Purpose: To assess injury risk in elite-level youth football (soccer) players based on anthropometric, motor coordination and physical performance measures with a machine learning model. Methods: A total of 734 players in the U10 to U15 age categories (mean age, 11.7 ± 1.7 yr) from seven Belgian youth academies were prospectively followed during one season. Football exposure and occurring injuries were monitored continuously by the academies’ coaching and medical staff, respectively. Preseason anthropometric measurements (height, weight, and sitting height) were taken and test batteries to assess motor coordination and physical fitness (strength, flexibility, speed, agility, and endurance) were performed. Extreme gradient boosting algorithms (XGBoost) were used to predict injury based on the preseason test results. Subsequently, the same approach was used to classify injuries as either overuse or acute. Results: During the season, half of the players (n = 368) sustained at least one injury. Of the first occurring injuries, 173 were identified as overuse and 195 as acute injuries. The machine learning algorithm was able to identify the injured players in the hold-out test sample with 85% precision, 85% recall (sensitivity) and 85% accuracy (f1 score). Furthermore, injuries could be classified as overuse or acute with 78% precision, 78% recall, and 78% accuracy. Conclusions: Our machine learning algorithm was able to predict injury and to distinguish overuse from acute injuries with reasonably high accuracy based on preseason measures. Hence, it is a promising approach to assess injury risk among elite-level youth football players. This new knowledge could be applied in the development and improvement of injury risk management strategies to identify youth players with the highest injury risk.

This study investigated differences in generic and soccer specific motor coordination, as well as speed and agility depending on age and maturity in elite youth soccer players (U10-U15, N = 619). Measurements included body height, body weight and sitting height to estimate age at peak height velocity (APHV); three Körperkoordinationstest für Kinder subtests (i.e. jumping sideways (JS), moving sideways (MS), balancing backwards (BB)) to assess generic motor coordination; the UGent dribbling test for soccer specific motor coordination; a 5m/30m sprint and T-test for speed and agility, respectively. Age specific z-scores of the predicted APHV identified players as earlier, on time or later maturing. (M)ANOVA analyses showed significant age by maturity interaction effects for the speed and agility test cluster, revealing maturity related differences in U14 and U15 players. Next to an overall higher performance with age for all test clusters (η² 0.080–0.468), earlier maturing players outperformed their later maturing peers in 5m/30m sprinting. The opposite was seen for JS and BB. So, players’ maturity status should be taken into account to adequately value performance in talent identification. Also, the focus on characteristics that appear to be minimally biased by an earlier maturational timing (i.e. motor coordination) should be increased.

This study examined the long-term effects of the 11+ on physical performance in adolescent male football (soccer) players. Eighty-two 14- to 16-year-old male football players (11+ = 42 players, control = 40 players) participated. Teams were randomised to control (CON) and intervention (INT) groups. INT applied the 11+ injury prevention programme for 30 weeks at least twice a week as a warm-up. CON performed their standard warm-up. Motor performance tests were conducted 1 week prior and 1 week after the competition season. We used magnitude-based inferences and linear mixed-effects models to analyse performance test results. INT showed superior results compared to CON in the vertical jump height 7.5% (95%-CI 4.4%, 10.7%), the Bosco 15-s-jump test 7.2% (95%-CI 2.2%, 12.4%), and the Illinois agility test −2.6% (95%-CI −4.1%, −1.1%). Possibly beneficial effects in favour of INT were found in the 9.1 m sprint test −3.1% (95%-CI −6.1%, 0.1%). Possibly harmful effects (i.e. in favour of CON) were observed in the dribbling test 2.8% (95%-CI −0.8%, 6.4%). The 11+ warm-up programme can improve different performance measures in football players. Coaches might implement additional dribbling drills next to the 11+ to achieve improvements observed in dribbling ability when using a regular warm-up programme.

Objective To evaluate a potential reduction in injury related healthcare costs when using the ‘11+ Kids’ injury prevention programme compared with a usual warmup in children’s football. Methods This cost effectiveness analysis was based on data collected in a cluster randomised controlled trial over one season from football teams (under-9 to under-13 age groups) in Switzerland. The intervention group (INT) replaced their usual warmup with ‘11+ Kids’, while the control group (CON) warmed up as usual. Injuries, healthcare resource use and football exposure (in hours) were collected prospectively. We calculated the mean injury related costs in Swiss Francs (CHF) per 1000 hours of football. We calculated the cost effectiveness (the direct net healthcare costs divided by the net health effects of the ‘11+ Kids’ intervention) based on the actual data in our study (trial based) and for a countrywide implementation scenario (model based). Results Costs per 1000 hours of exposure were CHF228.34 (95% CI 137.45, 335.77) in the INT group and CHF469.00 (95% CI 273.30, 691.11) in the CON group. The cost difference per 1000 hours of exposure was CHF−240.66 (95%CI −406.89, −74.32). A countrywide implementation would reduce healthcare costs in Switzerland by CHF1.48 million per year. 1002 players with a mean age of 10.9 (SD 1.2) years participated. During 76 373 hours of football, 99 injuries occurred. Conclusion The ‘11+ Kids’ programme reduced the healthcare costs by 51% and was dominant (ie, the INT group had lower costs and a lower injury risk) compared with a usual warmup. This provides a compelling case for widespread implementation.

Equations predicting age at peak height velocity (APHV) are often used to assess somatic maturity and to adjust training load accordingly. However, information on the intra-individual accuracy of A...