Search Results (116)

Negative transitions require teams to reorganise rapidly from attack to defence, yet few positional indicators describe collective reorganisation in relation to possession recovery. This study examined whether rβ, a GNSS-derived angular concentration performance indicator referenced to the goal to be protected, was associated with controlled possession recovery within 10 s after a negative transition. In this retrospective observational study, five official matches of a single professional team (Serie A and UEFA Conference League) were analysed. Negative-transition episodes ending with controlled recovery were classified as FAST (≤10 s) or SLOW (>10 s). For each outfield player, the angular deviation between movement direction and the direction to the protected goal was computed; rβ was calculated at the team level using Kuramoto’s order parameter. The sample comprised 248 episodes (133 FAST; 115 SLOW). FAST episodes showed higher mean rβ values than SLOW episodes (0.717 vs. 0.600; difference = 0.117; 95% CI [0.085, 0.150]; p < 0.001; and d = 0.906). This pattern remained consistent across thresholds, fixed-window analyses, zones, and matches. Among recovered transitions, greater goal-referenced angular concentration was associated with controlled recovery within 10 s; rβ may serve as a process indicator of immediate defensive reorganisation that could support training, team monitoring and performance analysis. Full article

Background: Injuries are a major concern in professional football because they may reduce player availability and affect team performance. Injury risk may vary across different phases of the season in relation to changes in training and competition demands, recovery, and cumulative workload. Objectives: To describe the epidemiology of injuries in a professional football team over three consecutive seasons and to evaluate seasonal variations in injury characteristics and injury-related time-loss. Methods: This retrospective study analyzed 260 time-loss injuries sustained by 78 of 96 registered male first-team players (mean age 27.0 ± 4.5 years) from a professional football club in Türkiye over three consecutive seasons (2022–2023 to 2024–2025). Total team exposure was 33,609 player-hours (2409 match player-hours and 31,200 training player-hours). Injuries were classified according to injury setting, seasonal period, anatomical location, injury type, and injury-related time-loss. Exploratory generalized estimating equations (GEE) analysis accounted for repeated injuries within players. Results: A total of 260 injuries were recorded; 62.3% occurred during training and 37.7% during matches. The overall injury incidence was 7.7 per 1000 player-hours (95% CI, 6.8–8.7), with rates of 40.7 per 1000 match player-hours (95% CI, 33.0–49.6) and 5.2 per 1000 training player-hours (95% CI, 4.4–6.1). The groin–thigh–lower-leg region (52.7%) and the thigh (25.4%) were the most frequently affected anatomical sites, while muscle injuries accounted for 43.5% of all injuries. Estimated injury incidence was highest during the mid- and late-season (9.29 and 9.12 per 1000 player-hours, respectively) and lowest during the preparation period (2.55 per 1000 player-hours). Exploratory GEE analysis showed significant differences in injury counts across seasonal periods (Wald χ² = 41.35, p < 0.001). Compared with the late season, injury incidence was lower during the preparation period (IRR 0.17, 95% CI 0.09–0.33; p < 0.001), whereas no significant differences were observed for the early or mid-season. Conclusions: Injury incidence was lowest during the preparation period and highest during the competitive season. Because exposure estimates were based on team-level rather than individual player-level data, these findings should be interpreted cautiously. Prospective multicentre studies with individual exposure data are needed. Full article

This study assessed body build and pain threshold in 300 professional American football players representing the top Polish teams, based on their tactical formations: big skill players (formation 1), linemen (formation 2), and skill players (formation 3). Morphological measurements, body proportion indices, and body composition were evaluated, and pain thresholds were measured using an algometer. American football players differ significantly in body build depending on formations. The values of the analyzed morphological traits and body composition components were the highest in players from formation 2 (linemen) who are responsible for blocking and tackling opponents and protecting or attacking the quarterback. The analysis of somatic differences between players from the other formations showed that players primarily responsible for scoring points (formation 1) had higher values for morphological traits compared to players from formation 3, who line up the farthest from the line of scrimmage. The highest pain threshold values were observed in players from formation 2, who are the most exposed to direct contact with opponents. This study provides an original description of anthropometric variables in American football players from three formations, as well as differences in pain perception between the player formations, which should be taken into account when selecting players for individual formations in this sport. Full article

Objectives: Sided games are commonly used to condition players for the demands of official games (OGs). Therefore, this study aimed to evaluate if different sided games match position-specific locomotor and mechanical OG demands of professional football players. Methods: Twenty-one male professional football players from a second team of a professional football club were monitored during the second half of the 2024/25 season. External load was assessed during OGs and sided games. The latter were categorized by area per player (ApP) as small- (SSG, ApP < 100 m²), medium- (MSG, ApP 100–200 m²) and large-sided games (LSG, ApP > 200 m²). External load was analyzed for total distance (TD), high-speed running (HSR), sprint distance (SPD), and the number of accelerations (ACC) and decelerations (DEC). Players were grouped by position: center backs (CBs), full backs (FBs), central midfielders (CMs), wide midfielders (WMs), and strikers (STs). Results: Across all playing positions (CB, FB, CM, WM, ST), SSGs, MSGs and LSGs elicited significantly higher TD than the OG, except for CM, where no significant differences were observed during SSGs and LSGs. All positions displayed similar HSR during LSGs than OG demands, and some positions also during MSGs (CB, CM, FB) and SSGs (CB). SPD was similar across all positions only during LSGs. ACC and DEC were significantly higher for all positions in SSGs and MSGs than OGs and similar in LSGs. Conclusions: Position-specific OG demands were not statistically from different sided-game formats. ACC, DEC and TD in LSGs met OG demands; however, smaller formats (SSGs, MSGs) overload those variables. In contrast, HSR and SPR load in SSGs and MSGs did not meet OG demands for most positions. For that, coaches should use LSGs, knowing that TD may be overloaded, or supplement SSGs/MSGs with running-based drills for more accurate programming. Full article

This paper presents a retrospective proof-of-concept development and preliminary evaluation of an interpretable decision-support system for daily fatigue-risk management in one elite women’s football club. The system integrates morning wellness, GPS-derived external load, and a daily wellness-duration internal-load proxy at the player-day level. It combines a player-day integration layer, an interpretable predictive layer, and a recommendation layer that returns one of three staff-facing actions: Reduce, Maintain, or Progress. The predictive model outputs a calibrated probability of elevated next-morning self-reported soreness. The target is a subjective questionnaire outcome, not an injury, medical diagnosis, or objective marker of recovery. The decision-support layer maps this probability to a three-state recommendation, informed by a review threshold, operational guardrails, and staff oversight. Using retrospective monitoring data from two competitive seasons (2024/25 and 2025/26) in a single professional team, we evaluated the proposed approach using rolling-origin temporal validation, leave-one-player-out cross-validation, and between-season validation. To separate genuine predictive signal from the day-to-day persistence of soreness, we report a baseline ladder ranging from a trivial persistence rule to the full model, with bootstrap confidence intervals for performance differences. Under rolling-origin validation across 16 monthly folds, the final logistic regression model achieved a mean ROC-AUC of $0.759$ ($SD=0.089$). Critically, a model excluding current soreness still outperformed the persistence baseline (ROC-AUC $0.738$ vs. $0.721$), and the isolated contribution of current soreness was modest but reliable ($\Delta$ROC-AUC $=+0.044$, 95% CI $[+0.027,+0.059]$). Between-season validation (train: 2024/25; test: 2025/26) yielded an ROC-AUC of 0.801. The three-state recommendation layer separated outcomes monotonically, with observed next-morning soreness rates of $0.054$ for Progress, $0.217$ for Maintain, and $0.326$ for Reduce ($p<0.001$ for the Progress-versus-Maintain contrast). These preliminary findings support the feasibility of the proposed approach within the club studied. However, because the model requires complete wellness, GPS, and proxy data, it operates only on the fully monitored on-pitch stratum (3386 of 17,703 player-days); the reported performance therefore applies to this stratum rather than to a typical player-day, and prospective evaluation and external validation by independent teams are required before broader implementation can be considered. Full article

Women’s football represents the convergence of the history of sport, the history of women, and the history of women’s participation in ball games. From Classical antiquity, literary and archeological evidence highlights a long-standing association between spherical objects and the female sphere. While ancient physical cultures primarily celebrated male athleticism, records from various Classical civilizations indicate that women occasionally engaged in ball games and recreational exercises. In ancient Greece and Rome, these activities were often socially framed around themes of youth, grace, and courtship rituals, rather than structured competitive sport. Over the centuries, women continuously negotiated their access to physical play, transitioning from these early symbolic associations to more organized activities by the late Middle Ages. It was only at the end of the nineteenth century, alongside broader movements for female emancipation, that women’s football began to emerge in Great Britain, marking the entry of women into an exclusively male sporting domain. In recent decades, women’s football has undergone substantial professionalization and global expansion, accompanied by growing scientific interest in understanding the determinants of performance. This narrative review synthesizes current evidence on the multidimensional factors influencing performance in women’s football, integrating physical and match demands, physiological and anthropometric characteristics, psychological and emotional components, menstrual cycle-related influences, and contextual variables. The literature published between 2008 and 2024 was examined across major scientific databases. Findings indicate that while total match distance has remained relatively stable (averaging 9500–10,500 m), high-speed running distances, sprint frequencies, and peak intensity demands have escalated by 15–30% over the tracked decade. Psychological resilience and team dynamics contribute meaningfully to performance outcomes, whereas menstrual cycle phases appear to exert limited and inconsistent effects on objective physical performance. Overall, performance in women’s football emerges from the dynamic interaction of multiple domains, underscoring the need for integrated and individualized performance management strategies. Full article

The accumulation of training and competition loads represents a critical determinant of musculoskeletal injury risk in professional team sports, yet contemporary monitoring systems remain limited by their reliance on single-domain temporal analysis that overlooks the multi-scale rhythmic patterns inherent in athletic workload signals. This study introduces FDTM (frequency-aware dual-stream temporal model), a deep learning framework that jointly encodes time-domain dependencies and frequency-domain spectral signatures from digital athlete monitoring streams to predict individual injury risk over a forward-looking seven-game horizon. The framework integrates a stacked bidirectional long short-term memory branch augmented with temporal self-attention pooling, a spectral encoding branch employing discrete Fourier transform decomposition across high-frequency (weekly), mid-frequency (bi-weekly), and low-frequency (seasonal) bands, and a cross-modal gated attention fusion module that adaptively balances temporal and spectral representations conditioned on player context. We evaluate FDTM on three heterogeneous public sports datasets spanning basketball (NBA game-log corpus 2013–2023), Australian rules football (AFL Player Workload Dataset), and soccer (SoccerMon open monitoring corpus), comprising 612 athletes and 247,830 player-game observations across ten competitive seasons. FDTM achieves AUC-ROC values of 0.858, 0.833, and 0.821 on the three datasets respectively, outperforming the strongest deep-learning baseline (FEDformer) by 2.0 to 3.3 percentage points and the strongest non-spectral baseline (TCN) by 3.2 to 4.5 percentage points while maintaining a Brier score below 0.04. Ablation studies confirm that the spectral branch contributes 5.1 percent to overall discriminative performance. SHAP attribution analyses identify high-frequency weekly components as the dominant injury-relevant signal, followed by low-frequency seasonal trends and the cumulative acute-to-chronic workload temporal feature, with gating-weight visualizations revealing dynamic modality contributions consistent with established sports science theory. Direct spectral analysis of the raw workload signal confirms that injury-preceding windows exhibit significantly elevated weekly-band power across all three datasets (Mann–Whitney U test, p < 1 × 10⁻⁷), and the architectural advantage is shown to be robust across 30 independent training seeds. These findings suggest that frequency-aware modeling may serve as a transferable methodology for sports engineering applications in injury prevention, return-to-play planning, and individualized rehabilitation, pending further external validation in female athletes and additional team sports. Full article

This study introduces a novel physics-inspired framework to quantify defensive pressure in football from tracking data. We model defender–attacker interactions as a variable-mass dynamical system, translating Newtonian mechanics into operational metrics that combine spatial configuration and motion. From this formulation we derive interpretable quantities at dyad, player, and team level, including a Center of Pressure (CP), Defensive Momentum, Defensive Force, and Defensive Work. We illustrate the framework in a single-match proof-of-concept using professional optical tracking data, analysing both full-match behaviour and football-specific phases such as counter-pressing, set-pieces, and throw-ins. Results show how the proposed metrics separate persistent spatial constraint (pressure) from energetically demanding defensive actions (work), enable identification of high-cost match-ups and workload concentration, and support time-resolved descriptions of coordinated pressing sequences. The framework provides a transferable, mechanically grounded toolkit for applied defensive performance analysis and motivates future validation on larger datasets. Full article

Monitoring performance in football often combines physical testing and GPS-derived external-load measures, although their relationships remain unclear. This study examined the relationships between physical-test outcomes and GPS-derived external-load variables during the pre-season in professional female football players and whether these measures appear to capture distinct dimensions of performance. This observational study monitored 24 outfield players from a Brazilian Women’s First Division team during a 6-week pre-season. Players performed the countermovement jump, 10 m and 30 m sprints, change-of-direction test, and 30–15 intermittent fitness test while external load was recorded across field sessions. Associations were examined using Pearson’s or Spearman’s correlations, and principal component analysis (PCA) was applied. Significant correlations were more frequent within than between domains. Total distance correlated with accelerations (ρ = 0.740, p < 0.001), decelerations (ρ = 0.684, p < 0.001), Z3 distance (ρ = 0.595, p = 0.003), and Z4 distance (ρ = 0.584, p = 0.003), while sprint count correlated with sprint distance (r = 0.950, p < 0.001). Estimated VO₂max correlated positively with CMJ (r = 0.533, p = 0.007) and negatively with 10 m (r = −0.445, p = 0.029) and 30 m sprint times (r = −0.476, p = 0.019). PCA identified two components explaining 61.4% of the total variance: external load (40.6%) and physical performance (20.8%). These findings indicate that both approaches capture distinct and complementary aspects of performance. Full article

The aim of this study was to examine temporal changes in eccentric hamstring strength, impulse-based mechanical outputs, and interlimb asymmetry in professional football players performing a football-specific eccentric hamstring training program. Forty male football players (18–25 years) from two teams competing in the Turkish Second Professional Football League participated in this longitudinal cohort study. Eccentric hamstring performance was assessed at three time points (pre-, mid-, and post-season) using the NordBord Hamstring Testing System. Mixed-design repeated-measures ANOVA revealed significant main effects of time and significant time × Team interactions for left and right maximal impulse values (p < 0.05). In contrast, maximal eccentric force variables showed no significant time effects, although significant time × Team interactions were observed for both limbs (p < 0.05). Interlimb maximal force asymmetry and mean asymmetry demonstrated significant time effects, while Team effects and interaction terms were not significant. Overall, these findings indicate that temporal changes in eccentric hamstring performance in professional football players may be more clearly reflected in force–time–dependent metrics, particularly impulse, rather than peak force outputs. Accordingly, impulse-based measures may provide additional insight into eccentric hamstring performance changes in professional football players. Full article

Load monitoring is essential in football to optimise training prescription and reduce injury risk, yet the internal and external demands of common possession drills such as rondos remain insufficiently described. Rondo formats are widely used across levels, but changes in player configuration may substantially alter their load profile. This study examined how three rondo configurations (5vs2, 6vs2 and 8vs2) affect internal load (RPE) and external load (GPS-derived metrics) in semi-professional football players. Twenty-one Spanish players (mean age = 28.9 years) from the same team participated in the study. All players completed three rondo formats (5vs2, 6vs2 and 8vs2) across four separate weeks. Each format consisted of three 3-min bouts with 1 min of recovery, and players were restricted to one touch. Internal load was assessed using players’ rating of perceived exertion (RPE), while external load was measured using a global positioning system (GPS). The results showed a significantly higher perceived exertion in the 5vs2 rondo compared with the other formats (p < 0.001). Regarding external load, significantly greater values (p < 0.001) were observed in the 6vs2 rondo for distance covered at 12.1–18.0 km·h⁻¹ (DZ2) and 18.1–21.0 km·h⁻¹ (DZ3) compared with the other rondo formats. In contrast, 6vs2 also elicited a significantly lower number of accelerations above 3 m·s⁻² and decelerations below −3 m·s⁻² than the other formats (p < 0.001; p < 0.006). Finally, 5vs2 produced significantly higher maximum speed than 8vs2 (p = 0.016). In conclusion, the 6vs2 rondo may be the most suitable option to target DZ2 and DZ3 compared with 5vs2 and 8vs2. Conversely, 5vs2 induced the greatest acceleration and deceleration demands, followed by 8vs2. Therefore, coaches can select the rondo format according to the desired external load requirements. Full article

Background/Objectives: American football (AF) is a contact sport with a high injury risk, where an integrated model of interdisciplinary care may support recovery. The aim of this study was to assess the relationship between diet quality, supplementation, dietician’s and physiotherapist’s support, injury rates and musculoskeletal pain among AF players in Poland. Methods: The study involved 53 male players from the FA Panthers Wrocław team and was conducted using the KomPAN questionnaire and an original survey on supplementation, injuries and pain intensity. Results: The results showed that, although players using supplements had a significantly greater proportion of healthy foods in their overall diet (p = 0.02), they did not report fewer injuries in the last 12 months and 7 days than those who did not use supplements (p = 0.87; p = 0.58, respectively). However, a positive correlation (p$\le$ 0.001, r = 0.53) was found between the healthy diet index and the number of injuries. Those who used the services of a dietitian and physiotherapist showed a higher quality of diet (p$=$ $0.02$; p$=$ $0.02$, respectively) and reported higher total pain intensity (p$=$ $0.009$; p$=$ $0.03$), while those who used only the services of a physiotherapist reported higher average pain intensity (p$\le$ 0.001). Conclusions: These results suggest that supplementation and professional support in this group are primarily due to exposure after injuries caused by severe pain, rather than serving a preventive function. Full article

This paper examines the organizational competitiveness and strategic transformation of an elite professional football entity in the Greek Super League during the period 2018–2020, using Panathinaikos as a case study within a comparative framework including Olympiacos, AEK, and PAOK. This period marked a phase of enforced reorientation for Panathinaikos due to UEFA sanctions for overdue debts and the club’s exclusion from European competitions, which resulted in extensive squad renewal and increased reliance on academy-developed players. The aim of the study is to identify the factors shaping Panathinaikos’ strategic position, diagnose the causes of its lagging performance, and suggest directions for strategic repositioning. To this end, a multi-criteria framework based on the Analytic Hierarchy Process (AHP) is employed, integrating qualitative assessments, expert judgements, and quantitative performance indicators through pairwise comparisons, weight calculations, and consistency checks. The analysis is based on a conceptually original model that defines the Football Organization as an integrated system composed of two interdependent subsystems: the Football Club and the Football Team (competitive subsystem). This approach highlights that league standings do not always reflect overall performance dynamics, as they are influenced by both organizational and on-field factors. The findings indicate that Panathinaikos is lagging behind in key areas and that a structural discontinuity between the Club and the Team limits strategic coherence and the ability to create a sustainable competitive advantage. The study concludes with proposals for restructuring and strategic repositioning, while the proposed model functions as a transferable decision-support tool for assessing organizational competitiveness, with broader applicability to complex organizational systems beyond professional football. Full article

Recent developments in computer vision have significantly enhanced the automation and objectivity of sports analytics. This paper proposes a novel deep learning-based framework for estimating football possession directly from broadcast video, eliminating the reliance on manual annotations or event-based data that are often labor-intensive, subjective, and temporally coarse. The framework incorporates two structurally improved object detection models: YOLOv8-P2S3A for football detection and YOLOv8-HWD3A for player detection. These models demonstrate superior accuracy compared to baseline detectors, achieving 79.4% and 71.1% validation average precision, respectively, while maintaining low computational latency. Team identification is accomplished through unsupervised DBSCAN clustering on jersey color features, enabling robust and label-free team assignment across diverse match scenarios. Object trajectories are maintained via the Norfair multi-object tracking algorithm, and a temporally aware refinement module ensures accurate estimation of ball possession durations. Extensive experiments were conducted on a dataset comprising 20 full-match Video clips. The proposed system achieved a root mean square error (RMSE) of 4.87 in possession estimation, outperforming all evaluated baselines, including YOLOv10n (RMSE: 5.12) and YOLOv11 (RMSE: 5.17), with a substantial improvement over YOLOv6n (RMSE: 12.73). These results substantiate the effectiveness of the proposed framework in enhancing the precision, efficiency, and automation of football analytics, offering practical value for coaches, analysts, and sports scientists in professional settings. Full article

Objectives: This clinical commentary presents a four-pillar rehabilitation framework implemented in the elite football setting of OFI Crete FC and designed to facilitate the return of football players to training and competitive play. The framework is structured around five core components: (a) effective load management during training and matches, (b) individualized rehabilitation programs and injury prevention strategies integrated within the recovery phase, (c) a novel on-field rehabilitation framework, and (d) an extended secondary prevention plan. Methods: This comprehensive approach was implemented over a three-year period with the OFI Crete FC football team and involved 87 elite professional players between the ages of 17 and 35. Throughout this time, 180 injuries were documented, ranging from mild to severe injuries. Results: The outcome illustrated that only 40% of these injuries led to players missing official matches, while the recurrence or follow-up injury rate was limited to just 10%. Over the course of the three years, a steady 60% decline in injury rates was observed. Conclusions: These findings emphasize the crucial importance of training load management, the integration of injury prevention strategies throughout the rehabilitation process, and the early initiation of on-field rehabilitation. Within the clinical setting of OFI Crete FC, the implementation of this integrated rehabilitation framework was associated with favorable observations in injury incidence, player absence days, and return-to-play timelines, which may reflect that the approach has potential benefits while remaining observational in nature. Full article