Player Activity and Load Profiling with Hidden Markov Models: A Novel Application in Rugby League

Player movement in rugby league is complex, being spatiotemporal and multifaceted. Modeling this complexity to provide robust measures of player activity and load has proved difficult, with important aspects of player movement yet to be considered. These include the influence of time-varying covariates on player activity and the combination of different dimensions of player movement. Few studies have simultaneously categorized player activity into different activity states and investigated factors influencing the transition between states, or compared player activity and load profiles between matches and training. This study applied hidden Markov models (HMMs)-a data-driven, multivariate approach-to rugby league training and match GPS data to i) demonstrate how HMMs can combine multiple variables in a data-driven way to effectively categorize player movement states, ii) investigate the influence of two time-varying covariates, score difference and elapsed match time on player activity states, and iii) compare player activity and load profiles within and between training and match modalities. HMMs were fitted to player GPS, accelerometer and heart rate data of one English Super League team across 60 training sessions and 35 matches. Distinct activity states were detected for both matches and training, with transitions between states in matches influenced by score difference and elapsed time and clear differences in activity and load profiles between training and matches. HMMs can model the complexity of player movement to effectively profile player activity and load in rugby league and have the potential to facilitate new research across several sports.

Variations in Internal and External Training Load Measures and Neuromuscular Performance of Professional Soccer Players During a Preseason Training Period

We described the internal and external training loads (TLs) experienced by soccer players over a 4-week preseason, examined their effects on vertical jump (VJ) performance, and investigated the relationships between different TL variables. Eighteen professional soccer players performed 17 training sessions and 1 friendly-match (FM) over the preseason. The internal TL was obtained using the session-rating of perceived exertion method. The external TL variables collected were total and high-intensity distances, body-load, and high-metabolic power distance via the GPS system. VJ performance was assessed 13 times throughout the study. Moreover, total quality recovery and delayed onset muscle soreness were assessed before every training session as a measure of recovery status. Players were divided, using a median split analysis, into two groups, according to their VJ performance (i.e., “lower” and “higher” VJ). External TL variables displayed similar variations across training sessions and were significantly interrelated (r ranging from 0.48 to 0.88). In periods where higher internal TLs were detected, impaired recovery status was noticed. Notably, the higher VJ group exhibited decreased jump performance at post-test and higher internal and external TLs across the entire preseason (compared to the lower VJ group). From our results it is suggested that professional soccer players with higher VJ performance are potentially more susceptible to concurrent training effects.

Positional Differences in Peak- and Accumulated- Training Load Relative to Match Load in Elite Football

Quantification of training and match load is an important method to personalize the training stimulus' prescription to players according to their match demands. The present study used time-motion analysis and triaxial-accelerometer to quantify and compare: a) The most demanding passages of play in training sessions and matches (5-min peaks); b) and the accumulated load of typical microcycles and official matches, by playing position. Players performance data in 15 official home matches and 11 in-season microcycles were collected for analysis. Players were divided into four different playing positions: Centre-backs, wing-backs, centre midfielders, and centre forwards. The results show that match demands were overperformed for acceleration counts (acc_counts) (131%-166%) and deceleration counts (dec_counts) (108%-134%), by all positions. However, relative to match values, training values for sprint distance (sprint_dist) and high-intensity run distance (HIR_dist) were considerably lower (36%-61% and 57%-71%) than for accelerations and decelerations. The most pronounced difference on the 5-min peaks was observed in sprints (sprint_peak), with wing-backs achieving during the microcycle only 64% of the sprint_peak in matches, while centre backs, centre midfielders, and centre forwards levelled and overperformed the match values (107%, 100%, and 107%, respectively). Differences observed across playing positions in matches and microcycles underline the lack of position specificity of common training drills/sessions adopted by coaches in elite football.

On-Ice Physical Demands of World-Class Women's Ice Hockey: From Training to Competition

PURPOSE

To compare on-ice external and internal training loads in world-class women's ice hockey during training and competition.

METHODS

On-ice training loads were collected during 1 season from 25 world-class ice hockey players via wearable technology. A total of 105 on-ice sessions were recorded, which consisted of 61 training sessions and 44 matches. Paired and unpaired t tests compared training and competition data between and across playing positions.

RESULTS

For training data, there was a difference between positions for PlayerLoad (P < .001, effect size [ES] = 0.32), PlayerLoad·minute-1 (P < .001, ES = 0.55), explosive efforts (P < .001, ES = 0.63), and training impulse (P < .001, ES = 0.48). For the competition data, there were also differences between positions for PlayerLoad (P < .001, ES = 0.26), PlayerLoad·minute-1 (P < .001, ES = 0.38), explosive efforts (P < .001, ES = 0.64), and training impulse (P < .001, ES = 1.47). Similar results were found when positions were viewed independently; competition had greater load and intensity across both positions for PlayerLoad, training impulse, and explosive efforts (P < .001, ES = 1.59-2.98) and with PlayerLoad·minute-1 (P = .016, ES = 0.25) for the defense.

CONCLUSIONS

There are clear differences in the volume and intensity of external and internal workloads between training and competition sessions. These differences were also evident when comparing the playing positions, with defense having lower outputs than forwards. These initial results can be used to design position-specific drills that replicate match demands for ice hockey athletes.

A 2-Year Prospective Study of Injury Epidemiology in Elite Australian Rugby Sevens: Exploration of Incidence Rates, Severity, Injury Type, and Subsequent Injury in Men and Women

BACKGROUND

Injuries are common in rugby sevens, but studies to date have been limited to short, noncontinuous periods and reporting of match injuries only.

PURPOSE

To report the injury incidence rate (IIR), severity, and burden of injuries sustained by men and women in the Australian rugby sevens program and to provide the first longitudinal investigation of subsequent injury occurrence in rugby sevens looking beyond tournament injuries only.

STUDY DESIGN

Descriptive epidemiology study.

METHODS

Ninety international rugby sevens players (55 men and 35 women) were prospectively followed over 2 consecutive seasons (2015-2016 and 2016-2017). All medical attention injuries were reported irrespective of time loss. Individual exposure in terms of minutes, distance, and high-speed distance was captured for each player for matches and on-field training, with the use of global positioning system devices. The IIR and injury burden (IIR × days lost to injury) were calculated per 1000 player-hours, and descriptive analyses were performed.

RESULTS

Seventy-three players (81.1%) sustained 365 injuries at an IIR of 43.2 per 1000 player-hours (95% CI, 43.0-43.3). As compared with male players, female players experienced a lower IIR (incidence rate ratio, 0.91; 95% CI, 0.90-0.91). Female players also sustained a higher proportion of injuries to the trunk region (relative risk, 1.75; 95% CI, 1.28-2.40) but a lower number to the head/neck region (relative risk, 0.58; 95% CI, 0.37-0.93; P = .011). The majority (80.7%) of subsequent injuries were of a different site and nature than previous injuries. A trend toward a reduced number of days, participation time, distance, and high-speed distance completed before the next injury was observed after successive injury occurrence.

CONCLUSION

Female players have a lower IIR than male players, with variation of injury profiles observed between sexes. With a surveillance period of 2 years, subsequent injuries account for the majority of injuries sustained in rugby sevens, and they are typically different from previous types of sustained injuries. After each successive injury, the risk profile for future injury occurrence appears to be altered, which warrants further investigation to inform injury prevention strategies in rugby sevens.

Should player fatigue be the focus of injury prevention strategies for international rugby sevens tournaments?

OBJECTIVE

To assess the incidence, severity and nature of injuries, to determine risk factors for injury and to identify potential injury prevention strategies in men's international Rugby-7s tournaments.

DESIGN

A prospective cohort study.

PARTICIPANTS

Players from core teams competing in matches at 6 Sevens World Series from 2008/2009 to 2014/2015.

RESULTS

The incidence of injury across all Series was 108.3 injuries/1000 player-match-hours (backs: 121.0; forwards: 91.5) with a mean severity of 44.2 days (backs: 46.1; forwards: 40.9) and a median severity of 28 days (backs: 29; forwards: 26). The proportion of injuries sustained in the second half was significantly higher (60%; p<0.001) than the first half of matches and the proportion increased from match to match and day to day in a tournament. The knee (17.4%), ankle (15.9%) and posterior thigh (13.2%) were the most common injury locations for backs and the knee (18.5%), head/face (17.3%) and shoulder/clavicle (13.0%) for forwards. The four most common injuries across all players were knee ligament (13.0%), ankle ligament (12.8%), concussion (10.4%) and posterior thigh muscle strains (9.8%).

CONCLUSIONS

The incidence of injury in Rugby-7s suggests that teams require squads of around 20 players for a Sevens World Series. The higher incidence of injury in the second half of matches is probably the result of player fatigue; therefore, injury prevention strategies for teams and the Governing Body should address this issue. The results presented support the World Rugby trial allowing 'rolling substitutes' during Sevens World Series matches, as this approach may help to mitigate the effects of player fatigue during the second half of matches.