Data Reduction Approaches to Athlete Monitoring in Professional Australian Football

Analysis of the most demanding passages of play in elite youth soccer: a comparison between congested and non-congested fixture schedules

This study aimed to examine the most demanding passages of play in elite youth soccer for congested and non-congested fixture schedules. Seventeen elite youth male soccer players (18.2 ± 1.3 years old) participated in this study across 30 competitive matches. Assessed matches included congested (n = 12, three matches within eight consecutive days or less) and non-congested matches (n = 18, at least 5 days between matches). The players' activity profiles during matches were analysed using global positioning measurement units (GPS). Players activity included: distance covered, distance covered at different velocities, high-intensity accelerations and decelerations, and player load. The most demanding passages (MDP) of match play was calculated using a moving average method within three-time windows (i.e., 1, 5, and 10 min). Data were analysed using a Bayesian ANOVA. During congested fixtures, the players' distance covered and player load declined, with the former decreasing across all the MDP time windows, whereas the latter exclusively into the long-time windows (i.e., 5 and 10 min). Conversely, statistical differences in the remaining variables were anecdotal and in favour of the null hypothesis (i.e., Bayes factor <1), suggesting a non-influence of the competition fixture schedule. These findings provide insight into the MDP of youth soccer, helping practitioners to periodize training and recovery strategies during different competitive fixture schedules.

Menstrual cycle and hormonal contraceptive phases' effect on elite rowers' training, performance and wellness

Objectives: To investigate the effect of menstrual cycle (MC) and hormonal contraception (HC) phases in elite rowers training, performance and wellness monitoring. Methods: Twelve French elite rowers were follow-up for 4,2 cycles on average in their final preparation for the Olympics and Paralympics Games in Tokyo 2021 through an on-site longitudinal study based on repeated measures. Daily self-reported evaluation using Likert rating scales of wellness (sleep quality, fitness, mood, injuries' pain), menstrual symptoms and training parameters (perceived exertion and self-assessment of performance) were collected (n = 1,281) in parallel to a coach evaluation of rowers' performance (n = 136), blinded to theirs MC and HC phases. Salivary samples of estradiol and progesterone were collected in each cycle to help to classify the MC into 6 phases and HC into 2-3 phases depending on the pills' hormone concentration. A chi-square test normalized by each rower was used to compare the upper quintile scores of each studied variable across phases. A Bayesian ordinal logistic regression was applied to model the rowers' self-reported performance. Results: Rowers with a natural cycle, n = 6 ( + 1 amenorrhea) evaluate their performance and wellness with significant higher score indices at the middle of their cycle. Top assessments are rarer at the premenstrual and menses phases, when they more frequently experience menstrual symptoms which are negatively correlated with their performance. The HC rowers, n = 5, also better evaluate their performance when taking the pills and more frequently experience menstrual symptoms during the pill withdrawal. The athletes self-reported performance is correlated with their coach's evaluation. Conclusion: It seems important to integrate MC and HC data in the wellness and training monitoring of female athletes since these parameters vary across hormonal phases affecting training perception of both athlete and coach.

Reliability of kettlebell swing one and five repetition maximum

Background

Research into the kettlebell swing has increased in the last decade. There has been a paucity of literature assessing an individual's ability to perform the kettlebell swing exercise. The purpose of this study was to determine the test-retest reliability of the one and five repetition maximum (1RM and 5RM) kettlebell swing.

Materials & Methods

Twenty four recreational resistance-trained participants performed an isometric mid-thigh pull (IMTP) and two familiarization sessions followed by three test sessions for each RM load approximately one week apart, using a custom-built plate-loaded kettlebell. On each test occasion, subjects completed a series of warm-up sets followed by 3-4 progressively heavier kettlebell swings to a standardized height until 1RM or 5RM was reached. Test-retest reliability was calculated using the intra-class correlation (ICC) and typical error was represented as the coefficient of variation (CV%) with 90% confidence limits (90% CL). The smallest worthwhile change (SWC%) representing the smallest change of practical importance, was calculated as 0.2 × between-subject standard deviation. The relationship of kettlebell swing performance and maximum strength was determined by Pearson correlation with ±90% CL between the absolute peak force recorded during IMTP and 1RM or 5RM.

Results

Results demonstrated a high test-retest reliability for both the 1RM (ICC = 0.97, 90% CL [0.95-0.99]; CV = 2.7%, 90% CL [2.2-3.7%]) and 5RM (ICC = 0.98, 90% CL [0.96-0.99]; CV = 2.4%, 90% CL [1.9-3.3%]), respectively. The CV% was lower than the SWC for both the 1RM (SWC = 2.8%, 90% CL [1.9-3.5]) and 5RM (SWC = 2.9%, 90% CL [1.9-3.6]) kettlebell swing. The correlation between IMTP absolute peak force and the 1RM (r = 0.69, 90% CL 0.43-0.83) was large and very large for the 5RM (r = 0.75, 90% CL [0.55-0.87]).

Conclusions

These results demonstrate the stability of 1RM and 5RM kettlebell swing performance after two familiarization sessions. Practitioners can be confident that changes in kettlebell swing 1RM and 5RM performance of >3.6 kg represent a practically important difference, which is the upper limit of the 90% CL.

Associations between refined athlete monitoring measures and individual match performance in professional Australian football

The purpose of this study was to assess relationships between measures of training load, training response and neuromuscular performance and changes in individual match performance in professional Australian football. Data were collected from 45 professional Australian footballers from one club during the 2019 competition season. External load was measured by GPS technology. Internal load was measured via session rate of perceived exertion (sRPE). Perceptual wellness was measured via pre-training questionnaires (1-5 Likert scale rating of soreness, sleep, fatigue, stress and motivation). Percentage of maximum speed was calculated relative to individual maximum recorded during preseason testing. Rolling derivative training load measures (7-day and 28-day) were calculated. Principal Component Analysis (PCA) identified eight uncorrelated components. PCA factor loadings were used to calculate summed variable covariates and single variables were chosen from components based on practicality and statistical contribution. Associations between covariates and performance were determined via linear Generalised Estimating Equations. Performance was assessed via Player Ratings from a commercial statistics company. Seven-day total distance, IMA event count and sRPE load showed significant positive relationships with performance (18-23% increase in performance z-score). No other covariates displayed significant associations with performance. Individual relative increases in training load within the 7-day period prior to a match may be beneficial for enhancing individual performance.

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.

Managing the Training Process in Elite Sports: From Descriptive to Prescriptive Data Analytics

Elite sport practitioners increasingly use data to support training process decisions related to athletes' health and performance. A careful application of data analytics is essential to gain valuable insights and recommendations that can guide decision making. In business organizations, data analytics are developed based on conceptual data analytics frameworks. The translation of such a framework to elite sport may benefit the use of data to support training process decisions. Purpose: The authors aim to present and discuss a conceptual data analytics framework, based on a taxonomy used in business analytics literature to help develop data analytics within elite sport organizations. Conclusions: The presented framework consists of 4 analytical steps structured by value and difficulty/complexity. While descriptive (step 1) and diagnostic analytics (step 2) focus on understanding the past training process, predictive (step 3) and prescriptive analytics (step 4) provide more guidance in planning the future. Although descriptive, diagnostic, and predictive analytics generate insights to inform decisions, prescriptive analytics can be used to drive decisions. However, the application of this type of advanced analytics is still challenging in elite sport. Thus, the current use of data in elite sport is more focused on informing decisions rather than driving them. The presented conceptual framework may help practitioners develop their analytical reasoning by providing new insights and guidance and may stimulate future collaborations between practitioners, researchers, and analytics experts.