Purpose: The study had 3 purposes: (1) to develop an index using machine-learning techniques to predict the fitness status of soccer players, (2) to explore the index’s validity and its relationship with a submaximal run test (SMFT), and (3) to analyze the impact of weekly training load on the index and SMFT outcomes. Methods: The study involved 50 players from an Italian professional soccer club. External and internal loads were collected during training sessions. Various machine-learning algorithms were assessed for their ability to predict heart-rate responses during the training drills based on external load data. The fitness index, calculated as the difference between actual and predicted heart rates, was correlated with SMFT outcomes. Results: Random forest regression (mean absolute error = 3.8 [0.05]) outperformed the other machine-learning algorithms (extreme gradient boosting and linear regression). Average speed, minutes from the start of the training session, and the work:rest ratio were identified as the most important features. The fitness index displayed a very large correlation (r = .70) with SMFT outcomes, with the highest result observed during possession games and physical conditioning exercises. The study revealed that heart-rate responses from SMFT and the fitness index could diverge throughout the season, suggesting different aspects of fitness. Conclusions: This study introduces an “invisible monitoring” approach to assess soccer player fitness in the training environment. The developed fitness index, in conjunction with traditional fitness tests, provides a comprehensive understanding of player readiness. This research paves the way for practical applications in soccer, enabling personalized training adjustments and injury prevention.

Purpose: To assess the concurrent validity of a continuous blood-glucose-monitoring system (CGM) postbreakfast, preexercise, exercise, and postexercise, while assessing the impact of 2 different breakfasts on the observed level of validity. Methods: Eight nondiabetic recreational athletes (age = 30.8 [9.5] y; height = 173.6 [6.6] cm; body mass = 70.3 [8.1] kg) took part in the study. Blood glucose concentration was monitored every 10 minutes using both a CGM (FreeStyle Libre, Abbott, France) and finger-prick blood glucose measurements (FreeStyle Optimum) over 4 different periods (postbreakfast, preexercise, exercise, and postexercise). Two different breakfasts (carbohydrates [CHO] and protein oriented) over 2 days (2 × 2 d in total) were used. Statistical analyses included the Bland–Altman method, standardized mean bias (expressed in standardized units), median absolute relative difference, and the Clarke error grid analysis. Results: Overall, mean bias was trivial to small at postbreakfast (effect size ± 90% confidence limits: −0.12 ± 0.08), preexercise (−0.08 ± 0.08), and postexercise (0.25 ± 0.14), while moderate during exercise (0.66 ± 0.09). A higher median absolute relative difference was observed during exercise (13.6% vs 7%–9.5% for the other conditions). While there was no effect of the breakfast type on the median absolute relative difference results, error grid analysis revealed a higher value in zone D (ie, clinically unsafe zone) during exercise for CHO (10.5%) compared with protein (1.6%). Conclusion: The CGM device examined in this study can only be validly used at rest, after both a CHO and protein-rich breakfast. Using CGM to monitor blood glucose concentration during exercise is not recommended. Moreover, the accuracy decreased when CHO were consumed before exercise.

Purpose: To examine the effects of an intensified tournament on workload, perceptual and neuromuscular fatigue, and muscle-damage responses in an international under-20 rugby union team. Methods: Players were subdivided into a high-exposure group (HEG, n = 13) and a low-exposure group (LEG, n = 11) according to match-play exposure time. Measures monitored over the 19-d period included training session (n = 10) and match (n = 5) workload determined via global positioning systems and session rating of perceived exertion. Well-being scores, countermovement jump height performance, and blood creatine kinase concentrations were collected at various time points. Results: Analysis of workload cumulated across the tournament entirety for training and match play combined showed that high-speed running distance was similar between groups, while a very likely larger session rating of perceived exertion load was reported in HEG vs LEG. In HEG, high-speed activity fluctuated across the 5 successive matches, albeit with no clear trend for a progressive decrease. No clear tendency for a progressive decrease in well-being scores prior to or following matches was observed in either group. In HEG, trivial to possibly small reductions in postmatch countermovement jump performance were observed, while unclear to most likely moderate increases in prematch blood creatine kinase concentrations occurred until prior to match 4. Conclusions: The magnitude of match-to-match changes in external workload, perceptual and neuromuscular fatigue, and muscle damage was generally unclear or small. These results suggest that irrespective of exposure time to match play players generally maintained performance and readiness to play across the intensified tournament. These findings support the need for holistic systematic player-monitoring programs.

Background: The objective of this study was to investigate the association between regional and total phase angle (PhA) with lower-body neuromuscular performance in young elite soccer players. Methods: Sixteen elite male soccer players (14.3 ± 1.0 years) participated in this study. Lower (LPhA)- and upper (UPhA)-hemisome PhA together with whole-body PhA (WBPhA) were measured by a bioelectrical-impedance analysis (BIA), while appendicular arm and leg lean soft tissue (ALST and LLST, respectively) were estimated. Urine osmolarity (UOsm) and urine-specific gravity (USG) were also considered. Sprints over 10 m and 20 m and countermovement jump (CMJ) tests were employed to evaluate neuromuscular performance. Results: LPhA (p = 0.003) and UOsm (p = 0.012) explained 62% of the variance in the 10 m sprint. UOsm (p = 0.001) and both LPhA (p < 0.001) and WBPhA (p = 0.024) explained 81% of the total variance in the 20 m sprint. The CMJ height was affected by LPhA (p < 0.001) and UOsm (p = 0.024), which overall explained 68% of its variance (p < 0.05), while 93% of the CMJ power variance was explained by LPhA (p < 0.001), ALST (p < 0.001), and WBPhA (p = 0.011). Conclusions: Regional PhA is a relevant and non-invasive tool to monitor lower-body neuromuscular performance in elite youth soccer. Specifically, LPhA may be favored over WBPhA as more informative.

Fleureau, A, Rabita, G, Leduc, C, Buchheit, M, and Lacome, M. Peak locomotor intensity in elite handball players: a first insight into player position differences and training practices. J Strength Cond Res 37(2): 432–438, 2023—The aims of the study were to (a) describe the peak locomotor intensity sustained during handball matches and (b) compare them with small-sided games (SSGs) programmed during training in elite handball players. Small-sided game (n = 342) and match (n = 121) data were collected among 11 players (25 ± 7 years, 191 ± 8 cm, 89 ± 12 kg) belonging to an elite French Handball team. Players' locomotor activity was recorded using 20-Hz Local Positioning System. Peak total (TD[m]) and high-speed running distance (HS[m]) and mechanical load (Accel’Rate [a.u.]) were calculated during different time periods (1–15 minutes different rolling averages). A plot of log (locomotor variables) against log (time) allowed to obtain a straight line with a slope and an intercept for each variable. Between-position differences during matches and difference between matches and SSGs were assessed with linear mixed model and magnitude-based decisions. Almost certainly higher peak locomotor intensity (intercept) was found in Wingers (TD: 156 ± 13; HS: 96 ± 12; Accel’Rate: 13 ± 3) compared with other playing positions for TD (Back players: 127 ± 10; Pivots: 136 ± 13), HS (Back players: 56 ± 9; Pivots: 57 ± 11), and Accel’Rate (Back players: 11 ± 2; Pivots: 11 ± 2). However, no clear between-position difference was found regarding the slope. Additionally, none of the SSGs format produced an overload in peak locomotor intensity in comparison with matches (TD: 138 ± 16; HS: 66 ± 20; Accel’Rate: 12 ± 2). Because reaching the peak locomotor intensity sustained during match is not possible using SSGs, practitioners should consider using isolated conditioning drills (e.g., short or long intervals, repeated sprints). Moreover, specific attention should be paid for Winger's work supplementation because they present the highest peak locomotor intensity in the team.

Purpose: This study aimed to enhance the understanding of soccer match peak demands by describing worst-case scenario (WCS) and time spent above 80% and 90% of the WCS for total distance (TD) and high-speed running (HSR). The investigation considered playing level (first team vs under-19 [U19] team) and playing position (center backs, fullbacks, midfielders, and forwards) to assess how WCS and the time spent above specific thresholds vary across different populations. Methods: Data from 31 players in a professional Italian soccer club were collected during the 2022–23 season. Microtechnology devices tracked physical activity during matches. Players were categorized by position, and WCS was determined using rolling averages over a 1-minute period. Time spent above 80% and 90% of WCS for TD and HSR was calculated. Results: The U19 team exhibited higher HSR WCS compared with the first team (∼63 m·min⁻¹ vs ∼56 m·min⁻¹). Midfielders recorded the highest TD WCS (∼208 m·min⁻¹), and forwards exhibited the highest HSR WCS (∼70 m·min⁻¹). The first team spent significantly more time above 80% (∼6 min) and 90% (∼1 min) of TD WCS. Midfielders spent significantly more time above the 80% (∼7 min) of TD WCS, while forwards above the 80% (∼2 min) of HSR WCS. Conclusions: The study emphasizes that WCS used alone may not sufficiently capture real match intensity. Considering the time spent above specific thresholds provides additional insights (ie, between-levels differences and position). Practitioners should consider both WCS and time spent above thresholds for individualized training prescriptions, reflecting differences in playing roles.