Female Elite Athletes

BACKGROUND

Injury risk prediction is an emerging field in which more research is needed to recognize the best practices for accurate injury risk assessment. Important issues related to predictive machine learning need to be considered, for example, to avoid overinterpreting the observed prediction performance.

PURPOSE

To carefully investigate the predictive potential of multiple predictive machine learning methods on a large set of risk factor data for anterior cruciate ligament (ACL) injury; the proposed approach takes into account the effect of chance and random variations in prediction performance.

STUDY DESIGN

Case-control study; Level of evidence, 3.

METHODS

The authors used 3-dimensional motion analysis and physical data collected from 791 female elite handball and soccer players. Four common classifiers were used to predict ACL injuries (n = 60). Area under the receiver operating characteristic curve (AUC-ROC) averaged across 100 cross-validation runs (mean AUC-ROC) was used as a performance metric. Results were confirmed with repeated permutation tests (paired Wilcoxon signed-rank-test; P < .05). Additionally, the effect of the most common class imbalance handling techniques was evaluated.

RESULTS

For the best classifier (linear support vector machine), the mean AUC-ROC was 0.63. Regardless of the classifier, the results were significantly better than chance, confirming the predictive ability of the data and methods used. AUC-ROC values varied substantially across repetitions and methods (0.51-0.69). Class imbalance handling did not improve the results.

CONCLUSION

The authors' approach and data showed statistically significant predictive ability, indicating that there exists information in this prospective data set that may be valuable for understanding injury causation. However, the predictive ability remained low from the perspective of clinical assessment, suggesting that included variables cannot be used for ACL prediction in practice.

Predictive Modeling of Injury Risk Based on Body Composition and Selected Physical Fitness Tests for Elite Football Players

Injuries are one of the most significant issues for elite football players. Consequently, elite football clubs have been consistently interested in having practical, interpretable, and usable models as decision-making support for technical staff. This study aimed to analyze predictive modeling of injury risk based on body composition variables and selected physical fitness tests for elite football players through a sports season. The sample comprised 36 male elite football players who competed in the First Portuguese Soccer League in the 2020/2021 season. The models were calculated based on 22 independent variables that included players' information, body composition, physical fitness, and one dependent variable, the number of injuries per season. In the net elastic analysis, the variables that best predicted injury risk were sectorial positions (defensive and forward), body height, sit-and-reach performance, 1 min number of push-ups, handgrip strength, and 35 m linear speed. This study considered multiple-input single-output regression-type models. The analysis showed that the most accurate model presented in this work generates an error of RMSE = 0.591. Our approach opens a novel perspective for injury prevention and training monitorization. Nevertheless, more studies are needed to identify risk factors associated with injury prediction in elite soccer players, as this is a rising topic that requires several analyses performed in different contexts.

Forecasting football injuries by combining screening, monitoring and machine learning

Identifying players or circumstances associated with an increased risk of injury is fundamental for successful risk management in football. So far, time-constant and volatile risk factors are generally considered separately in either a screening (constant) or a monitoring (volatile) approach each resulting in a restricted set of explanatory variables. Consequently, improvements in predictive accuracy may be expected when screening and monitoring data are combined, especially when analysed with current machine learning (ML) techniques. This trial was designed as a prospective observational cohort study aiming to forecast non-contact time-loss injuries in male professional football (soccer). Injuries were registered according to the Fuller consensus. Gradient boosting with ROSE upsampling within a leave-one-out cross-validation was used for data analysis. The hierarchical data structure was considered throughout. Different splits of the original dataset were used to probe the robustness of results. Data of 88 players from 4 teams and 51 injuries could be analysed. The cross-validated performance of the gradient boosted model (ROC area under the curve 0.61) was promising and higher compared to models without integration of screening data. Importantly, holdout test set performance was similar (ROC area under the curve 0.62) indicating prospect of generalizability to new cases. However, the variation of predictive accuracy and feature importance with different splits of the original dataset reflects the relatively low number of events. It is concluded that ML-based injury forecasting based on the integration of screening and monitoring data is promising. However, external prospective verification and continued model development are required.

Wellness Forecasting by External and Internal Workloads in Elite Soccer Players: A Machine Learning Approach

Training for success has increasingly become a balance between maintaining high performance standards and avoiding the negative consequences of accumulated fatigue. The aim of this study is to develop a big data analytics framework to predict players’ wellness according to the external and internal workloads performed in previous days. Such a framework is useful for coaches and staff to simulate the players’ response to scheduled training in order to adapt the training stimulus to the players’ fatigue response. 17 players competing in the Italian championship (Serie A) were recruited for this study. Players’ Global Position System (GPS) data was recorded during each training and match. Moreover, every morning each player has filled in a questionnaire about their perceived wellness (WI) that consists of a 7-point Likert scale for 4 items (fatigue, sleep, stress, and muscle soreness). Finally, the rate of perceived exertion (RPE) was used to assess the effort performed by the players after each training or match. The main findings of this study are that it is possible to accurately estimate players’ WI considering their workload history as input. The machine learning framework proposed in this study is useful for sports scientists, athletic trainers, and coaches to maximise the periodization of the training based on the physiological requests of a specific period of the season.

Just How Confident Can We Be in Predicting Sports Injuries? A Systematic Review of the Methodological Conduct and Performance of Existing Musculoskeletal Injury Prediction Models in Sport

BACKGROUND

An increasing number of musculoskeletal injury prediction models are being developed and implemented in sports medicine. Prediction model quality needs to be evaluated so clinicians can be informed of their potential usefulness.

OBJECTIVE

To evaluate the methodological conduct and completeness of reporting of musculoskeletal injury prediction models in sport.

METHODS

A systematic review was performed from inception to June 2021. Studies were included if they: (1) predicted sport injury; (2) used regression, machine learning, or deep learning models; (3) were written in English; (4) were peer reviewed.

RESULTS

Thirty studies (204 models) were included; 60% of studies utilized only regression methods, 13% only machine learning, and 27% both regression and machine learning approaches. All studies developed a prediction model and no studies externally validated a prediction model. Two percent of models (7% of studies) were low risk of bias and 98% of models (93% of studies) were high or unclear risk of bias. Three studies (10%) performed an a priori sample size calculation; 14 (47%) performed internal validation. Nineteen studies (63%) reported discrimination and two (7%) reported calibration. Four studies (13%) reported model equations for statistical predictions and no machine learning studies reported code or hyperparameters.

CONCLUSION

Existing sport musculoskeletal injury prediction models were poorly developed and have a high risk of bias. No models could be recommended for use in practice. The majority of models were developed with small sample sizes, had inadequate assessment of model performance, and were poorly reported. To create clinically useful sports musculoskeletal injury prediction models, considerable improvements in methodology and reporting are urgently required.

Machine Learning for Understanding and Predicting Injuries in Football

Attempts to better understand the relationship between training and competition load and injury in football are essential for helping to understand adaptation to training programmes, assessing fatigue and recovery, and minimising the risk of injury and illness. To this end, technological advancements have enabled the collection of multiple points of data for use in analysis and injury prediction. The full breadth of available data has, however, only recently begun to be explored using suitable statistical methods. Advances in automatic and interactive data analysis with the help of machine learning are now being used to better establish the intricacies of the player load and injury relationship. In this article, we examine this recent research, describing the analyses and algorithms used, reporting the key findings, and comparing model fit. To date, the vast array of variables used in analysis as proxy indicators of player load, alongside differences in approach to key aspects of data treatment-such as response to data imbalance, model fitting, and a lack of multi-season data-limit a systematic evaluation of findings and the drawing of a unified conclusion. If, however, the limitations of current studies can be addressed, machine learning has much to offer the field and could in future provide solutions to the training load and injury paradox through enhanced and systematic analysis of athlete data.

Blood sample profile helps to injury forecasting in elite soccer players

Purpose

By analyzing external workloads with machine learning models (ML), it is now possible to predict injuries, but with a moderate accuracy. The increment of the prediction ability is nowadays mandatory to reduce the high number of false positives. The aim of this study was to investigate if players’ blood sample profiles could increase the predictive ability of the models trained only on external training workloads.

Method

Eighteen elite soccer players competing in Italian league (Serie B) during the seasons 2017/2018 and 2018/2019 took part in this study. Players’ blood samples parameters (i.e., Hematocrit, Hemoglobin, number of red blood cells, ferritin, and sideremia) were recorded through the two soccer seasons to group them into two main groups using a non-supervised ML algorithm (k-means). Additionally to external workloads data recorded every training or match day using a GPS device (K-GPS 10 Hz, K-Sport International, Italy), this grouping was used as a predictor for injury risk. The goodness of ML models trained were tested to assess the influence of blood sample profile to injury prediction.

Results

Hematocrit, Hemoglobin, number of red blood cells, testosterone, and ferritin were the most important features that allowed to profile players and to analyze the response to external workloads for each type of player profile. Players’ blood samples’ characteristics permitted to personalize the decision-making rules of the ML models based on external workloads reaching an accuracy of 63%. This approach increased the injury prediction ability of about 15% compared to models that take into consideration only training workloads’ features. The influence of each external workload varied in accordance with the players’ blood sample characteristics and the physiological demands of a specific period of the season.

Conclusion

Field experts should hence not only monitor the external workloads to assess the status of the players, but additional information derived from individuals’ characteristics permits to have a more complete overview of the players well-being. In this way, coaches could better personalize the training program maximizing the training effect and minimizing the injury risk.

The demands of the extra-time period of soccer: A systematic review

OBJECTIVE

Soccer match-play is typically contested over 90 min; however, in some cup and tournament scenarios, when matches are tied, they proceed to an additional 30 min, which is termed "extra-time" (ET). This systematic review sought to appraise the literature available on 120-min of soccer-specific exercise, with a view to identifying practical recommendations and future research opportunities.

METHODS

The review was conducted according to the PRISMA guidelines. Independent researchers performed a systematic search of PubMed, CINAHL, and PsycINFO in May 2019, with the following keywords entered in various combinations: "soccer", "football", "extra-time", "extra time", "extratime", "120 minutes", "120 min", "additional 30 minutes", and "additional 30 min".

RESULTS

The search yielded an initial 73 articles. Following the screening process, 11 articles were accepted for analyses. Articles were subsequently organized into the following 5 categories: movement demands of ET, performance responses to ET, physiological and neuromuscular response during ET, nutritional interventions, and recovery and ET. The results highlighted that during competitive match-play, players cover 5%-12% less distance relative to match duration (i.e., meters per minute) during ET compared to the preceding 90 min. Reductions in technical performance (i.e., shot speed, number of passes and dribbles) were also observed during ET. Additionally, carbohydrate provision may attenuate and improve dribbling performance during ET. Moreover, objective and subjective measures of recovery may be further compromised following ET when compared to 90 min.

CONCLUSION

Additional investigations are warranted to further substantiate these findings and identify interventions to improve performance during ET.

Impact of Gender and Feature Set on Machine-Learning-Based Prediction of Lower-Limb Overuse Injuries Using a Single Trunk-Mounted Accelerometer

Even though practicing sports has great health benefits, it also entails a risk of developing overuse injuries, which can elicit a negative impact on physical, mental, and financial health. Being able to predict the risk of an overuse injury arising is of widespread interest because this may play a vital role in preventing its occurrence. In this paper, we present a machine learning model trained to predict the occurrence of a lower-limb overuse injury (LLOI). This model was trained and evaluated using data from a three-dimensional accelerometer on the lower back, collected during a Cooper test performed by 161 first-year undergraduate students of a movement science program. In this study, gender-specific models performed better than mixed-gender models. The estimated area under the receiving operating characteristic curve of the best-performing male- and female-specific models, trained according to the presented approach, was, respectively, 0.615 and 0.645. In addition, the best-performing models were achieved by combining statistical and sports-specific features. Overall, the results demonstrated that a machine learning injury prediction model is a promising, yet challenging approach.

Characteristics of Complex Systems in Sports Injury Rehabilitation: Examples and Implications for Practice

Complex systems are open systems consisting of many components that can interact among themselves and the environment. New forms of behaviours and patterns often emerge as a result. There is a growing recognition that most sporting environments are complex adaptive systems. This acknowledgement extends to sports injury and is reflected in the individual responses of athletes to both injury and rehabilitation protocols. Consequently, practitioners involved in return to sport decision making (RTS) are encouraged to view return to sport decisions through the complex systems lens to improve decision-making in rehabilitation. It is important to clarify the characteristics of this theoretical framework and provide concrete examples to which practitioners can easily relate. This review builds on previous literature by providing an overview of the hallmark features of complex systems and their relevance to RTS research and daily practice. An example of how characteristics of complex systems are exhibited is provided through a case of anterior cruciate ligament injury rehabilitation. Alternative forms of scientific inquiry, such as the use of computational and simulation-based techniques, are also discussed-to move the complex systems approach from the theoretical to the practical level.