A machine learning approach for the classification of sports based on a coaches' perspective of environmental, individual and task requirements: A sports profile analysis.

Well-designed talent programmes in sports with a focus on talent identification, orientation, development, and transfer support the engagement of young individuals and the pursuit of elite performance. To facilitate these processes, an analysis of task, environmental and individual characteristics per sport is much needed. The aims of this study were to 1) analyse whether unique profiles per sport could be established by generic characteristics and 2) to discuss similarities and differences for the potential application in talent development and transfer. By means of a validated survey, 1247 coaches from 34 sports ranked 18 characteristics on importance to their sports (0 = not important - 10 = very important). To discriminate the responses per sport a Discriminant Analysis (DA) was carried out. To refine the DA-classification, Uniform Manifold Approximation and Projection (UMAP) with CatBoost classifier was performed. To test the performance of the CatBoost classifier-algorithm, a confusion-matrix was generated. The cross-validated DA showed that 70.2% of the coaches were correctly classified to their sport. The UMAP/CatBoost technique revealed 75.1% accuracy with correctly predicted responses per sport ranging from 18.2% (sailing) to 98.2% (soccer). With varying precision, the algorithm was able to differentiate sports by importance of its characteristics indicating similarities and differences per sport.

Can perceptuo-motor skills outcomes predict future competition participation/drop-out and competition performance in youth table tennis players? A 9-year follow-up study.

Tools that provide a fair estimate of young table tennis players' potential and their chances to succeed will support making decisions whether to commit to an extensive development program and the accompanying lifestyle. Consequently, this study included two research questions (RQ) to evaluate the capability of the Dutch perceptuo-motor skills assessment to predict competition participation/drop-out (RQ1) and competition performance (RQ2) in young table tennis players (n = 39; 7-11 years) using a tracking period of 9 years. The perceptuo-motor skills assessment consists of eight tests assessing gross motor function (i.e., sprint, agility, vertical jump) and ball control (i.e., speed while dribbling, aiming at target, ball skills, throwing a ball and eye-hand coordination). A Cox regression analysis demonstrated that a higher level of ball control was associated with a lower risk to drop-out from table tennis competition. The eye-hand coordination test appeared to be most suitable since it was the only test included in the multivariable Cox regression model (HR = .908; p = .001) (RQ1). Similarly, a multilevel regression analysis showed that a higher level of ball control was associated with a higher future competition performance. The eye-hand coordination and aiming at target tests were included in the multivariable multilevel model (p < 0.05; R2 = 36.4%) (RQ2). This evaluation demonstrates promising prospects for the perceptuo-motor skills assessment to be included in a talent development programme. Future studies are needed to obtain valid thresholds scores and clarify the predictive value in a larger sample of youth competition players.

Primary School Pupils: Unequal GMC Developmental Pathways in a Single School Year.

Gross motor coordination (GMC) is essential for the development of specific motor skills and long-term participation in physical activities and sports. Group analysis reveals that, on average, children develop these skills gradually; however, how individuals develop GMC is less clear. The main aim of this study is to increase the understanding of developmental patterns within one school year, and whether children's grade, gender, or baseline GMC proficiency are associated with these developmental patterns. In total, 2594 Dutch children aged 6−12 years performed the modified Körper Koordinations Test für Kinder (KTK3+) twice in one school year (autumn and spring). The KTK3+ includes four subtests: walking backwards, moving sideways, jumping sideways, and eye-hand coordination (EHC) test. On average, children developed significantly on all subtests (p < 0.001). At baseline, children in higher grades scored significantly higher than children in lower grades, and children in grades 5 and 6 (age 9 and 10 years) showed most development (raw scores on average, p < 0.001). Boys outperformed girls on EHC across all grades, whereas girls outperformed boys on walking backwards. Nevertheless, both boys and girls developed similarly. Children with lower scores at baseline developed more quickly across all grades. Noteworthy is that 12.1−24% (depending on the test item) of the children scored lower in the spring than in the autumn tests. On average, children develop their GMC; however, we report large differences in their individual trajectories and note that a substantial number did not show a positive GMC development. Further research should examine GMC development with more possible influencing factors as well as over a longer time span to better understand differences in children's GMC development. This may result in more individualized programs in PE lessons, enabling children to optimally develop their GMC, and better use of GMC assessment tools to monitor children's development.

Is Motor Coordination the Key to Success in Youth Cycling?

PURPOSE: To evaluate the predictive value of a (non-)sport-specific test battery on the future success of young cyclists, test scores were compared with competition performances 2-3 years later. METHODS: Three motor coordination, 5 physical performance, and 2 cycling-specific measurements were collected in 111 U15 (13.0-14.9 y) and 67 U17 (15.0-16.9 y) male road cyclists. In addition, maturity status, relative age, and competition history were assessed. National and provincial competition results 2-3 years later, in the U17year2 and U19year2 categories, were submitted to 2 separate 4-stage hierarchical regressions. RESULTS: The results of the model of the U15 group revealed that maturity, relative age, competition history, motor coordination, physical performance, and cycling-specific performance accounted for 22.6% of the variance in competitive success. For the U15 category, only maturity and motor coordination were significant predictors of competitive success in the U17year2 category. Maturity and motor coordination each uniquely explained ±5% of the variance. However, for the U17 group-neither motor coordination, physical performance, nor cycling-specific performance could predict competitive success in the U19year2 category. CONCLUSIONS: The current study underlines the importance of general motor coordination as a building block necessary for optimal development in youth cycling. However, considering the lack of predictive value from the U17 category onward, other features may determine further development of youth athletes. Nevertheless, it is questioned why athletes need to possess a minimum level of all physical, motor coordination, and cycling-specific characteristics to experience success and enjoyment in their sport.

Mind, body, and shuttle: multidimensional benchmarks for talent identification in male youth badminton.

The aim of the study was to identify benchmarks for anthropometric, physical performance, motor coordination, and psychological characteristics by comparing youth badminton players of different levels through the use of a multifactorial test battery. Sixty-one male participants aged 12-18 years were divided into three groups: elite (N = 10), sub-elite (N = 24), and novice (N = 27). Standard test batteries for anthropometry (including measures to estimate biological maturity), physical performance, and motor coordination were applied, as well as the modified PCDEQ2 questionnaire for psychological characteristics of youth athletes (Hill, 2016). Multivariate analyses of covariance (MANCOVAs) with age and biological maturity as covariates were used to investigate differences between skill levels. A discriminant analysis was used to reveal to what extent participants could be correctly assigned to their skill group. Significant differences were found in physical performance (explosive power, flexibility, speed, and endurance), BMI and motor coordination. In the psychological domain, perfectionism was found to be significantly different and elites scored highest. The discriminant analysis showed that 100% of the participants were correctly classified and 80.0% were correctly cross validated. These results significantly add to the previously limited youth players' reference values, and confirm the value of a generic, i.e. without sport-specific testing, multifactorial approach to talent identification in youth badminton.

A Retrospective Analysis of the National Youth Teams in Volleyball: Were They Always Faster, Taller, and Stronger?

ABSTRACT: Mireille, M, Johan, P, Matthieu, L, and Pieter, V. A retrospective analysis of the national youth teams in volleyball: Were they always faster, taller, and stronger? J Strength Cond Res 36(9): 2615-2621, 2022-Although there are numerous studies comparing the characteristics of young and adult volleyball players of different levels, it remains unclear to what extent these findings can be used for performance prediction because very few are based on longitudinal or retrospective analyses. The aim of the current retrospective study was to test to what extent anthropometry, physical performance, and motor coordination can predict future selection in national youth teams. From 2012 to 2015, 1738 10- to 13-year-old boys and girls who played volleyball completed 3 anthropometric, 4 physical performance, and 3 motor coordination tests. In January 2020, 52 athletes of this sample were found to be part of one of the national youth teams of Belgium. A multivariate analysis of covariance, discriminant analyses, and logistic regression analyses were conducted to compare the test results of the selected vs. the nonselected players. Significance level was set at p ≤ 0.05. Results showed that the selected players were already taller and showed better jumping performance, and for females, they tended to have better motor coordination at the time of baseline measurement. Therefore, it seems important to focus on the development of motor coordination and jumping performance at young ages because superiority in these characteristics increases the chances to be selected for the national team 4-8 years later. Nevertheless, considering the large variation in results, selection cannot be made based on these characteristics alone. The practical implications for coaches and federations with respect to training and talent detection are discussed.

The importance of performance in youth competitions as an indicator of future success in cycling.

ABSTRACTIn sports, outperforming your peers at young age does not guarantee a professional sports career as an adult. To gain more insight in how performance in youth cycling competitions can be an indicator for future success, the current study (a) examined differences in success rate between future achievers and future non-achievers, (b) investigated whether the relative age effect affects these career pathways and (c) explored to what extent youth competitive performance can predict success at adult age. The sample consisted of 307 male road cyclists who achieved at least one top 10 result during national and provincial youth competitions (U15, U17, U19). Thirty-two were classified as future achievers because they reached senior elite level; the remaining 275 were classed as future non-achievers. Non-parametric analyses of longitudinal data, Kruskal-Wallis and logistic regressions were applied. These analyses revealed that the future achievers started to outperform the future non-achievers from U17 onwards. While the relatively older cyclists have an advantage over other cyclists in U15, this effect was smaller in U17 and was absent in U19. Finally, the competitive success rate of U15 cyclists could not predict success at adult age. However, for U17 and U19 cyclists each additional top 10 result was associated with 3-5%, and 6% higher chance to reach elite level at adult age, respectively. Overall, these results demonstrate that estimating potential based on competition results is unpredictable in the U15 category, however, may provide a better indication of future success from U17 onwards.Highlights The competitive success rate of U15 cyclists could not predict success at adult ageFrom the U17 category onwards, future achievers had higher success rates, and success rate has some predictive value for performance at senior elite level.Competitive performance is influenced by relative age effect in the U15 category, however, this effect disappeared as the athlete progressed into older age categories.Future non-achievers experience a significant decrease in success rate when transitioning to a new competition category.

Predicting Youth Athlete Sleep Quality and the Development of a Translational Tool to Inform Practitioner Decision Making.

BACKGROUND: Identifying key variables that predict sleep quality in youth athletes allows practitioners to monitor the most parsimonious set of variables that can improve athlete buy-in and compliance for athlete self-report measurement. Translating these findings into a decision-making tool could facilitate practitioner willingness to monitor sleep in athletes. HYPOTHESIS: Key predictor variables, identified by feature reduction techniques, will lead to higher predictive accuracy in determining youth athletes with poor sleep quality. STUDY DESIGN: Cross-sectional study. LEVEL OF EVIDENCE: Level 3. METHODS: A group (N = 115) of elite youth athletes completed questionnaires consisting of the Pittsburgh Sleep Quality Index and questions on sport participation, training, sleep environment, and sleep hygiene habits. A least absolute shrinkage and selection operator regression model was used for feature reduction and to select factors to train a feature-reduced sleep quality classification model. These were compared with a classification model utilizing the full feature set. RESULTS: Sport type, training before 8 am, training hours per week, presleep computer usage, presleep texting or calling, prebedtime reading, and during-sleep time checks on digital devices were identified as variables of greatest influence on sleep quality and used for the reduced feature set modeling. The reduced feature set model performed better (area under the curve, 0.80; sensitivity, 0.57; specificity, 0.80) than the full feature set models in classifying youth athlete sleep quality. CONCLUSION: The findings of our study highlight that sleep quality of elite youth athletes is best predicted by specific sport participation, training, and sleep hygiene habits. CLINICAL RELEVANCE: Education and interventions around the training and sleep hygiene factors that were identified to most influence the sleep quality of youth athletes could be prioritized to optimize their sleep characteristics. The developed sleep quality nomogram may be useful as a decision-making tool to improve sleep monitoring practice among practitioners.

Similarities and differences between sports subserving systematic talent transfer and development: The case of paddle sports.

OBJECTIVES: The aim of this study was to investigate similarities and differences for 18 sports toward canoe/kayak in order to identify donorsport and/or multisports, based upon a systematic analysis of the task constraints per sport that are assumed to be either crucial or less important from the coaches' viewpoint. DESIGN: Descriptive survey analysis. METHODS: 891 certified coaches from 19 sports valued (0-10; not important at all-very important) 15 characteristics by a questionnaire (Flemish Sports Compass) within their sport. Unique sport-profiles (discriminant analysis - DA) were constructed for 19 sports based on these characteristics. Similarities and differences between canoe/kayak and the other 18 sports were analyzed by means of MANOVAs on anthropometric, physical and motor coordination characteristics. RESULTS: Cross validated DA (rcan=0.660, Wilks' Lambda=0.564, p<0.001) showed that 72.1% of the canoe/kayak coaches were correctly assigned to their sport. For canoe/kayak seven characteristics were valued crucial; dynamic balance (8.51±1.69), core stability (8.45±2.27), pulling power (8.12±1.68), speed (7.54±2.07), endurance (7.27±2.03), stature (6.43±1.41) and rhythm (6.01±3.01). Least important characteristics were: flexibility (6.16±1.75), agility (4.27±3.10), catching (3.90±3.22), climbing (2.45±3.05), jumping (1.81±2.11), throwing (1.60±2.24), hitting (.94±1.77) and kicking (.61±1.04). CONCLUSIONS: This novel approach to determine important characteristics per sport makes identifying similarities and differences between sports possible. Similarities might enlarge talent-pools for possible talent transfers. Differences can help identify sports based on complementary characteristics for the construction of broad motor development programs. From this viewpoint gymnastics can serve as potential donorsport (similarities) for canoe/kayak, while handball and tennis can subserve broad development for young canoe/kayak athletes.

Accuracy of maturity prediction equations in individual elite male football players.

BACKGROUND: 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 APHV in youth athletes is not available. AIM: The purpose of this study is to assess the accuracy of predication equations for the estimation of APHV in individual youth male football players. SUBJECTS AND METHODS: Body dimensions were measured at least every three months in 17 elite youth male football players (11.9 ± 0.8 years at baseline) from the 2008-2009 through the 2011-2012 seasons. APHV was predicted at each observation with four suggested equations. Predicted APHV was compared to the player's observed APHV using one-sample-t-tests and equivalence-tests. Longitudinal stability was assessed by comparing the linear coefficient of the deviation to zero. RESULTS: Predicted APHV was equivalent to the observed APHV in none of the players. A difference with a large effect size (Cohen's d > 0.8) was noted in 87% of the predictions. Moreover, predictions were not stable over time in 71% of the cases. CONCLUSIONS: None of the evaluated prediction equations is accurate for estimating APHV in individual players nor are predictions stable over time, which limits their utility for adjusting training programmes.

Sink or Swim? A survival analysis of sport dropout in Australian youth swimmers.

OBJECTIVES: To examine long-term participation and dropout rates in Australian youth swimming using survival analyses and to determine whether multiple individual, socio-demographic, and competition-related factors influenced dropout. DESIGN: Retrospective cohort study of registration and competitive performance data. METHODS: Part 1-Registration data from N = 17 161 female (n = 9400) and male (n = 7761) New South Wales (NSW) swimmers aged 10-15 years (inclusive). Part 2-Competition level involvement in a subsample of female (n = 1011) and male (n = 811) swimmers, aged 12-15 years, was also examined. To determine dropout rates and influential factors, Kaplan-Meier survival analyses supplemented by Cox regression were used. RESULTS: (1) Kaplan-Meier analyses identified median sustained participation rates of four years (95% CI = 3.93-4.06), with 15.9% maintaining participation over 10 years. Cox regressions identified age-group was associated with dropout (P < .001), with a 184.9% higher Hazard Rate (HR) for 10- vs 15-year-olds. Residential proximity to major cities was associated with dropout (P < .001), with urban swimmers reporting a 24.8% higher HR rate than rural swimmers. Sex and relative age were not associated with dropout. (2) The subsample median sustained participation was five years (95% CI = 4.79-5.20), with 25.3% maintaining participation for ten years. Level of competition was associated (P < .001), with an 86% higher HR when considering lower competition levels (ie, club/district v national). CONCLUSION: In a large representative sample of swimmers, survival analyses identified age-group, competition level, and city proximity were associated with increased swimming dropout rates.

Teachers' perceptions of children's sport learning capacity predicts their fundamental movement skill proficiency.

The intrapersonal mechanism that drives and explains individual differences in motor development is still a relatively underexplored area of research. In this study, we set out to determine whether in teachers' perceptions, higher sport-learning capacity (SLC) is associated with the level of fundamental movement skills, and the changes therein over 24 weeks in 7-year-olds. We assessed 170 children from eight primary schools in the Netherlands twice (T1, T2) in 24 weeks, using a tool to assess their FMS in applied settings (Platvoet, Elferink-Gemser, & Visscher, 2018). The schools' eight PE teachers used a digital questionnaire to score their perceptions of children's SLC (Platvoet, Elferink-Gemser, Baker, & Visscher, 2015). Based on their SLC, each child was then placed in the low (n = 33), average (n = 107), or high SLC-group (n = 30). We used a MANOVA to examine group differences, with the four subtests as dependent variables. The results revealed that regardless of SLC-group, children improved their FMS over 24 weeks (F(4,163) = 10.22, p < .05, Wilks Lamba = 0.800). An interaction effect was found for FMS assessment and SLC-group (F(8,326) = 2.23, p < 0,05, Wilks Lamba = 0.899). The children in the average and high groups improved more on the moving sideways subtest than those in the low group (p < .05). The MANOVA showed a main effect for SLC-group (F(4,163) = 4.69, p < .05, Wilks Lamba = 0.804). The average and high groups outperformed the low group on the measurements for walking backwards and moving sideways (p < .05). The high group also outperformed the low group on jumping sideways at both measurements, while the average group only achieved this at T1. The high group scored better on jumping sideways than the average group at T1 (p < .05). No differences in proficiency were found between the three groups on the hand-eye coordination assessment (p > .05). In sum, we found an association between children's SLC and level of FMS and changes therein; this was especially pronounced in children with a lower SLC, who had a lower proficiency and improved less on the subtest moving sideways.

Identification of elite performance characteristics in a small sample of taekwondo athletes.

Along with the increasing popularity of taekwondo, there is a need of evidence-based talent identification (TID) and development programs based upon profiles of future elite athletes. This study first aims to investigate the differences between elite and non-elite taekwondo athletes in anthropometry, physical performance and motor coordination. The second aim is to demonstrate the applicability of z-scores in TID research. A total of 98 Taekwondo athletes between 12 and 17 years old were tested using a generic test battery consisting of four anthropometrical (Height, Weight, Fat Percentage, BMI), six physical performance (Sit & Reach, Sprint 5m, Sprint 30m, Counter Movement Jump, Squat Jump, Endurance Shuttle Run) and three motor coordination tests (Moving Sideways, Jumping Sideways, Walking Backwards). Based on the individual success at international competition level, 18 were categorised as elite athletes and 80 were considered as non-elite. T-tests (step 1) on raw test scores and MANOVAs on z-scores (step 2) were conducted to examine differences between the elite and non-elite taekwondo athletes for anthropometry, physical performance and motor coordination tests. Finally, z-scores were reconverted to raw scores to demonstrate practical significance for coaches. Overall, elite taekwondo athletes score better compared to the non-elite group. The MANOVA analysis better scores for elites on fat percentage (-0.55 versus 0.12;p = 0.006), BMI (-0.37 versus 0,08;p = 0.067) sprint speed 30m (-0.48 versus 0.11;p = 0.029), counter movement jump (0.79 versus -0.18;p = 0.000), squat jump (0.42 versus -0.11;p = 0.041), moving sideways (0.79 versus -0.18;p = 0.000) and walking backwards (0.54 versus -0.12;p = 0.006). This study confirms our knowledge on physical profiles of elite taekwondo athletes and expands our knowledge to the domain of motor coordination. This study showed how the z-score method can be used to distinguish between elite and non-elite athletes, the former being low in number by definition.

Physiological, Anthropometric, and Motor Characteristics of Elite Chinese Youth Athletes From Six Different Sports.

Several talent selection programs in elite sport schools are based on motor diagnostics for the purpose of recommending or transferring promising talents to general groups of sports; game sports, combat sports or endurance sports, and to more concrete sports such as gymnastics, skiing, or tennis. However, the predictive value of such testing is unclear. This study evaluated the concurrent validity of physiological performance prerequisites, body dimensions, as well as specific motor performances. The sample consisted of N = 97 youth athletes from all ninth grade classes of a Shanghai Elite Sport school belonging to six different sports including basketball (n = 7), fencing (n = 23), judo (n = 20), swimming (n = 10), table tennis (n = 15), and volleyball (n = 22). The performance diagnosis took place between September 2016 and March 2017, and comprised five physiological measurements of the heart rate at rest, vital capacity, systolic and diastolic blood pressure, and hemoglobin concentration in the blood, eighteen anthropometric parameters, and two motor tests on back strength and complex reaction speed. The aim of the study was to investigate whether U15 age group athletes participating in six different sports already at this age show a sport specific anthropometric, motor performance, and physiological profile which is in line with the specific requirements of each of the sports. A discriminant analysis and a Neural Network (Multilayer Perceptron) were used to test whether it is possible to discriminate between athletes of the six sports and to assign each individual of the Under-15 athletes to his own sport on the basis of a unique profile of the morphological, motor, and physiological prerequisites. All diagnostic methods exhibited medium to high validity to discriminate between the six different sports. The relevance of the eighteen body dimensions, five physiological measures, and two motor tests for talent identification was confirmed.

Is international junior success a reliable predictor for international senior success in elite combat sports?

Currently in the literature, there is a dearth of empirical research that confirms whether international junior success is a reliable predictor for future international senior success. Despite the uncertainty of the junior-senior relationship, federations and coaches still tend to use junior success as a predictor for long-term senior success. A range of former investigations utilising a retrospective lens has merely focused on success that athletes attained at junior level competitions. Success that was achieved at senior-level competitions but at a junior age was relatively ignored. This study explored to what extent international senior success can be predicted based on success that athletes achieved in either international junior level competitions (i.e. junior medalists) or senior competitions at a junior age (i.e. early achievers). The sample contains 4011 international male and female athletes from three combat sports (taekwondo, wrestling and boxing), who were born between 1974 and 1990 and participated in both international junior and senior-level competitions between 1990 and 2016. Gender and sport differences were compared. The results revealed that 61.4% of the junior medalists and 90.4% of the early achievers went on to win international medals at a senior age. Among the early achievers, 92.2% of the taekwondo athletes, 68.4% of the wrestling athletes and 37.9% of the boxing athletes could be reliably "predicted" to win international senior medals. The findings demonstrate that specific to the three combat sports examined, international junior success appears to be an important predictor to long-term international senior success.

A coaches' perspective on the contribution of anthropometry, physical performance, and motor coordination in racquet sports.

Differences and similarities between table tennis and other racquet sports exist, but are not well documented in the literature, in spite of the relevance for talent identification. In this study we aimed at identifying the key characteristics of table tennis in comparison with tennis and badminton based upon a survey in coaches. A total of 177 licensed coaches from all across the world and with diverse professional backgrounds completed a survey on anthropometric measures, physical performance, and motor coordination skills. On a scale from 1 to 10, coaches indicated to what extent a talent characteristic was important for their sport. MANOVA identified key differences as well as similarities between all three racquet sports and a subsequent discriminant analysis allocated coaches correctly for table tennis, tennis, and badminton 81.01%, 55.6%, and 71.4% respectively. Our results show that table tennis and other racquet sport coaches are well aware of differences between the racquet sports and also the importance and value of testing and assortment of skill components. These findings can assist coaches in future talent orientation and transfer in racquet sports.

Does a perceptuomotor skills assessment have added value to detect talent for table tennis in primary school children?

Talent detection intends to support lifelong sports participation, reduce dropouts and stimulate sports at the elite level. For this purpose it is important to reveal the specific profile which directs children to the sports that connect to their strengths and preferences. This study evaluated a perceptuomotor skills assessment as part of talent detection for table tennis, a sport in which perceptuomotor skills are considered essential to cope with the difficult technical aspects. Primary school children (n = 121) and gifted young table tennis players (n = 146) were assessed using the Dutch perceptuomotor skills assessment measuring "ball control" and "gross motor function". A discriminant function analysis confirmed the added value by identifying primary school children fitting the table tennis perceptuomotor profile of the young gifted table tennis players (28%). General linear model analyses for the assessment's individual test items showed that the table tennis players outperformed their primary school peers on all "ball control" items (P < 0.001). In conclusion, the assessment appears to be of added value for talent detection in table tennis at this young age. Longitudinal studies need to reveal the predictive value for sports participation and elite sports.

Predictive models reduce talent development costs in female gymnastics.

This retrospective study focuses on the comparison of different predictive models based on the results of a talent identification test battery for female gymnasts. We studied to what extent these models have the potential to optimise selection procedures, and at the same time reduce talent development costs in female artistic gymnastics. The dropout rate of 243 female elite gymnasts was investigated, 5 years past talent selection, using linear (discriminant analysis) and non-linear predictive models (Kohonen feature maps and multilayer perceptron). The coaches classified 51.9% of the participants correct. Discriminant analysis improved the correct classification to 71.6% while the non-linear technique of Kohonen feature maps reached 73.7% correctness. Application of the multilayer perceptron even classified 79.8% of the gymnasts correctly. The combination of different predictive models for talent selection can avoid deselection of high-potential female gymnasts. The selection procedure based upon the different statistical analyses results in decrease of 33.3% of cost because the pool of selected athletes can be reduced to 92 instead of 138 gymnasts (as selected by the coaches). Reduction of the costs allows the limited resources to be fully invested in the high-potential athletes.

A longitudinal study investigating the stability of anthropometry and soccer-specific endurance in pubertal high-level youth soccer players.

We investigated the evolution and stability of anthropometric and soccer-specific endurance characteristics of 42 high-level, pubertal soccer players with high, average and low yo-yo intermittent recovery test level 1 (YYIR1) baseline performances over two and four years. The rates of improvement were calculated for each performance group, and intra-class correlations were used to verify short- and long-term stability. The main finding was that after two and four years, the magnitudes of the differences at baseline were reduced, although players with high YYIR1 baseline performance still covered the largest distance (e.g., low from 703 m to 2126 m; high from 1503 m to 2434 m over four years). Furthermore, the YYIR1 showed a high stability over two years (ICC = 0.76) and a moderate stability over four years (ICC = 0.59), due to large intra-individual differences in YYIR1 performances over time. Anthropometric measures showed very high stability (ICCs between 0.94 to 0.97) over a two-year period, in comparison with a moderate stability (ICCs between 0.57 and 0.75) over four years. These results confirm the moderate-to-high stability of high-intensity running performance in young soccer players, and suggest that the longer the follow-up, the lower the ability to predict player's future potential in running performance. They also show that with growth and maturation, poor performers might only partially catch up their fitter counterparts between 12 and 16 years. Key pointsYoung, high-level soccer players with a relatively low intermittent-endurance capacity are capable to catch up with their better performing peers after four years.Individual development and improvements of anthropometric and physical characteristics should be considered when evaluating young soccer players.

Anthropometric characteristics, physical fitness and motor coordination of 9 to 11 year old children participating in a wide range of sports.

OBJECTIVES: The aim of this study was to investigate to what extent 9 to 11 year old children participating in a specific sport already exhibit a specific anthropometric, physical fitness and motor coordination profile, in line with the requirements of that particular sport. In addition, the profiles in children with a different training volume were compared and possible differences in training hours per week between children from a low, moderate, and high level of physical fitness and motor coordination were investigated. METHODS AND RESULTS: Data of 620 children, 347 boys and 273 girls, who participated in the Flemish Sports Compass were used. Only the primary sport of each child was considered and six groups of sports (Ball sports, Dance, Gymnastics, Martial arts, Racquet sports and Swimming) were formed based on common characteristics. Measurements consisted of 17 tests. Independent T-tests and Mann-Whitney U-tests revealed few differences between the groups of sports and the discriminant analyses with the moderate and low active group did not show any significant results (p > .05). However, when discriminating among the high active children, a 85.2 % correct classification between six groups of sports was found (Wilks' Λ = .137 and p < .001). Finally, children performing under average on the tests spent significantly fewer hours in sport per week (2.50 ± 1.84 hours) compared to the children performing best (3.25 ± 2.60 hours) (p = .016) and the children performing above average (2.90 ± 1.96 hours) (p = .029) on physical fitness and motor coordination. DISCUSSION: The study showed that in general, children at a young age do not exhibit sport-specific characteristics, except in children with a high training volume. It is possible that on the one hand, children have not spent enough time yet in their sport to develop sport-specific qualities. On the other hand, it could be possible that they do not take individual qualities into account when choosing a sport.