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

Machine learning approaches to injury risk prediction in sport: a scoping review with evidence synthesis

OBJECTIVE

This study reviewed the current state of machine learning (ML) research for the prediction of sports-related injuries. It aimed to chart the various approaches used and assess their efficacy, considering factors such as data heterogeneity, model specificity and contextual factors when developing predictive models.

DESIGN

Scoping review.

DATA SOURCES

PubMed, EMBASE, SportDiscus and IEEEXplore.

RESULTS

In total, 1241 studies were identified, 58 full texts were screened, and 38 relevant studies were reviewed and charted. Football (soccer) was the most commonly investigated sport. Area under the curve (AUC) was the most common means of model evaluation; it was reported in 71% of studies. In 60% of studies, tree-based solutions provided the highest statistical predictive performance. Random Forest and Extreme Gradient Boosting (XGBoost) were found to provide the highest performance for injury risk prediction. Logistic regression outperformed ML methods in 4 out of 12 studies. Three studies reported model performance of AUC>0.9, yet the clinical relevance is questionable.

CONCLUSIONS

A variety of different ML models have been applied to the prediction of sports-related injuries. While several studies report strong predictive performance, their clinical utility can be limited, with wide prediction windows or broad definitions of injury. The efficacy of ML is hampered by small datasets and numerous methodological heterogeneities (cohort sizes, definition of injury and dependent variables), which were common across the reviewed studies.

Predictive models of injury risk in male professional football players: a systematic review

BACKGROUND

One of the challenges for professional football players is injuries. Due to their influence on their teams, injuries greatly impact the sports business. This research aims to assess predictive models of injury risk in male professional football players.

METHODS

A systematic literature review was performed, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The search was conducted in the PubMed, Web of Science and Scopus databases. Two independent reviewers screened articles, assessed eligibility and extracted data. Methodological quality was determined by the Newcastle-Ottawa Scale.

RESULTS

26 studies met the inclusion criteria.

DISCUSSION

Various statistical techniques were used in research on injury prediction in professional football, with logistic regression being the most used. The assessment predictors, especially the area under the receiver operating characteristic Curve, showed significant variation, which indicates the prediction models' efficacy. The focus was frequently on lower limb injuries, where several risk predictors, including muscular strength, flexibility and global positioning system-derived data, were found to substantially impact the occurrence of injuries. Prominent predictors included age, position, physiological parameters, injury history and genetic polymorphisms.

CONCLUSIONS

This comprehensive analysis highlights the complexity of injury prediction and reinforces the necessity for football injury research to adopt a multivariate approach with accuracy and comprehensiveness.

PROSPERO REGISTRATION NUMBER

CRD42023465524.

The Influence of Futsal Players' Initial Physical Condition on the Occurrence of Injuries

Although there are some studies that have linked fitness parameters and sports injuries, the literature remains controversial. The aim of the study was to prospectively analyze the influence of initial physical condition parameters on the development of injury in the first three months of the sports season in futsal players. A total of 68 players (24.26±4.63 years old) were assessed before the start of the sports season in relation to certain physical condition parameters, such as body composition (bioimpedance), lower limb power (countermovement jump, CMJ) and muscle strength (isokinetic dynamometer). The injured players showed significantly worse initial performance in the CMJ compared to the uninjured players (p<0.001). There were no significant differences between groups in body composition and muscle strength. Lower power values were associated with a higher risk of injury in the first few months of the sports season (OR=0.92; 95% CI=0.88-0.99). Muscle power was an independent predictor of injury in the first few months of the sports season in futsal players, indicating that improving players' physical condition could help reduce the number of injuries.

The Impact of Heat Exposure on the Health and Performance of Soccer Players: A Narrative Review and Bibliometric Analysis

The impact of heat exposure on the health and performance of soccer players is a widely discussed topic. The purpose of this study is to provide a comprehensive overview of the international literature that has addressed this issue. To achieve this objective, we initially conducted a bibliometric analysis and a literature review of the main topics that emerged through bibliometric techniques. For the bibliometric analysis, we employed VOSviewer software (version 1.6.20.0) and used documents found in the Scopus database. The analysis ultimately included 133 documents published in 66 sources. Key journals and authors were identified, highlighting significant contributions to the field. Science mapping revealed collaboration networks and research focus areas such as physical health, safety, soccer performance, dehydration and hydration, physiological mechanisms and monitoring, nutrition, fluid intake, and cooling techniques. Based on the key areas highlighted in the identified clusters, which emerged from the co-occurrence analysis of the author keywords, the following three topics were developed in the literature review: (a) the physiology and health of football players; (b) performance impacts; and (c) strategies to prevent negative consequences. The review showed that high heat exposure can reduce the physical and cognitive performance of athletes and prove detrimental to their health. To mitigate the negative consequences, appropriate hydration strategies, heat acclimatization, and cooling techniques have been proposed. Our findings provide the international scientific community with comprehensive knowledge of the existing literature, laying the foundation for future research while simultaneously offering coaches and athletes the necessary theoretical knowledge to help improve safety and performance.

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.

The Effects of Pre-Season and Relationships with Physical, Physiological, Body Composition, and Load Markers: A Case Study Comparing Starters versus Non-Starters from an Elite Female Professional Soccer Team

Background and Objectives: Research on female soccer players that analyzes playing status is scarce and has previously only examined load monitoring, while other markers, such as physical (i.e., strength, power, and agility), physiological (i.e., maximal oxygen uptake), and body composition (i.e., body fat mass, fat-free mass, body water, and phase angle) markers, warrant further investigation. Thus, the study aims were to (a) compare physical, physiological, body composition, and load markers between starters and non-starters; (b) compare measurements pre- and post-training intervention (five weeks); and (c) analyze any relationships between physical, physiological, body composition, and load markers in an elite female soccer team. Materials and Methods: Fourteen first-team players participated in the study (age 23.29 ± 3.19 years, weight 59.14 ± 6.87 kg, height 1.66 ± 0.08 m). Several physical (n = 15), physiological (n = 1), body composition (n = 11), and load markers (n = 14) were collected. In addition, participants were sub-divided into starters (n = 7) and non-starters (n = 7). Results: No differences were revealed between starters and non-starters in any of the examined variables. Moreover, following the training intervention, a significantly lower value was found for total body water/fat-free mass ratio (p = 0.043; ES = 0.582). In addition, there were several correlations detected between load and physical/physiological markers (n = 28); load and body composition markers (n = 6); physical/physiological and body composition markers (n = 34); and physical and physiological markers (n = 42). Conclusions: In conclusion, only a slight tendency of higher load values for starters than non-starters was observed. In addition, no differences in physical, physiological, and body composition markers were found between starters and non-starters, possibly suggesting that five weeks were not enough to improve such variables. Finally, the present results provide novel information assessing the effects of the pre-season in elite female Portuguese soccer players and contribute to a better understanding of the associations between different types of measurements.

Advancements in Sports Medicine

Sports medicine has developed rapidly in recent years [...].

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.

Sports Injuries of a Portuguese Professional Football Team during Three Consecutive Seasons

Professional football players are exposed to high injury risk due to the physical demands of this sport. The purpose of this study was to characterize the injuries of a professional football team in the First Portuguese League over three consecutive sports seasons. Seventy-one male professional football players in the First Portuguese Football League were followed throughout the sports seasons of 2019/2020, 2020/2021, and 2021/2022. In total, 84 injuries were recorded. Each player missed an average of 16.6 days per injury. Lower limbs were massively affected by injuries across all three seasons, mainly with muscular injuries in the quadriceps and hamstrings and sprains in the tibiotarsal structure. Overall, the injury incidence was considerably higher in matches than in training. The two times of the season that proved most conducive to injuries were the months of July and January. Our results emphasize the importance of monitoring sports performance, including injury occurrence, and assisting in identifying risk factors in professional football. Designing individualized training programs and optimizing prevention and recovery protocols are crucial for maximizing this global process.