Predicting Future Perceived Wellness in Professional Soccer: The Role of Preceding Load and Wellness

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.

Sleep architecture of elite soccer players surrounding match days as measured by WHOOP straps

This study aimed to quantify and compare sleep architecture before and after home and away matches in elite soccer players from the English Premier League. Across two seasons, 6 male players (age 28 ± 5 y; body mass 85.1 ± 9.5 kg; height 1.86 ± 0.09 m) wore WHOOP straps to monitor sleep across 13 matches that kicked off before 17:00 h. For each, sleep was recorded the night before (MD-1), after (MD) and following the match (MD +1). Across these 3 days total sleep time (TST), sleep efficiency (SE), sleep disturbances, wake time, light sleep, deep sleep, REM sleep, sleep and wake onsets, alongside external load, were compared. TST was reduced after MD versus MD +1 (392.9 ± 76.4 vs 459.1 ± 66.7 min, p = 0.003) but no differences existed in any other sleep variables between days (p > 0.05). TST did not differ after home (386.9 ± 75.7 min) vs. away matches (401.0 ± 78.3 min) (p = 0.475), nor did other sleep variables (p > 0.05). GPS-derived external load peaked on MD (p < 0.05). In conclusion, despite reduced TST on MD, sleep architecture was unaffected after matches played before 17:00 h, suggesting sleep quality was not significantly compromised.

The Perception of Volleyball Student-Athletes: Evaluation of Well-Being, Sport Workload, Players' Response, and Academic Demands

Physical activity has been shown to improve the health and well-being of students, athletes and the general population, especially when it is properly monitored and responses are evaluated. However, data are mostly gathered without considering a valuable element, participants' perceptions. Therefore, the objective was to know the perception of volleyball student-athletes when using different monitoring and response tools that assess well-being, workloads, responses to workloads, and academic demands. A qualitative study using semi-structured interviews with female volleyball student-athletes (n = 22) was used to know players' perceptions when using a wellness/well-being questionnaire, session ratings of perceived exertion (sRPE), and countermovement jumps (CMJ), and consider academic demands. Results show that the wellness questionnaire and sRPE increased student-athletes' awareness of well-being and readiness to perform, improved self-evaluation, self-regulation, and self-demand. However, motivation and overcoming challenges were based on the CMJ. Academic demands affected 82% of student-athletes, altering stress, fatigue, and sleep quality. Nonetheless, sport was seen as an activity that helped with academic commitments. Therefore, the wellness questionnaires and the sRPE facilitated self-awareness and positive dispositions toward self-regulation. Simultaneous intensive academic demands and training can produce mutual positive effects if the variables of physical and mental loads are harmonized in the critical academic and sports periods.

Relationships between External, Wearable Sensor-Based, and Internal Parameters: A Systematic Review

Micro electro-mechanical systems (MEMS) are used to record training and match play of intermittent team sport athletes. Paired with estimates of internal responses or adaptations to exercise, practitioners gain insight into players' dose-response relationship which facilitates the prescription of the training stimuli to optimize performance, prevent injuries, and to guide rehabilitation processes. A systematic review on the relationship between external, wearable-based, and internal parameters in team sport athletes, compliant with the PRISMA guidelines, was conducted. The literature research was performed from earliest record to 1 September 2020 using the databases PubMed, Web of Science, CINAHL, and SportDISCUS. A total of 66 full-text articles were reviewed encompassing 1541 athletes. About 109 different relationships between variables have been reviewed. The most investigated relationship across sports was found between (session) rating of perceived exertion ((session-)RPE) and PlayerLoad™ (PL) with, predominantly, moderate to strong associations (r = 0.49-0.84). Relationships between internal parameters and highly dynamic, anaerobic movements were heterogenous. Relationships between average heart rate (HR), Edward's and Banister's training impulse (TRIMP) seem to be reflected in parameters of overall activity such as PL and TD for running-intensive team sports. PL may further be suitable to estimate the overall subjective perception. To identify high fine-structured loading-relative to a certain type of sport-more specific measures and devices are needed. Individualization of parameters could be helpful to enhance practicality.

Wellness Forecasting by External and Internal Workloads in Elite Soccer Players: A Machine Learning Approach

Training for success has increasingly become a balance between maintaining high performance standards and avoiding the negative consequences of accumulated fatigue. The aim of this study is to develop a big data analytics framework to predict players’ wellness according to the external and internal workloads performed in previous days. Such a framework is useful for coaches and staff to simulate the players’ response to scheduled training in order to adapt the training stimulus to the players’ fatigue response. 17 players competing in the Italian championship (Serie A) were recruited for this study. Players’ Global Position System (GPS) data was recorded during each training and match. Moreover, every morning each player has filled in a questionnaire about their perceived wellness (WI) that consists of a 7-point Likert scale for 4 items (fatigue, sleep, stress, and muscle soreness). Finally, the rate of perceived exertion (RPE) was used to assess the effort performed by the players after each training or match. The main findings of this study are that it is possible to accurately estimate players’ WI considering their workload history as input. The machine learning framework proposed in this study is useful for sports scientists, athletic trainers, and coaches to maximise the periodization of the training based on the physiological requests of a specific period of the season.

Injury Prediction in Competitive Runners With Machine Learning

PURPOSE

Staying injury free is a major factor for success in sports. Although injuries are difficult to forecast, novel technologies and data-science applications could provide important insights. Our purpose was to use machine learning for the prediction of injuries in runners, based on detailed training logs.

METHODS

Prediction of injuries was evaluated on a new data set of 74 high-level middle- and long-distance runners, over a period of 7 years. Two analytic approaches were applied. First, the training load from the previous 7 days was expressed as a time series, with each day's training being described by 10 features. These features were a combination of objective data from a global positioning system watch (eg, duration, distance), together with subjective data about the exertion and success of the training. Second, a training week was summarized by 22 aggregate features, and a time window of 3 weeks before the injury was considered.

RESULTS

A predictive system based on bagged XGBoost machine-learning models resulted in receiver operating characteristic curves with average areas under the curves of 0.724 and 0.678 for the day and week approaches, respectively. The results of the day approach especially reflect a reasonably high probability that our system makes correct injury predictions.

CONCLUSIONS

Our machine-learning-based approach predicts a sizable portion of the injuries, in particular when the model is based on training-load data in the days preceding an injury. Overall, these results demonstrate the possible merits of using machine learning to predict injuries and tailor training programs for athletes.

Load Measures in Training/Match Monitoring in Soccer: A Systematic Review

In soccer, the assessment of the load imposed by training and a match is recognized as a fundamental task at any competitive level. The objective of this study is to carry out a systematic review on internal and external load monitoring during training and/or a match, identifying the measures used. In addition, we wish to make recommendations that make it possible to standardize the classification and use of the different measures. The systematic review was carried out according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The search was conducted through the electronic database Web of Science, using the keywords "soccer" and "football", each one with the terms "internal load", "external load", and "workload". Of the 1223 studies initially identified, 82 were thoroughly analyzed and are part of this systematic review. Of these, 25 articles only report internal load data, 20 report only external load data, and 37 studies report both internal and external load measures. There is a huge number of load measures, which requires that soccer coaches select and focus their attention on the most useful and specific measures. Standardizing the classification of the different measures is vital in the organization of this task, as well as when it is intended to compare the results obtained in different investigations.

Psychobiological Changes during National Futsal Team Training Camps and Their Relationship with Training Load

The aim of this study was two-fold: (1) to analyze the within-week variations of heart rate, session-rated of perceived exertion (sRPE), total distance, distance in 8.0–11.99 km/h⁻¹, recovery distance in 12.0–17.99 km/h⁻¹, distance in >18.0 km/h⁻¹, maximum speed, number of sprints, heart rate variability, delayed onset muscle soreness (DOMS), and fatigue during training camps of a national futsal team; and (2) to analyze the relationships between load and the well-being. Twenty-eight men from the Chinese Taipei U−20 national futsal team were analyzed. Comparisons of training days revealed that the total distance was significantly smaller on day 1 (d = −1.22) and day 6 (d = −1.95) than on day 3. The sRPE values were significantly lower on day 1 than days 4 (d = −1.53), 5 (d = −2.07), and 6 (d = −2.59). The relationships between training load and recovery parameters revealed moderate correlations between the DOMS and the sRPE recorded one (r = −0.321) and two days before training (r = −0.289). It is possible conclude that first day imposed a smaller external load and internal load, and that the internal load had a greater dependent relationship with reported DOMS and fatigue during the training camps.

Antifragility in Climbing: Determining Optimal Stress Loads for Athletic Performance Training

In the past decades, much research has examined the negative effects of stressors on the performance of athletes. However, according to evolutionary biology, organisms may exhibit growth under stress, a phenomenon called antifragility. For both coaches and their athletes, a key question is how to design training conditions to help athletes develop the kinds of physical, physiological, and behavioral adaptations underlying antifragility. An answer to this important question requires a better understanding of how individual athletes respond to stress or loads in the context of relevant sports tasks. In order to contribute to such understanding, the present study leverages a theoretical and methodological approach to generate individualized load-response profiles in the context of a climbing task. Climbers (n = 37) were asked to complete different bouldering (climbing) routes with increasing loading (i.e. difficulty). We quantified the behavioral responses of each individual athlete by mathematically combining two measures obtained for each route: (a) maximal performance (i.e. the percentage of the route that was completed) and (b) number of attempts required to achieve maximal performance. We mapped this composite response variable as a function of route difficulty. This procedure resulted in load-response curves that captured each athlete's adaptability to stress, termed phenotypic plasticity (PP), specifically operationalized as the area under the generated curves. The results indicate individual load-response profiles (and by extension PP) for athletes who perform at similar maximum levels. We discuss how these profiles might be used by coaches to systematically select stress loads that may be ideally featured in performance training.

Internal training load monitoring in professional football: a systematic review of methods using rating of perceived exertion

INTRODUCTION

The rate of perceived exertion (RPE) is widely adopted to quantify internal training load (ITL) in professional football. The aim of this study was to systematically review the use RPE-based methods in professional football.

EVIDENCE ACQUISITION

Observational studies conducted during training routines of professional football players over a minimum of one-week were selected based on the preferred reporting items for systematic reviews and meta-analyses statement.

EVIDENCE SYNTHESIS

Thirty-eight articles met the inclusion criteria (average qualitative score was 6.3 out of 10 [3 to 9]). The main deficiencies identified concerned the poor description of study design (~52% of the studies), and the non-quantification of match load (~44%). Ten studies complemented RPE-based ITL information with time-motion analysis (~26%) and seven studies added HR recordings (~18%). Nine studies collected RPE data after complementary training, separately to field sessions (~3%). Operational questions (e.g. How was your workout? ~71%) were preferred to instructions (e.g. Please rate the intensity of today's session; ~8%). Session-RPE (s-RPE; RPE multiplied by training duration) was more commonly adopted as measure of exercise intensity than isolated RPE (~76 vs. ~8%). RPE-derived variables calculated on weekly values included absolute week-to-week change, acute: chronic workload ratio, monotony and strain and were not frequently used (7 to 15%). Four studies (~11%) divided RPE in two components: respiratory and muscular.

CONCLUSIONS

There is a lack of consensus for the use of RPE in professional football and "good practices" are warranted. This review might help practitioners regarding procedures to adopt in RPE data collection and interpretation.