Unveiling the nonlinear dynamics of player performance in China's super league as a function of age.

To explore the dynamics in physical and technical performance of professional football players and changes across age groups. Match statistics were collected from 1900 games across ten seasons (2012-2021) in the Chinese Super League. Generalized additive models visualized age-related trends in 12 key performance indicators including technical and physical variables. Revealed nonlinear trajectories characterized by rapid early declines, stable peak periods and accelerated late decreases. Physical indicators decreased progressively from the early 20 s before stabilizing briefly then declining further after 30. Conversely, technical metrics gradually improved into the late 20 s and early 30 s prior to decreasing again. This study provides novel evidence that football performance changes nonlinearly across age. Targeted training and development strategies should be tailored to the specific needs of different career stages.

Player selection in football by integrated SWARA-VIKOR methods under fuzzy environment.

This study aims to provide an objective evaluation and selection of the most suitable players for the Turkish National Football Team by using multi-criteria decision-making methods, specifically Stepwise Weight Assessment Ratio Analysis (SWARA) and VIsekriterijumsko KOmpromisno Rangiranje (VIKOR) based on neutrosophic numbers. In the initial step of the study, the important criteria for player selection were determined, and a total of 21 and 26 criteria were identified for goalkeeper and players, respectively. Agility, reflexes and jumping ability are very important for goalkeeper whereas marking, passing ability, agility, dribbling, and footwork are the most important criteria for players. The performances of the players were evaluated due to these criteria and finally the Turkish National Football Team was established scientifically because of the best player selection. This decision-making process will be more beneficial in making more informed and effective decisions in the national team's player selection process. The success of the team can be improved by providing an objective and systematic player selection approach.

Descriptive epidemiology study of hand injuries sustained in Gaelic football referred to a hand therapy service over 1 year.

Objectives: Gaelic football requires ball handling, such as bouncing, fist passing and catching. To date, no research has examined the types of injuries sustained to the hand in this sport. This study aims to establish the types of orthopaedic hand injuries sustained in Gaelic football. Methods: This was a retrospective descriptive epidemiology study of Gaelic football-related hand injuries treated at a hand therapy unit. The nature of injuries was categorised along with collated variables on player demographics and injury profiles. Potential correlations between injury and continuous demographic data were analysed using the Mann-Whitney U and Kruskal-Wallis tests. Pearson's χ2 test was used for categorical data (p<0.05). Results: 287 referrals were identified. Most players were men (n=189; 65.9%), and the average age was 17 (IQR 14-25). Most fractures were to the volar base of the middle phalanx (n=110; 42.8%). Significant differences were found between the age of male and female players with fractures under 18 (p<0.05), the distribution of left and right-hand fractures by age (p<0.05), the distribution of fractures by bone type (p<0.05) and also between sex and affected ray (p<0.05), bone type (p<0.05) and mechanism of injury (p=0.05). Conclusion: This study established the types of musculoskeletal hand injuries sustained by players in Gaelic football. Considering developmental, anthropometric and rule differences between male and female players across the age range may explain variations in injuries. This data can help devise injury prevention and management strategies for Gaelic football.

Elite Soccer Players' Weekly Workload Assessment Through a New Training Load and Performance Score.

Purpose: Monitoring players' training load allows practitioners to enhance physical performance while reducing injury risk. The aim of this study was to identify the key external load indicators in professional U19 soccer. Methods: Twenty-four-professional Italian young (U19) soccer players were monitored by using the rating of perceived exertion (CR-10 RPE scale) and a wearable inertial sensor during the competitive season. Three main components were detected by a Principal Component Analysis (PCA): i) volume metabolic related component, ii) intensity mechanical stimuli component, and iii) intensity metabolic/mechanical component. We hence computed two scores (i.e. Performance [PERF] and total workload [WORK]) permitting to investigate the weekly microcycle. Results: Correlation analysis showed that scores (i.e. PERF and WORK) are low correlated (r = -0.20) suggesting that they were independent. Autocorrelation analysis showed that a weekly microcycle is detectable in all the scores. Two-way ANOVA RM showed a statistical difference between match day (MD) and playing position for the three PCA components and PERF score. Conclusion: We proposed an innovative approach to assess both the players' physical performance and training load by using a machine learning approach allowing reducing a large dataset in an objective way. This approach may help practitioners to prescribe the training in the microcycle based on the two scores.

The association between unilateral and bilateral performance-related measures in elite female soccer players: a multifaceted investigation.

Purpose: The present study aimed to investigate a) the associations between bilateral performance utilizing countermovement jump (CMJ), squat jump (SJ), speed and unilateral CMJ, isokinetic peak torque in knee extension and flexion with angular velocities of 60°/s and 180°/s and tensiomyography (TMG) parameters; b) whether the asymmetries derived from unilateral tests are associated with bilateral CMJ, SJ and speed in elite female soccer players. Methods: Thirty-five elite female soccer players (average age: 20 ± 5 years) completed CMJ, SJ, speed, isokinetic muscle strength and TMG tests. Results: Compared to the non-dominant leg, the dominant leg demonstrated greater peak torque output in both knee flexion (7.4%) and knee extension (5.6%) isokinetic tasks, as well as m. vastus medialis contraction time (7.6%), and soccer-specific agility test (4.1%). Conversely, the hamstring to quadriceps peak torque ratio at 180°/s (8.5%) was significantly greater in the non-dominant leg. The associations between CMJ, SJ and speed performance were positive and ranged from weak (r = 0.350) to high (r = 0.710). For speed and TMG-derived variables, correlations were negative and ranged from weak (r = -0.345, p = 0.042, for vastus medialis contraction time) to moderate (r = -0.530, p = 0.001, for biceps femoris contraction time). Furthermore, both bilateral CMJ and SJ negatively correlated with TMG-derived variables, ranging from weak (r = -0.350, p = 0.039, for vastus lateralis contraction time) to moderate (r = -0.537, p = 0.003, for rectus femoris contraction time). Conclusion: The overall significant, albeit inconsistent, correlations between the diverse performance scores obtained highlight the necessity for a multifaceted and thorough diagnostic strategy in female soccer players.

Analyzing soccer match sprint distances: A comparison of GPS-based absolute and relative thresholds.

This study compared the most common absolute sprint threshold (> 25.2 km/h) with relative and individualized thresholds (> 70%, > 75%, > 80%, > 85% and > 90% of peak match speed). Twenty elite soccer players, competing in the first division of the Portuguese League, were monitored using GNSS equipment during thirty-four official matches. Peak match speed was retrieved as the individual maximal speed reached during the full season. Distances were registered when speed overcame the absolute and the relative thresholds. Mean ± SD of peak speeds and distances covered were calculated, and Pearson correlation (r) and mean paired differences were performed to analyze relationships and differences between thresholds. The peak match speed was 32.9 ± 1.4 km/h. Correlations between distances covered using the absolute and relative thresholds varied from very strong (> 70%: r = 0.84, p < .001; > 75%: r = 0.89, p < .001; and > 80%: r = 0.88, p < .001), strong (> 85%: r = 0.79, p < .001), to moderate (> 90%: r = 0.59, p < .001). Overall, the > 75% (ES: 0.23 [95% CI: 0.16, 0.31]) and the > 90% (ES: -1.65 [95%CI: -1.85, -1.48]) relative thresholds presented the smallest and largest differences, respectively, with the absolute threshold. Differences were also found when considering the playing positions. While the distances covered by central midfielders were similar between the absolute and > 80% thresholds (-0.03 [-0.16, 0.10]), fullbacks covered largely more distance -1.88 [-2.42 -1.50]) in the absolute threshold than in the > 80% threshold. The distances covered by players varied based on the selected threshold, affecting the distances covered by different playing positions. Being the highest speed threshold within displacements thresholds, the absolute sprint threshold showed greater similarity to lower rather than higher relative thresholds.

Match running performance is similar in lower and higher competitive standards of Spanish professional soccer accounting for effective playing time.

This study aimed to compare match running performance of players in the top two competitive standards of Spanish professional soccer, accounting for effective playing time (the duration of play after subtracting the game interruptions). A total of 2,784 match observations from 44 teams competing in the Spanish First Division (LaLiga Santander) and the Second Division (LaLiga Smartbank) were undertaken during two consecutive seasons (from 2021/22 to 2022/23). Total distance (TD), medium-speed running (MSR, distance 14.1-21 km · h-1), high-speed running (HSR, > 21 km · h-1), very high-speed running (VHSR, 21.1-24 km · h-1) and sprinting speed running distance (Sprint, > 24 km · h-1) were analyzed using a computerized tracking system (TRACAB, Chyronhego, New York, NY). These physical performance variables were calculated for both total and effective playing time. The main results showed that the mean effective playing time was significantly higher in matches of the First Division than in the Second Division (p < .01). In contrast to those observed when total playing time was considered, there were no significant differences (p > .05) between both competitive standards on medium speed running (MSR), high speed running (HSR), very high-speed running (VHSR), and sprint distances when the effective playing time was considered. Such findings demonstrate that contrary to previous research match running performance of players was similar in lower and higher competitive standards. Thus, effective playing time should be taken into account when interpreting the match running performance of professional soccer players.

Injury incidence and characteristics in adolescent female football players: A systematic review with meta-analysis of prospective studies.

To observe overall, training, and match injury incidence in female youth football. We also aimed to quantify the incidence of injuries by affected tissue and body location. The following databases were examined: PubMed, Web of Science, Scopus, SPORTDiscus, Cochrane and PEDro. Papers that reported overall injury incidence, training or match injury incidence were included. Additionally, studies had to be performed in adolescent female football players (13-19 years of age). The Newcastle-Ottawa Scale and the checklist of items that must be included in epidemiological football reports were used to assess methodological quality of the included articles. For the meta-analyses, a random effect model was used. A total of 13 studies were included. There were 2,333 injuries; incidence was higher during games (12.7/1000 h) compared to training sessions (2.3/1000 h). The injury match-to-training ratio was 5.8. The lower limbs were the region in which the greatest number of injuries occurred, with the ankle (1.2/1000 h) and knee (0.8/1000 h) having the most injuries. In relation to injured tissue, ligament injuries represented an incidence of 1.3/1000 h, followed by muscle injuries (0.9/1000 h). This study represents the first step towards the creation and implementation of preventative measures in female youth football. The results suggest that attention should be focused on ankle and knee injuries, since they are the most frequent and can lead to sport retirement in some cases depending on the severity.

Evaluating the Validity of Tests to Predict Sprint and Change of Direction Speed in Para-Athletes With Brain Impairments.

Maximum running speed is a performance determinant in para-athletics and cerebral palsy football. Sixty international para-athletes with brain impairments completed five activity-limitation tests (standing broad jump, four bounds for distance, split jumps, 10-m speed skip, and running in place) and two criterion tests (40-m sprint and modified agility test). The same three tests (standing broad jump, four bounds for distance, and 10-m speed skip) that correlated with running performance in nondisabled runners (.67 < r < -.82; p < .05; 75% of variance) also correlated in para-athletes with brain impairments (.41 < r < -.62; p < .01; 55% of variance). Standing broad jump, four bounds for distance, split jumps, and running in place also correlated with change-of-direction speed (.43 < r < -.63; p < .01; 58% of variance). Results indicate that methods of classification for para-athletics with nondisabled runners are also valid with para-athletes with brain impairments, and new sport-specific relationships were found for assessing the performance of rapid and short sprints toward different directions, specific of a team para-sport like cerebral palsy football.

The effects of simulated monocular and binocular vision impairment on football penalty kick performance.

Sports performance is relatively robust under high levels of binocular blur. However, the limited research studies investigating monocular impairments has shown it has a larger impact on sport performance. This research study is relevant for classification in sports for athletes with vision impairment (VI), where visual acuity (VA) from the better eye is used during classification. Across two experiments, we aimed to establish the point at which binocular and monocular impairments affected performance in a football penalty kick (PK) through simulating varying severities of degraded VA and contrast sensitivity (CS) in active football players. In experiment one, 25 footballers performed PKs as VA and CS were systematically decreased in both eyes, and in one condition, visual field (VF) was reduced. The most severe VA/CS condition and reduced VF significantly impacted outcome, ball velocity and placement (ball kicked closer to the centre of the goal) (p < 0.05). In experiment two, 29 different footballers performed PKs as VA and CS of only the dominant eye were systematically decreased and in one condition the dominant eye was occluded, and participants viewed their environment through the non-dominant eye (monocular viewing). No differences were observed when assessing monocular impairments influence on outcome, velocity and ball placement. PKs have a high resilience to VI, but binocular impairment has a more immediate effect, suggesting binocular measures should be used in classification processes in football.

Risk and prevalence of Relative Energy Deficiency in Sport (REDs) among professional female football players.

A high prevalence of low energy availability (LEA) has been reported in female football players. This is of concern as problematic LEA may evolve into a syndromic pattern known as relative energy deficiency in sport (REDs). Given the difficulties in accurately assessing LEA, our study shifts emphasis to measurable indicators of REDs, serving as proxies for health detriments caused by LEA. The present cross-sectional study aimed to quantify the risk of REDs and to assess the prevalence of indicators indicative of the syndrome. 60 players (tiers 3 and 4) from three Norwegian football teams were analyzed as a single cohort but also stratified based on player position and menstrual status. The proportion of players at risk for REDs was 22%, that is, 17% with mild, 3% with moderate to high, and 2% with very high/extreme risk, respectively. The majority of the cohort (71%) presented with no primary indicators, while 20%, 7%, and 2% presented with one, two, and three primary indicators, respectively. Regarding secondary indicators, 57% had none, 33% had one, and 10% had two indicators. For associated indicators, 30% had none, 42% had one, 18% had two, 8% had three, and 2% had four indicators. Player position did not affect the prevalence of REDs indicators. Among noncontraceptive users (n = 27), secondary amenorrhea (AME) was reported by 30%. These findings indicate that health and performance teams should prioritize universal health promoting strategies rather than selective or indicative strategies. Particularly, focus on nutritional periodization to secure sufficient energy availability, mitigating the risk of problematic LEA and REDs should be addressed.

Bayes-xG: player and position correction on expected goals (xG) using Bayesian hierarchical approach.

This study employs Bayesian methodologies to explore the influence of player or positional factors in predicting the probability of a shot resulting in a goal, measured by the expected goals (xG) metric. Utilising publicly available data from StatsBomb, Bayesian hierarchical logistic regressions are constructed, analysing approximately 10,000 shots from the English Premier League (for the years of 2003 and 2015) to ascertain whether positional or player-level effects impact xG. The findings reveal positional effects in a basic model that includes only distance to goal and shot angle as predictors, highlighting that strikers and attacking midfielders exhibit a higher likelihood of scoring. However, these effects diminish when more informative predictors are introduced. Nevertheless, even with additional predictors, player-level effects persist, indicating that certain players possess notable positive or negative xG adjustments, influencing their likelihood of scoring a given chance. The study extends its analysis to data from Spain's La Liga ( ≈ 20 K shots from 1973 and 2004 to 2020) and Germany's Bundesliga ( ≈ 7.5 K shots from 2015), yielding comparable results. Additionally, the paper assesses the impact of prior distribution choices on outcomes, concluding that the priors employed in the models provide sound results but could be refined to enhance sampling efficiency for constructing more complex and extensive models feasibly.

Psychological risk factors for a first hamstring strain injury in soccer: a qualitative study.

Introduction: Hamstring strain injuries (HSIs) remain one of the most burdensome injuries in soccer. Current recommendations to prevent sports injuries suggest the importance for coaches and medical staff to consider psychological and contextual risk factors and to specify them according to the injury type and context. HSI risk factors in soccer have been widely investigated, mainly from physiological and biomechanical perspectives. However, psychological and health-related risk factors are still unexplored. Therefore, the objective of this study was to determine the psychological and health-related risk factors for a first HSI in male competitive soccer. Method: Individual semi-structured interviews were conducted with ten male competitive soccer players, who had recently sustained a HSI. Based on multifactorial models of sports injury causation, soccer players' individual, contextual, and situational risk factors at the time of their first HSI were investigated. Interviews were analyzed using thematic analysis with deductive and inductive approaches. Results: Individual psychological risk factors included common at-risk personality traits, obsessive passion for soccer with competitive motivational goals, strong athletic identity, and poor health literacy. The injured players were exposed to a controlling coaching style, with a fear of negative staff evaluations, and had recently experienced life stressors. They were injured during matches or overload periods and were highly engaged in the activity. Discussion: Previously injured soccer players exhibit a lack of perspective concerning the repercussions of their actions on their health. From a preventive viewpoint, these results suggest enhancing the players' health literacy, supporting their autonomy, and moderating the controlling coaching style.

A Rehabilitation Algorithm After Lateral Ankle Sprains in Professional Football (Soccer): An Approach Based on Clinical Practice Guidelines.

Lateral ankle sprain (LAS) is one of the most common types of injury in professional football (soccer) players with high risk of recurrence. The rehabilitation after LAS in professional football players is often still time-based and relies on anecdotal experience of clinicans. There is still a lack of utilization of criteria-based rehabilitation concepts after LAS in professional football. The aims of this clinical commentary are (1) to critically discuss the need for criteria-based rehabilitation concepts after LAS in professional football players, (2) to highlight the current lack of these approaches and (3) to present a novel clinical guideline-based rehabilitation algorithm. Short time-loss (15 days) and high recurrence rate (17%) raise the question of trivialization of LAS in professional football. Despite consequences for many stakeholders involved (players, teams, clubs, insurers), there is still a lack of of criteria-based, step-by-step approaches. The use of a criteria-based rehabilitation approach might reduce the high recurrence rate after LAS in professional football players and will lead, in turn, to increased long-term player availability. Practical experiences of he authors demonstrate the feasibility of such an approach. The effectiveness of this novel rehabilitation algorithm remains to be evaluated in future studies. Level of Evidence: 5.

Vitamin D levels and bone mineral density of middle-aged premenopausal female football and volleyball players in Japan: a cross-sectional study.

BACKGROUND: The number of football teams in senior categories has increased. As outdoor sports entail players being exposed to sunlight, playing football may contribute to maintaining vitamin D stores and body mineral density while preventing osteoporosis. This study aimed to determine the bone mineral density and vitamin D levels in middle-aged premenopausal female football players. METHODS: Participants were premenopausal females in their 40s. We evaluated bone mineral density of the second to the fourth lumbar vertebrae and femoral neck, serum 25-hydroxy vitamin D (25-OHD) levels, which is an indicator of vitamin D stores, and body composition. In addition, we administered a questionnaire survey on exercise habits and lifestyle. Ninety-two participants were categorised into three groups: the football group (n = 27), volleyball group (n = 40), and non-exercise group (n = 25). RESULTS: Bone mineral density was higher in the football and volleyball groups than in the non-exercise group (P < 0.01). The volleyball group had a significantly higher bone mineral density of the lumbar spine and femoral neck than the non-exercise group (P < 0.01). The football group had a significantly higher bone mineral density of the femoral neck than the non-exercise group (P < 0.01). Although the football group had played fewer years than the volleyball group (P < 0.01), serum 25-OHD levels were the highest in the football group and were significantly higher than those in the volleyball and non-exercise groups (P < 0.01). CONCLUSIONS: Middle-aged premenopausal football players had higher body vitamin D levels and bone mineral densities than non-active females. These results suggest that playing football may contribute to the prevention of osteoporosis. TRIAL REGISTRATION: UMIN Clinical Trials Registry UMIN000054235. 2024/04/23. Retrospectively registered.

Upper and lower limb bone mass accrual in adolescent footballers across a short period of training and competition

Abstract Objectives: To analyze bone mineral content (BMC) and area bone mineral density (aBMD) accrual in adolescent male footballers who started their first football season. Methods: 17 athletes (14.8 ± 0.4 years) were monitored across 15 weeks of football training. Participants were evaluated for somatic maturation (HPHV), BMC, and aBMD at three time points: before (M1) and after (M2) a preparatory phase, and at the end of the competitive phase (M3). BMC and aBMD were measured using DXA scans. Participants were divided into groups according to maturation status (circa-PHV and post-PHV), and the amount of accumulated training load (median split). Results: A significant effect (12.1 g/week, standard error (SE) = 2.6 g/week) was observed for lower limbs BMC across the three time points. There were no significant effects of time for upper limbs BMC. There was a significant effect of time for total body aBMD (0.007, SE = 0.003 g/cm2/week) across the three time points. Adolescents at post-PHV had a significant 245.6 g (SE = 56.1 g) higher BMC compared to adolescents at circa-PHV. No significant effects were observed for the accumulated training load. Conclusion: Systematic football training, even during the growth spurt, has a positive impact on adolescent bone markers despite the accumulated training load and maturation.

Predicting sports performance of elite female football players through smart wearable measurement platform.

Recent development of information technology and wearable devices has led to the analysis of multidimensional sports information and the enhancement of athletes' sports performance convenient and potentially more efficient. In this study, we present a novel data platform tailored for capturing athletes' cognitive, physiological, and body composition data. This platform incorporates diverse visualization modes, enabling athletes and coaches to access data seamlessly. Fourteen elite female football players (average age=20.6±1.3years; 3 forwards, 5 midfielders, 4 defenders, and 2 goalkeepers) were recruited from National Taiwan Normal University, Taiwan, as the primary observational group, and 12 female university students without regular sport/exercise habits (average age=21.6±1.3years) were recruited as control group. Through multidimensional data analysis, we identified significant differences in limb muscle mass and several cognitive function scores (e.g., reaction times of attention and working memory) between elite female football varsity team and general female university students. Furthermore, 1-month heart rate data obtained from wearable devices revealed a significant negative correlation between average heart rate median and cognitive function scores. Overall, this study demonstrates the potential of this platform as an efficient multidimensional data collection and analysis platform. Therefore, valuable insights between cognitive functions, physiological signals and body composition can be obtained via this multidimensional platform for facilitating sports performance.

Goldfit Soccer: A Multidimensional Model for Talent Identification of Young Soccer Players.

Studies have provided empirical evidence on the prognostic relevance of test batteries and the "coach's eye" for talent identification. The aims were 1) to compare objective and subjective assessments as well as a combined soccer-specific potential index between future selected and non-selected players and 2) to evaluate the prognostic validity of a multidimensional model as a tool for talent identification in soccer. The sample was composed by 132 male players (14,5 ± 1,4 years; regional competitive level) from U13 to U17 age groups of a Brazilian soccer talent development program. Athletes completed a multidimensional test battery and were subjectively rated by their coaches for sporting potential. Players' success was evaluated five years later and was operationalized by achieving under-20 category of the Brazilian Championship or adult professional level (success rate, 15.9%). Confirming univariate prognostic validity, future selected outperformed non-selected players regarding 20-m sprint (p = .009), agility (p = .04), countermovement jump (p = .04), sit-and-reach (p = .001), Yo-Yo IR1 (p = .001), dribbling (p < .001), perceived competence (p = .007), peaking under pressure (p = .01), confidence/motivation (p = .03), coping skills (p = .03), intangibles (p < .001) and player potential (p < .001). A combined index (objective tests, athlete's assessments and coach's eye) named Gold Score Soccer (GSS) showed high prognostic validity (p < .001). A binary logistic regression estimated the probability of success (yes/not) with GSS, ambidextrous and predicted age at peak height velocity as predictors. This multidimensional model named GoldFit Soccer showed high prognostic validity (sensitivity = 85.7%; specificity = 83.8%; accuracy = 84.1%; area under the ROC curve = .93 [.87-.98]). Thus, GoldFit Soccer is a valid multidimensional scientific model for talent identification in soccer.

A comparative video analysis of hamstring injuries mechanism and situational pattern in men's and women's football (soccer).

PURPOSE: To describe the injury mechanism and situational patterns of severe (absence >28 days) hamstring muscle injuries in professional male and female football (soccer) players. METHODS: The data for males were sourced from Serie A clubs participating in both national and international competitions from 2018 to 2021. For the female cohort, hamstring injuries were identified during matches of the top national/international competitions from 2017 to 2023. Video footage was obtained, and three raters categorised injury mechanisms and situational patterns. Injuries were also examined according to the month, minute and location. RESULTS: A total of 129 severe hamstring injuries were identified, with 64 occurring in females and 65 in males. Video analysis was possible for 29 (45%) female cases and 61 (94%) male cases. Female injuries had longer lay-off times (97.8 ± 77.1 days) than males (39.6 ± 20.9 days). Females had a higher proportion of indirect contact injuries (34%) than males (13%) and a lower proportion of non-contact injuries (66% vs. 87%). Four situational patterns were identified: running was the most common for both sexes, representing 59% of female injuries and 41% of male injuries. Over-stretching injuries were split across open and CKC scenarios but collectively explained nearly half (48%) of male injuries but only one in five (21%) female injuries. Kicking injuries had a higher proportion in females (17%) than males (10%). Injuries were more common in the second half for females and the first half for males. CONCLUSION: Females had a higher proportion of indirect contact, running and kicking injuries and a lower proportion of non-contact and stretch-type injuries than males. Understanding injury patterns can inform tailored prevention programs, considering sex-specific differences. LEVEL OF EVIDENCE: Level IV.

Application of Machine Learning Methods to Investigate Joint Load in Agility on the Football Field: Creating the Model, Part I.

Laboratory studies have limitations in screening for anterior cruciate ligament (ACL) injury risk due to their lack of ecological validity. Machine learning (ML) methods coupled with wearable sensors are state-of-art approaches for joint load estimation outside the laboratory in athletic tasks. The aim of this study was to investigate ML approaches in predicting knee joint loading during sport-specific agility tasks. We explored the possibility of predicting high and low knee abduction moments (KAMs) from kinematic data collected in a laboratory setting through wearable sensors and of predicting the actual KAM from kinematics. Xsens MVN Analyze and Vicon motion analysis, together with Bertec force plates, were used. Talented female football (soccer) players (n = 32, age 14.8 ± 1.0 y, height 167.9 ± 5.1 cm, mass 57.5 ± 8.0 kg) performed unanticipated sidestep cutting movements (number of trials analyzed = 1105). According to the findings of this technical note, classification models that aim to identify the players exhibiting high or low KAM are preferable to the ones that aim to predict the actual peak KAM magnitude. The possibility of classifying high versus low KAMs during agility with good approximation (AUC 0.81-0.85) represents a step towards testing in an ecologically valid environment.