Previous studies have shown that variation in PlayerLoad (PL) could be used to detect fatigue in soccer players. Machine learning techniques (ML) were used to develop a new locomotor efficiency index (LEI) based on the prediction of PL. Sixty-four elite soccer players were monitored during an entire season. GPS systems were employed to collect external load data, which in turn were used to predict PL during training/matches. Random Forest Regression (RF) produced the best performance (mean absolute percentage error = 0.10 ± 0.01) and was included in further analyses. The difference between the PL value predicted by the ML model and the real one was calculated, individualized for each player using a z-score transformation (LEI), and interpreted as a sign of fatigue (negative LEI) or neuromuscular readiness (positive LEI). A linear mixed model was used to analyze how LEI changed according to the period of the season, day of the week, and weekly load. Regarding seasonal variation, the lowest and highest LEI values were recorded at the beginning of the season and in the middle of the season, respectively. On a weekly basis, our results showed lower values on match day − 2, while high weekly training loads were associated with a reduction in LEI.

Metabolomics is a promising tool for studying exercise physiology and exercise-associated metabolism. It has recently been defined with the term “sportomics” due to metabolomics’ capability to characterize several metabolites in several biological samples simultaneously. This narrative review on exercise metabolomics provides an initial and brief overview of the different metabolomics technologies, sample collection, and further processing steps employed for sport. It also discusses the data analysis and its biological interpretation. Thus, we do not cover sample collection, preparation, and analysis paragraphs in detail here but outline a general outlook to help the reader to understand the metabolomics studies conducted in team-sports athletes, alongside endeavoring to recognize existing or emergent trends and deal with upcoming directions in the field of exercise metabolomics in a team-sports setting.

This study examined the impact of training load periodization on neuromuscular readiness in elite football players using the Locomotor Efficiency Index (LEI) as a measure of performance optimization. Throughout the 2021/22 and 2022/23 seasons, 106 elite male players (age: 19.5 ± 3.9 years) from an Italian professional football club were monitored using Global Positioning Systems (GPS) external load data. The LEI was derived from a machine learning model, specifically random forest regression, which compared predicted and actual PlayerLoad™ values to evaluate neuromuscular efficiency. Players were categorized by weekly LEI into three readiness states: bad, normal, and good. Analysis focused on the variation in weekly LEI relative to weekly load percentage variation (large decrease, moderate decrease, no variation, moderate increase, large increase), which included total distance, high-speed distance (above 25.2 km/h), and mechanical load, defined as the sum of accelerations and decelerations. Statistical analysis showed significant differences only with variations in total distance and mechanical load. Specifically, reducing weekly loads improved LEI in players in lower readiness states, while maintaining or slightly increasing loads promoted optimal readiness. This approach enables coaches to tailor training prescriptions more effectively, optimizing workload and recovery to sustain player performance throughout a demanding season.

Elite football players face increasing physical and tactical demands due to rising match schedules emphasizing the need for effective load monitoring strategies to optimize performance and reduce injury risk. This study integrates fitness and fatigue indices derived from a machine learning approach to develop a performance score based on Banister’s fitness–fatigue model. Data were collected over two seasons (2022/23 and 2023/24) from 23 elite players of an Italian professional team. Fitness was assessed via heart rate collected during small-sided games, while fatigue was evaluated through PlayerLoad recorded during training sessions; both were normalized using z-scores. Match outcomes, including physical (e.g., total distance, high-sprint distance) and tactical metrics (e.g., field tilt, territorial domination), were analyzed in relation to performance conditions (optimal, intermediate, poor). Results revealed that players in the optimal performance condition exhibited significantly higher second-half physical outputs, including total distance (z-TD_2ndHalf: p < 0.05, ES = 0.29) and distance covered at >14.4 km/h (z-D14.4_2ndHalf: p < 0.01, ES = 0.52), alongside improved match tactical parameters as territorial domination (%TDO_2ndHalf: p < 0.01, r = 0.431). This study underscores the utility of invisible monitoring in football, providing actionable insights for weekly training periodization. This research establishes a foundation for integrating data-driven strategies to enhance physical and tactical performance in professional football.

In contemporary sports science, the integration of wearable inertial measurement units (IMUs) has revolutionized athlete performance monitoring, offering insights into training load management and injury risk mitigation. The acute:chronic workload ratio (ACWR) has emerged as a pivotal metric, indicating the balance between acute training stress and chronic adaptation. This study investigates the relationship between ACWR and running parameters, i.e., contact time (CT), flight time (FT), and vertical stiffness (K_vert). Data from thirty-five elite male soccer players were analyzed using the WIMU Pro system. Statistical analyses showed that CT increased with workload, with significant differences observed between athletes in the sweet spot and others in the danger zone (p < 0.05), and effect sizes (Cohen’s d) ranging from 0.28 to 0.37. K_vert values were consistently lower in athletes in the danger zone across all workload indicators (p < 0.001), with large effect sizes going up to 0.94. Conversely, FT showed no significant variation between ACWR groups. These findings suggest that elevated ACWRs may be linked to reductions in vertical stiffness, highlighting a potential increase in risk of injury. Coaches and practitioners can utilize these insights to tailor training programs, integrating load monitoring with tactical considerations to optimize athlete performance. Understanding the nuanced interplay between workload ratios and biomechanical parameters provides valuable insights for performance optimization for elite football athletes.

Temporal parameters are crucial for understanding running performance, especially in elite sports environments. Traditional measurement methods are often labor-intensive and not suitable for field conditions. This study seeks to provide greater clarity in parameter estimation using a single device by comparing it to the gold standard. Specifically, this study aims to investigate how the temporal parameters and vertical stiffness (K_vert) of running stride exerted by IMU sensors are related to the parameters of the smart insole for outdoor acquisition. Ten healthy male subjects performed four 60-meter high-speed runs. Data were collected using the WIMU PRO™ device and smart insoles. Contact time (CT) and flight time (FT) were identified, and K_vert was calculated using Morin’s method. Statistical analyses assessed data normality, correlations, and reliability. WIMU measured longer CT, with differences ranging from 26.3% to 38.5%, and shorter FT, with differences ranging from 27.3% to 54.5%, compared to smart insoles, across different running speeds. K_vert values were lower with WIMU, with differences ranging from 23.96% to 45.01% depending on the running activity, indicating significant differences (p < 0.001). Using these results, a multiple linear regression model was developed for the correction of WIMU’s K_vert values, improving the accuracy. The improved accuracy of K_vert measurements has significant implications for athletic performance. It provides sports scientists with a more reliable metric to estimate player fatigue, potentially leading to more effective training regimens and injury prevention strategies. This advancement is particularly valuable in team sports settings, where easy-to-use and accurate biomechanical assessments of multiple athletes are essential.