Wearable microtechnology can accurately identify collision events during professional rugby league match-play

Professional soccer practitioners' perceptions of using performance analysis technology to monitor technical and tactical player characteristics within an academy environment: A category 1 club case study

This study aimed to identify professional soccer practitioners' perceptions of the application of performance analysis technology within a single academy club. Secondary aims were to understand the importance that practitioners place on monitoring technical and tactical player characteristics, current practices, and barriers to implementing wearable technology. Utilising a mixed method design, forty-four professional soccer academy practitioners (Age = 32 ± 5.8; Years of experience = 8.5 ± 6.2) completed an online survey intended to examine present trends, professional practices, and perceptions regarding the monitoring of technical and tactical metrics. Frequency and percentages of responses for individual items were calculated. Subsequently, eleven participants who were directly involved with the monitoring of players were recruited to participate in a semi-structured interview. Interview data was transcribed and analysed using a combination of deductive and inductive approaches to identify key themes. The main findings across both phases of the study were that (1) technical and tactical metrics are monitored more frequently in matches (Technical: 89%; tactical: 91%) than training (Technical: 80%; Tactical 64%), predominantly due to time constraints and staffing numbers. Accordingly, practitioners believe that it would be beneficial to have an automated way of tracking technical (79%) and tactical (71%) metrics and would consider using a foot-mounted IMU to do so (technical (68%) and tactical (57%)). (2) Monitoring technical and tactical metrics is beneficial to assist with player development and to enrich feedback provision (3) Key stake holders, coaches and players should be informed of the relevance and rationale for monitoring. (4) For successful implementation and continued uptake, the information delivered needs to be both meaningful and easy to understand. Findings suggest that although participants appreciate the need to collect technical and tactical metrics, they are keen to ensure that wearable-derived data does not replace experiential and contextual knowledge. Accordingly, practitioners need to work closely with coaches to determine the contexts in which metrics may or may not prove useful. However, as the sample comprised of participants from a single academy, further studies including more practitioners are warranted. Likewise, future research could also extend to include academy soccer players perceptions too.

Quantifying Offense and Defense Workloads in Professional Rugby Union

PURPOSE

Rugby union is a contact team sport demanding high levels of physical capacity, and understanding the match workloads can be useful to inform training. In this study, the factors influencing locomotion and contact workloads for offensive and defensive ball-in-play periods are quantified.

METHODS

Locomotion and contact metrics were collected from global positioning system units and videos for 31 professional players of a Super Rugby team across 14 games in the 2021 season. Data were analyzed with a generalized mixed-model procedure that included effects for type of play, playing position, match outcome, and ball-in-play time. Magnitudes were assessed with standardization, and evidence for substantial magnitudes was derived from sampling uncertainty.

RESULTS

When offense was compared to defense, most metrics showed decisively substantial increases (small to moderate) for forwards and backs. There was decisive evidence that locomotion metrics were substantially lower (large differences) and contact metrics were higher (very large differences) when comparing forwards to backs on offense and defense. When winning was compared to losing, there was good evidence that forwards experienced small increases in overall workload on defense, and backs experienced a small increase in high-speed running and a moderate decrease in contacts on offense. Match-to-match changes associated with ball-in-play time, attributed to fatigue, were decisive (moderate to very large) across most metrics for forwards and backs in offense and defense.

CONCLUSIONS

The increased locomotion and contact workloads in offensive periods and the differing physical requirements between positions and match outcomes for both types of play are novel findings that should aid practitioners in designing effective training.

Assessing the Relationship Between External Workloads and Noncontact Injuries During Summer Conditioning and Preseason Practice in National Collegiate Athletic Association Division 1 Football Players

ABSTRACT

Burghardt, WP, Pfeiffer, KA, and Kuenze, C. Assessing the relationship between external workloads and noncontact injuries during summer conditioning and preseason practice in National Collegiate Athletic Association Division 1 football players. J Strength Cond Res 37(4): 816-822, 2023-The purpose of this study was to prospectively investigate the relationship between noncontact injuries and workload in collegiate football during summer conditioning and preseason training. Workload and noncontact injury data were collected over the summer conditioning and preseason practice periods for a Division 1 National Collegiate Athletic Association football team ( n = 34). Seven- and 21-day exponentially weighted moving averages (EWMA) were calculated daily for each athlete. The acute:chronic ratio (A:C ratio) of these 2 measures was also calculated daily. Injury rates for noncontact injuries were calculated for both periods. Continuous variable modeling (panel logistic regression and restricted cubic spline) was used to assess the relationship of EWMA A:C ratio and noncontact injury using a 3-day lag period. Athletic exposures (AEs) were defined as individual sport training, practice, or competition sessions. Nine injuries were observed (6.97/1,000 AEs), with 4 injuries resulting in lost time (3.09/1,000 AEs). The mean EWMA A:C ratio was 0.92 ± 0.41 (95% confidence interval: 0.03-2.09). Both the panel logistic regression and the restricted cubic spline models showed a significant relationship between EWMA A:C ratio and noncontact injuries. However, the odds ratio (14.16) in the logistic regression had a very large standard error (14.51) and a wide 95% confidence interval (1.90-105.49). The restricted cubic spline model had a pseudo R2 of 0.136. Injury occurrence at given EWMA ratio values was lower than reported in previous research. Although both continuous models demonstrated a significant relationship between the EWMA A:C ratio and subsequent noncontact injuries over the next 3 days, neither model had sufficient goodness of fit to warrant adoption at this time.

The Influence of Physical Contact on Athlete Load in International Female Rugby Sevens

ABSTRACT

Epp-Stobbe, A, Tsai, M-C, Morris, C, and Klimstra, M. The influence of physical contact on athlete load in international female rugby sevens. J Strength Cond Res 37(2): 383-387, 2023-Although self-reported rate of perceived exertion (RPE) is a simple and popular metric for monitoring player loads, this holistic measure may not adequately represent the distinct contributing factors to athlete loading in team sports, such as contact load. The purpose of this investigation is to determine the relationship between the number of contacts experienced and playing time on RPE in elite women's rugby sevens athletes during competition. Additionally, we examine the contribution of the number of contacts and playing time to RPE. The data collected included RPE, playing time, and number of contacts from 1 team participating in 74 international women's sevens matches. The relationship was modeled using multiple linear regression. Results, including the coefficients for the number of contacts and playing time, were significant (p < 0.001), and R2adjusted was 0.3063. Because contacts are accounted for within the measure of RPE in the proposed model, this further supports the value of RPE as a global measure of athlete experience. However, this study has found a different relationship between RPE and playing time dependent on the number of contacts, such that the influence of playing time on RPE decreases as the number of contacts increase. Ultimately, this may mean that the weighting of individual salient factors affecting player loads, such as the number of contacts or playing time, depend on the levels of all known and potentially unknown factors experienced and may limit the use of RPE when contextualizing player load across athletes. Taken together, the findings suggest that the number of contacts, playing time, and RPE should be considered when monitoring athlete loads while further substantiating the need for more, and higher resolution, measures to better quantify competition loads in contact team sports.

Prototype Machine Learning Algorithms from Wearable Technology to Detect Tennis Stroke and Movement Actions

This study evaluated the accuracy of tennis-specific stroke and movement event detection algorithms from a cervically mounted wearable sensor containing a triaxial accelerometer, gyroscope and magnetometer. Stroke and movement data from up to eight high-performance tennis players were captured in match-play and movement drills. Prototype algorithms classified stroke (i.e., forehand, backhand, serve) and movement (i.e., "Alert", "Dynamic", "Running", "Low Intensity") events. Manual coding evaluated stroke actions in three classes (i.e., forehand, backhand and serve), with additional descriptors of spin (e.g., slice). Movement data was classified according to the specific locomotion performed (e.g., lateral shuffling). The algorithm output for strokes were analysed against manual coding via absolute (n) and relative (%) error rates. Coded movements were grouped according to their frequency within the algorithm's four movement classifications. Highest stroke accuracy was evident for serves (98%), followed by groundstrokes (94%). Backhand slice events showed 74% accuracy, while volleys remained mostly undetected (41-44%). Tennis-specific footwork patterns were predominantly grouped as "Dynamic" (63% of total events), alongside successful linear "Running" classifications (74% of running events). Concurrent stroke and movement data from wearable sensors allows detailed and long-term monitoring of tennis training for coaches and players. Improvements in movement classification sensitivity using tennis-specific language appear warranted.

Tackle Technique and Changes in Playerload™ During a Simulated Tackle: An Exploratory Study

In collision sports, the tackle has the highest injury incidence, and is key to a successful performance. Although the contact load of players has been measured using microtechnology, this has not been related to tackle technique. The aim of this study was to explore how PlayerLoad™ changes between different levels of tackling technique during a simulated tackle. Nineteen rugby union players performed twelve tackles on a tackle contact simulator (n = 228 tackles). Each tackle was recorded with a video-camera and each player wore a Catapult OptimEyeS5. Tackles were analysed using tackler proficiency criteria and split into three categories: Low scoring(≤5 Arbitrary units (AU), medium scoring(6 and 7AU) and high scoring tackles(≥8AU). High scoring tackles recorded a higher PlayerLoad™ at tackle completion. The PlayerLoad™ trace was also less variable in the high scoring tackles. The variability in the PlayerLoad™ trace may be a consequence of players not shortening their steps before contact. This reduced their ability to control their movement during the contact and post-contact phase of the tackle and increased the variability. Using the PlayerLoad™ trace in conjunction with subjective technique assessments offers coaches and practitioners insight into the physical-technical relationship of each tackle to optimise tackle skill training and match preparation.

The field and resistance training loads of academy rugby league players during a pre-season: Comparisons across playing positions

Male academy rugby league players are required to undertake field and resistance training to develop the technical, tactical and physical qualities important for success in the sport. However, limited research is available exploring the training load of academy rugby league players. Therefore, the purpose of this study was to quantify the field and resistance training loads of academy rugby league players during a pre-season period and compare training loads between playing positions (i.e., forwards vs. backs). Field and resistance training load data from 28 adolescent male (age 17 ± 1 years) rugby league players were retrospectively analysed following a 13-week pre-season training period (85 total training observations; 45 field sessions and 40 resistance training sessions). Global positioning system microtechnology, and estimated repetition volume was used to quantify external training load, and session rating of perceived exertion (sRPE) was used to quantify internal training load. Positional differences (forwards n = 13 and backs n = 15) in training load were established using a linear mixed effect model. Mean weekly training frequency was 7 ± 2 with duration totaling 324 ± 137 minutes, and a mean sRPE of 1562 ± 678 arbitrary units (AU). Backs covered more high-speed distance than forwards in weeks two (p = 0.024), and 11 (p = 0.028). Compared to the forwards, backs completed more lower body resistance training volume in week one (p = 0.02), more upper body volume in week three (p< 0.001) and week 12 (p = 0.005). The findings provide novel data on the field and resistance-based training load undertaken by academy rugby league players across a pre-season period, highlighting relative uniformity between playing positions. Quantifying training load can support objective decision making for the prescription and manipulation of future training, ultimately aiming to maximise training within development pathways.

The Distribution of Match Activities Relative to the Maximal Mean Intensities in Professional Rugby League and Australian Football

ABSTRACT

Johnston, RD, Thornton, HR, Wade, JA, Devlin, P, and Duthie, GM. The distribution of match activities relative to the maximal mean intensities in professional rugby league and Australian football. J Strength Cond Res 36(5): 1360-1366, 2022-This study determined the distribution of distance, impulse, and accelerometer load accumulated at intensities relative to the maximal mean 1-minute peak intensity within professional rugby league and Australian football. Within 26 rugby league (n = 24 athletes) and 18 Australian football (n = 38 athletes) games, athletes wore global navigation satellite system devices (n = 608 match files). One-minute maximal mean values were calculated for each athlete per game for speed (m·minP-1P), accelerometer load (AU·minP-1P), and acceleration (m·sP-2P). Volumes for each parameter were calculated by multiplying by time, specifying total distance, accelerometer load, and impulse. The distribution of intensity of which these variables were performed relative to the maximal mean was calculated, with percentages ranging from 0-110%, separated into 10% thresholds. Linear mixed models determined whether the distribution of activities within each threshold varied, and positional differences. Effects were described using standardized effect sizes (ESs), and magnitude-based decisions. Across both sports, the distribution of activity (%) largely reduced the closer to the maximal mean 1-minute peak and was highest at ∼60% of the maximal mean peak. When compared with Australian football, a higher percentage of total distance was accumulated at higher intensities (70-80% and 100-110%) for rugby league (ES range = 0.82-0.87), with similar, yet larger differences for accelerometer load >80% (0.78-1.07) and impulse >60% (1.00-2.26). These findings provide information of the volume of activities performed relative to the mean maximal 1-minute peak period, which may assist in the prescription of training.

Impact and workload are dominating on-field data monitoring techniques to track health and well-being of team-sports athletes

Participation in sports has become an essential part of healthy living in today's world. However, injuries can often occur during sports participation. With advancements in sensor technology and data analytics, many sports have turned to technology-aided, data-driven, on-field monitoring techniques to help prevent injuries and plan better player management. This review searched three databases, Web of Science, IEEE, and PubMed, for peer-reviewed articles on on-field data monitoring techniques that are aimed at improving the health and well-being of team-sports athletes. It was found that most on-field data monitoring methods can be categorized as either player workload tracking or physical impact monitoring. Many studies covered during this review attempted to establish correlations between captured physical and physiological data, as well as injury risk. In these studies, workloads are frequently tracked to optimize training and prevent overtraining in addition to overuse injuries, while impacts are most often tracked to detect and investigate traumatic injuries. This review found that current sports monitoring practices often suffer from a lack of standard metrics and definitions. Furthermore, existing data-analysis models are created on data that are limited in both size and diversity. These issues need to be addressed to create ecologically valid approaches in the future.

Tracking Systems in Team Sports: A Narrative Review of Applications of the Data and Sport Specific Analysis

Seeking to obtain a competitive advantage and manage the risk of injury, team sport organisations are investing in tracking systems that can quantify training and competition characteristics. It is expected that such information can support objective decision-making for the prescription and manipulation of training load. This narrative review aims to summarise, and critically evaluate, different tracking systems and their use within team sports. The selection of systems should be dependent upon the context of the sport and needs careful consideration by practitioners. The selection of metrics requires a critical process to be able to describe, plan, monitor and evaluate training and competition characteristics of each sport. An emerging consideration for tracking systems data is the selection of suitable time analysis, such as temporal durations, peak demands or time series segmentation, whose best use depends on the temporal characteristics of the sport. Finally, examples of characteristics and the application of tracking data across seven popular team sports are presented. Practitioners working in specific team sports are advised to follow a critical thinking process, with a healthy dose of scepticism and awareness of appropriate theoretical frameworks, where possible, when creating new or selecting an existing metric to profile team sport athletes.

Quantifying Collision Frequency and Intensity in Rugby Union and Rugby Sevens: A Systematic Review

BACKGROUND

Collisions in rugby union and sevens have a high injury incidence and burden, and are also associated with player and team performance. Understanding the frequency and intensity of these collisions is therefore important for coaches and practitioners to adequately prepare players for competition. The aim of this review is to synthesise the current literature to provide a summary of the collision frequencies and intensities for rugby union and rugby sevens based on video-based analysis and microtechnology.

METHODS

A systematic search using key words was done on four different databases from 1 January 1990 to 1 September 2021 (PubMed, Scopus, SPORTDiscus and Web of Science).

RESULTS

Seventy-three studies were included in the final review, with fifty-eight studies focusing on rugby union, while fifteen studies explored rugby sevens. Of the included studies, four focused on training-three in rugby union and one in sevens, two focused on both training and match-play in rugby union and one in rugby sevens, while the remaining sixty-six studies explored collisions from match-play. The studies included, provincial, national, international, professional, experienced, novice and collegiate players. Most of the studies used video-based analysis (n = 37) to quantify collisions. In rugby union, on average a total of 22.0 (19.0-25.0) scrums, 116.2 (62.7-169.7) rucks, and 156.1 (121.2-191.0) tackles occur per match. In sevens, on average 1.8 (1.7-2.0) scrums, 4.8 (0-11.8) rucks and 14.1 (0-32.8) tackles occur per match.

CONCLUSIONS

This review showed more studies quantified collisions in matches compared to training. To ensure athletes are adequately prepared for match collision loads, training should be prescribed to meet the match demands. Per minute, rugby sevens players perform more tackles and ball carries into contact than rugby union players and forwards experienced more impacts and tackles than backs. Forwards also perform more very heavy impacts and severe impacts than backs in rugby union. To improve the relationship between matches and training, integrating both video-based analysis and microtechnology is recommended. The frequency and intensity of collisions in training and matches may lead to adaptations for a "collision-fit" player and lend itself to general training principles such as periodisation for optimum collision adaptation. Trial Registration PROSPERO registration number: CRD42020191112.

A GNSS-based method to define athlete manoeuvrability in field-based team sports

This study presented a method of quantifying the manoeuvrability of two field-based team sport athletes and investigated its relationship with running velocity during competition. Across a season, 10 Hz Global navigation satellite system (GNSS) devices were worn during matches by 62 athletes (Australian Football League [AFL]; n = 36, 17 matches, National Rugby League [NRL]; n = 26, 21 matches). To quantify manoeuvrability, tortuosity was calculated from the X and Y coordinates from match GNSS files (converted from latitude and longitude). Tortuosity was calculated as 100 x natural logarithm of the chord distance (distance travelled between X and Y coordinates), divided by the straight-line distance. The maximal tortuosity was then quantified for each 0.5 m∙s-1 speed increment, ranging from 0 to the highest value for each game file. A quadratic model was fitted for each match file, controlling for the curvilinear relationship between tortuosity and velocity. A comparison of the quadratic coefficients between sports, and within sport between positions was investigated using linear mixed models. Resulting standard deviations (SDs) and mean differences were then assessed to establish standardized effect sizes (ES) and 90% confidence intervals (CI). A curvilinear relationship exists between maximal tortuosity and running speed, reflecting that as speed increases, athletes' ability to deviate from a linear path is compromised (i.e., run in a more linear path). Compared to AFL, NRL had a greater negative quadratic coefficient (a) (ES = 0.70; 0.47 to 0.93) for the 5 second analysis, meaning that as speed increased, NRL athletes' manoeuvrability reduced at a faster rate than when compared to AFL. There were no positional differences within each sport. GNSS derived information can be used to provide a measure of manoeuvrability tortuosity during NRL and AFL matches. The curvilinear relationship between tortuosity and speed demonstrated that as speed increased, manoeuvrability was compromised.

Validity of Real-Time Ultra-wideband Global Navigation Satellite System Data Generated by a Wearable Microtechnology Unit

Johnston, RD, Hewitt, A, and Duthie, G. Validity of real-time ultra-wideband global navigation satellite system data generated by a wearable microtechnology unit. J Strength Cond Res 34(7): 2071-2075, 2020-This study aimed to determine the validity of real-time ultra-wideband data generated by a wearable microtechnology unit during rugby league training sessions using a repeated-measures crossover study. Twenty-four semiprofessional rugby league players wore a commercially available microtechnology device (StatSports Apex, Newry, Northern Ireland) during 10 training sessions. Total distance; moderate-speed running (3.6-4.9 m·s); high-speed running (5.0-6.9 m·s); very high-speed running (≥7 m·s); maximum velocity (m·s); the number of high-intensity accelerations (≥2.78 m·s) and decelerations (≥-2.78 m·s); dynamic stress load (AU); and high metabolic load distance (m) were recorded in real time through an Apex beacon over a secured wireless network before being exported to a csv file at the end of the session. The data were then downloaded to a computer after event. To determine the validity of the real-time data, they were compared with the postevent downloaded data using coefficient of variation and Pearson's correlation coefficient. There was almost perfect agreement between real-time and postevent downloaded data for all variables reported. The overall bias effect size scores were all trivial, ranging from 0.00 for total distance and high-speed running up to -0.12 for maximal velocity; Pearson's correlations were either perfect or nearly perfect (r = 0.98-1.00). Irrespective of the movement speed, the data collected by these devices in real time show excellent levels of agreement with postevent downloaded data.

The Validity and Reliability of Wearable Microtechnology for Intermittent Team Sports: A Systematic Review

BACKGROUND

Technology has long been used to track player movements in team sports, with initial tracking via manual coding of video footage. Since then, wearable microtechnology in the form of global and local positioning systems has provided a less labour-intensive way of monitoring movements. As such, there has been a proliferation in research pertaining to these devices.

OBJECTIVE

A systematic review of studies that investigate the validity and/or reliability of wearable microtechnology to quantify movement and specific actions common to intermittent team sports.

METHODS

A systematic search of CINAHL, MEDLINE, and SPORTDiscus was performed; studies included must have been (1) original research investigations; (2) full-text articles written in English; (3) published in a peer-reviewed academic journal; and (4) assessed the validity and/or reliability of wearable microtechnology to quantify movements or specific actions common to intermittent team sports.

RESULTS

A total of 384 studies were retrieved and 187 were duplicates. The titles and abstracts of 197 studies were screened and the full texts of 88 manuscripts were assessed. A total of 62 studies met the inclusion criteria. Additional 10 studies, identified via reference list assessment, were included. Therefore, a total of 72 studies were included in this review.

CONCLUSION

There are many studies investigating the validity and reliability of wearable microtechnology to track movement and detect sport-specific actions. It is evident that for the majority of metrics, validity and reliability are multi-factorial, in that it is dependent upon a wide variety of factors including wearable technology brand and model, sampling rate, type of movement performed (e.g., straight line, change of direction) and intensity of movement (e.g., walk, sprint). Practitioners should be mindful of the accuracy and repeatability of the devices they are using when making decisions on player training loads.

Profiling the Post-match Recovery Response in Male Rugby: A Systematic Review

Aben, HGJ, Hills, SP, Cooke, CB, Davis, D, Jones, B, and Russell, M. Profiling the post-match recovery response in male rugby: A systematic review. J Strength Cond Res XX(X): 000-000, 2020-To minimize underperformance, injury, and illness, and to enhance readiness for training and match-play, post-match responses are commonly monitored within professional rugby. As no clear consensus exists regarding the magnitude and duration of post-match recovery, this review summarized the literature (17 studies yielded from literature searching/screening) reporting neuromuscular (countermovement jump [CMJ], peak power output [PP], and flight time [FT]), biochemical (creatine kinase [CK]) or endocrine (cortisol [C] and testosterone [T] concentrations), and subjective (wellness questionnaire and muscle soreness) indices after rugby match-play. For neuromuscular responses (11 studies), reductions in PP <31.5% occurred <30 minutes after match, returning to baseline within 48-72 hours. Post-match reductions in FT of <4% recovered after 48 hours. For biochemical and endocrine responses (14 studies), increases in CK, ranging from 120 to 451%, peaked between 12 and 24 hours, returning to baseline within 72 hours of match-play. Initial increases of <298% in C and reductions in T concentrations (<44%) returned to pre-match values within 48-72 hours. Mood disturbances (6 studies) required 48-72 hours to normalize after peak decrements of <65% at 24 hours. This review highlights that 72 hours were needed to restore perturbations in neuromuscular, biochemical and endocrine, and subjective/perceptual responses after competitive rugby match-play. Notably, only 4 studies reported responses in more ecologically valid scenarios (i.e., those in which regular training and recovery strategies were used) while also reporting detailed match demands. A lack of research focusing on youth players was also evident, as only 3 studies profiled post-match responses in younger athletes. Deeper insight regarding post-match responses in ecologically valid scenarios is therefore required.

The Validity of Automated Tackle Detection in Women's Rugby League

Cummins, C, Charlton, G, Naughton, M, Jones, B, Minahan, C, and Murphy, A. The validity of automated tackle detection in women's rugby league. J Strength Cond Res XX(X): 000-000, 2020-This study assessed the validity of microtechnology devices to automatically detect and differentiate tackles in elite women's rugby league match-play. Elite female players (n = 17) wore a microtechnology device (OptimEye S5 device; Catapult Group International) during a representative match, which involved a total of 512 tackles of which 365 were defensive and 147 were attacking. Tackles automatically detected by Catapult's tackle detection algorithm and video-coded tackles were time synchronized. True positive, false negative and false positive events were utilized to calculate sensitivity (i.e., when a tackle occurred, did the algorithm correctly detect this event) and precision (i.e., when the algorithm reported a tackle, was this a true event based on video-coding). Of the 512 video-derived attacking and defensive tackle events, the algorithm was able to detect 389 tackles. The algorithm also produced 81 false positives and 123 false negatives. As such when a tackle occurred, the algorithm correctly identified 76.0% of these events. When the algorithm reported that a tackle occurred, this was an actual event in 82.8% of circumstances. Across all players, the algorithm was more sensitive to the detection of an attacking event (sensitivity: 78.2%) as opposed to a defensive event (sensitivity: 75.1%). The sensitivity and precision of the algorithm was higher for forwards (sensitivity: 81.8%; precision: 92.1%) when compared with backs (sensitivity: 64.5%; precision: 66.1%). Given that understanding the tackle demands of rugby league is imperative from both an injury-prevention and physical-conditioning perspective there is an opportunity to develop a specific algorithm for the detection of tackles within women's rugby league.

Locomotor characteristics of the women's inaugural super league competition and the rugby league world cup

Understanding the locomotor characteristics of competition can help rugby league (RL) coaches optimise training prescription. To date, no research exists on the locomotor characteristics of women's RL. The aim was to compare whole match and peak locomotor characteristics of women's RL competition at international (RL World Cup [WRLWC]) and domestic level (Super League [WSL]). Microtechnology data were collected from 58 players from 3-WSL clubs and 1-WRLWC team. Participants were classified into forwards (n = 30) and backs (n = 28). Partial least squares correlation analysis established which variables were important to discriminate between the level of competition (international vs. domestic) and positional group (forwards vs. backs). Linear mixed-effects models estimated the differences between standards of competition and positional group for those variables. International forwards were most likely exposed to greater peak 1-min average acceleration (standardised mean difference = 1.23 [0.42 to 2.04]) and peak 3-min average acceleration (1.13 [0.41 to 1.85]) than domestic forwards. International backs likely completed greater peak 1-min average acceleration (0.83 [0.08 to 1.58]) than domestic backs and possibly greater high-speed-distances (0.45 [-0.17 to 1.07]). Findings highlight the need for positional specific training across levels to prepare representative players for the increased match characteristics of international competition.

Sensitivity, reliability and construct validity of GPS and accelerometers for quantifying peak periods of rugby competition

Training prescription and monitoring of team-sport athletes rely on accurate quantification of player movement. Our aim was to determine the sensitivity, reliability and construct validity of measures derived from a wearable device incorporating Global Positioning System (GPS) and accelerometer technology to quantify the peak periods of rugby competition. Match movement data were collected from 30 elite and 30 sub-elite rugby union players across respective competitive seasons. Accelerometer and GPS measures were analysed using a rolling average to identify peak movement for epochs ranging from 5 to 600 seconds. General linear mixed modelling was used to quantify the effects of playing position and match-half on the peak movement and variabilities within and between players represented reliability of each measure. Mean positional differences and match-half changes were assessed via standardisation and magnitude-based decisions. Sensitivity of measures was quantified via evaluation of ("signal") and typical error of measurement ("noise"). GPS and accelerometer measures had poor sensitivity for quantifying peak movement across all epochs and both levels of rugby union competition (noise 4× to 5× the signal). All measures displayed correspondingly low reliability across most epochs and both levels of competition (ICC<0.50). Construct validity was evident in mean differences between playing positions and match halves that were consistent with expected activity profiles in rugby union. However, it was clear from the pattern of differences across epoch durations and levels of competition that GPS and accelerometer measures provided different information about player movement. The poor sensitivity and low reliability of GPS and accelerometer measures of peak movement imply that rugby union players need to be monitored across many matches to obtain adequate precision for assessing individuals. Although all measures displayed construct validity, accelerometers provided meaningful information additional to that of GPS. We recommend using accelerometers alongside GPS to monitor and prescribe match respresentative training.

Auto detecting deliveries in elite cricket fast bowlers using microsensors and machine learning

Cricket fast bowlers are at a high risk of injury occurrence, which has previously been shown to be correlated to bowling workloads. This study aimed to develop and test an algorithm that can automatically, reliably and accurately detect bowling deliveries. Inertial sensor data from a Catapult OptimEye S5 wearable device was collected from both national and international level fast bowlers (n = 35) in both training and matches, at various intensities. A machine-learning based approach was used to develop the algorithm. Outputs were compared with over 20,000 manually recorded events. A high Matthews correlation coefficient (r = 0.945) showed very good agreement between the automatically detected bowling deliveries and manually recorded ones. The algorithm was found to be both sensitive and specific in training (96.3%, 98.3%) and matches (99.6%, 96.9%), respectively. Rare falsely classified events were typically warm-up deliveries or throws preceded by a run. Inertial sensors data processed by a machine-learning based algorithm provide a valid tool to automatically detect bowling events, whilst also providing the opportunity to look at performance metrics associated with fast bowling. This offers the possibility to better monitor bowling workloads across a range of intensities to mitigate injury risk potential and maximise performance.

Development of a Human Activity Recognition System for Ballet Tasks

Background

Accurate and detailed measurement of a dancer’s training volume is a key requirement to understanding the relationship between a dancer’s pain and training volume. Currently, no system capable of quantifying a dancer’s training volume, with respect to specific movement activities, exists. The application of machine learning models to wearable sensor data for human activity recognition in sport has previously been applied to cricket, tennis and rugby. Thus, the purpose of this study was to develop a human activity recognition system using wearable sensor data to accurately identify key ballet movements (jumping and lifting the leg). Our primary objective was to determine if machine learning can accurately identify key ballet movements during dance training. The secondary objective was to determine the influence of the location and number of sensors on accuracy.

Results

Convolutional neural networks were applied to develop two models for every combination of six sensors (6, 5, 4, 3, etc.) with and without the inclusion of transition movements. At the first level of classification, including data from all sensors, without transitions, the model performed with 97.8% accuracy. The degree of accuracy reduced at the second (83.0%) and third (75.1%) levels of classification. The degree of accuracy reduced with inclusion of transitions, reduction in the number of sensors and various sensor combinations.

Conclusion

The models developed were robust enough to identify jumping and leg lifting tasks in real-world exposures in dancers. The system provides a novel method for measuring dancer training volume through quantification of specific movement tasks. Such a system can be used to further understand the relationship between dancers’ pain and training volume and for athlete monitoring systems. Further, this provides a proof of concept which can be easily translated to other lower limb dominant sporting activities

Using Smart Sensors to Monitor Physical Activity and Technical-Tactical Actions in Junior Tennis Players

The use of smart devices to obtain real-time data has notably increased in the context of training. These technological tools provide data which monitor the external load and technical–tactical actions related to psychological and physical health in junior tennis players. The purpose of this paper is to monitor technical–tactical actions and physical activity during a current tennis competition in the Green stage using a Zepp Tennis Smart Sensor 2. The participants were 20 junior tennis players (under 10 years of age), with an average age of 9.46 years. The total number of strokes (n= 21,477) during 75 matches was analyzed. The study variables were the following aspects: (a) number of strokes, (b) ball impact in the sweet spot; (c) racket speed; (d) ball spin; (e) calories burned; and (f) match time. The current system of competition, based on knockout, does not meet the World Health Organization’s recommendations for daily physical activity time. Players mainly used flat forehands with a lack of variability in technical–tactical actions which did not meet the current learning opportunity criteria of comprehensive methodologies. The competition system in under-11 tennis should be adapted to the players’ characteristics by improving the variability and quantity of practice.

An Exploration of Machine-Learning Estimation of Ground Reaction Force from Wearable Sensor Data

This study aimed to develop a wearable sensor system, using machine-learning models, capable of accurately estimating peak ground reaction force (GRF) during ballet jumps in the field. Female dancers (n = 30) performed a series of bilateral and unilateral ballet jumps. Dancers wore six ActiGraph Link wearable sensors (100 Hz). Data were collected simultaneously from two AMTI force platforms and synchronised with the ActiGraph data. Due to sensor hardware malfunctions and synchronisation issues, a multistage approach to model development, using a reduced data set, was taken. Using data from the 14 dancers with complete multi-sensor synchronised data, the best single sensor was determined. Subsequently, the best single sensor model was refined and validated using all available data for that sensor (23 dancers). Root mean square error (RMSE) in body weight (BW) and correlation coefficients (r) were used to assess the GRF profile, and Bland–Altman plots were used to assess model peak GRF accuracy. The model based on sacrum data was the most accurate single sensor model (unilateral landings: RMSE = 0.24 BW, r = 0.95; bilateral landings: RMSE = 0.21 BW, r = 0.98) with the refined model still showing good accuracy (unilateral: RMSE = 0.42 BW, r = 0.80; bilateral: RMSE = 0.39 BW, r = 0.92). Machine-learning models applied to wearable sensor data can provide a field-based system for GRF estimation during ballet jumps.

Quantifying the Collision Dose in Rugby League: A Systematic Review, Meta-analysis, and Critical Analysis

BACKGROUND

Collisions (i.e. tackles, ball carries, and collisions) in the rugby league have the potential to increase injury risk, delay recovery, and influence individual and team performance. Understanding the collision demands of the rugby league may enable practitioners to optimise player health, recovery, and performance.

OBJECTIVE

The aim of this review was to (1) characterise the dose of collisions experienced within senior male rugby league match-play and training, (2) systematically and critically evaluate the methods used to describe the relative and absolute frequency and intensity of collisions, and (3) provide recommendations on collision monitoring.

METHODS

A systematic search of electronic databases (PubMed, SPORTDiscus, Scopus, and Web of Science) using keywords was undertaken. A meta-analysis provided a pooled mean of collision frequency or intensity metrics on comparable data sets from at least two studies.

RESULTS

Forty-three articles addressing the absolute (n) or relative collision frequency (n min^-1) or intensity of senior male rugby league collisions were included. Meta-analysis of video-based studies identified that forwards completed approximately twice the number of tackles per game than backs (n = 24.6 vs 12.8), whilst ball carry frequency remained similar between backs and forwards (n = 11.4 vs 11.2). Variable findings were observed at the subgroup level with a limited number of studies suggesting wide-running forwards, outside backs, and hit-up forwards complete similar ball carries whilst tackling frequency differed. For microtechnology, at the team level, players complete an average of 32.7 collisions per match. Limited data suggested hit-up and wide-running forwards complete the most collisions per match, when compared to adjustables and outside backs. Relative to playing time, forwards (n min^-1 = 0.44) complete a far greater frequency of collision than backs (n min^-1 = 0.16), with data suggesting hit-up forwards undertake more than adjustables, and outside backs. Studies investigating g force intensity zones utilised five unique intensity schemes with zones ranging from 2-3 g to 13-16 g. Given the disparity between device setups and zone classification systems between studies, further analyses were inappropriate. It is recommended that practitioners independently validate microtechnology against video to establish criterion validity.

CONCLUSIONS

Video- and microtechnology-based methods have been utilised to quantify collisions in the rugby league with differential collision profiles observed between forward and back positional groups, and their distinct subgroups. The ball carry demands of forwards and backs were similar, whilst tackle demands were greater for forwards than backs. Microtechnology has been used inconsistently to quantify collision frequency and intensity. Despite widespread popularity, a number of the microtechnology devices have yet to be appropriately validated. Limitations exist in using microtechnology to quantify collision intensity, including the lack of consistency and limited validation. Future directions include application of machine learning approaches to differentiate types of collisions in microtechnology datasets.

Quantification of Internal and External Load in School Football According to Gender and Teaching Methodology

The design of teaching tasks determines the physical and physiological demands that students are exposed to in physical education classes. The purpose of this study is to quantify and compare, according to gender and teaching methodology, the external (eTL) and internal (iTL) load resulting from the application of two programs that follow different teaching methodologies, i.e., a Tactical Games Approach (TGA) and Direct Instruction (DI), to teach school football. The Ratings of Perceived Exertion (RPEs) recorded in the assessments were also studied. A total of 41 students in the fifth year of primary education from a state school from Spain participated in the study (23 boys and 18 girls), aged from 10 to 11 (M ± SD, 10.63 ± 0.49 years) and divided into two class groups. All the sessions were monitored with inertial devices that made it possible to record physical activity and convert the information into kinematic parameters. The results indicated that the students who followed the TGA method recorded higher iTL values (heart rate) and spent more time performing high-intensity activities. Boys recorded higher eTL, iTL, and RPE values than girls. There was an evolution in the RPE between the assessments, with both groups presenting a more efficient RPE in the posttest. The TGA method favors student physical fitness and health, thus, this method is recommended when planning physical education sessions.

Peak movement and collision demands of professional rugby league competition

To quantify the peak movement and contact demands of National Rugby League (NRL) and European Super League (ESL) competition players were tracked during 10 NRL (166 files) and 10 ESL (143 files) matches using microtechnology devices. The peak 1- to 5-min periods were then calculated for average match speed (m·min^-1), and acceleration (m·s^-2) when 0, 1, 2, and ≥3 collisions per min occurred. Linear mixed effect models and Cohen's effect size statistic (± 90%CI) were used to determine the differences in movement profiles when collisions occurred. Compared to no collision periods, as frequency of collisions per minute increased, there were progressive reductions in running speed for most positional groups. The addition of 1 or more collisions per min resulted in average effect size reductions in match speed of -0.14 for NRL forwards, -0.89 for NRL backs, -0.48 for ESL forwards, and -2.41 for ESL backs. ESL forwards had the highest frequency of peak periods involving 3 or more collisions per min, 22% of all periods, followed by NRL forwards (14%), NRL backs (10%) and ESL backs (8%). This study highlights the peak movement and collision demands of professional rugby league competition and allows practitioners to develop training drills that reflect worst case scenarios.

Comparison of Preseason and In-Season Practice and Game Loads in National Collegiate Athletic Association Division I Football Players

Wellman, AD, Coad, SC, Flynn, PJ, Siam, TK, and McLellan, CP. A Comparison of preseason and in-season practice and game loads in NCAA Division I football players. J Strength Cond Res 33(4): 1020-1027, 2019-The aim of this study was to quantify the individual practice and game loads throughout the National Collegiate Athletic Association (NCAA) Division I football season to determine whether significant differences exist between the practice loads associated with the preseason training camp and those undertaken during the in-season period. Thirty-one NCAA Division I football players were monitored using the global positioning system and triaxial accelerometer (IA) (MinimaxX S5; Catapult Innovations, Melbourne, Australia) during 22 preseason practices, 36 in-season practices, and 12 competitions. The season was divided into 4 distinct phases for data analysis: preseason week 1 (preseason 1), preseason week 2 (preseason 2), preseason week 3 (preseason 3), and 12 in-season weeks. Individual IA data sets represented players from every offensive and defensive position group Wide Receiver (WR: n = 5), Offensive Line (OL: n = 4), Running Back (RB: n = 4), Quarterback (QB: n = 2), Tight End (TE: n = 3), Defensive Line (DL: n = 4), Linebacker (LB: n = 4), Defensive Back (DB: n = 5). Data were set at the practice level, where an observation for each player's maximum player load (PLMax) or mean player load (PLMean) from each training camp phase was referenced against each player's respective PL from each game, Tuesday, Wednesday, or Thursday practice session. Notable results included significantly (p ≤ 0.05) greater PLMax values attributed to preseason 1 compared with PL resulting from all in-season practices, and significantly (p ≤ 0.05) higher cumulative PL reported for preseason 1, 2, and 3 compared with every in-season week. Data from this study augment our understanding of the practice demands experienced by NCAA Division I college football players, and provide scope for the improvement of preseason practice design and physical conditioning strategies for coaches seeking to optimize performance.

The Use of Microtechnology to Quantify the Peak Match Demands of the Football Codes: A Systematic Review

BACKGROUND

Quantifying the peak match demands within the football codes is useful for the appropriate prescription of external training load. Wearable microtechnology devices can be used to identify the peak match demands, although various methodologies exist at present.

OBJECTIVES

This systematic review aimed to identify the methodologies and microtechnology-derived variables used to determine the peak match demands, and to summarise current data on the peak match demands in the football codes.

METHODS

A systematic search of electronic databases was performed from earliest record to May 2018; keywords relating to microtechnology, peak match demands and football codes were used.

RESULTS

Twenty-seven studies met the eligibility criteria. Six football codes were reported: rugby league (n = 7), rugby union (n = 5), rugby sevens (n = 4), soccer (n = 6), Australian Football (n = 2) and Gaelic Football (n = 3). Three methodologies were identified: moving averages, segmental and 'ball in play'. The moving averages is the most commonly used (63%) and superior method, identifying higher peak demands than other methods. The most commonly used variables were relative distance covered (63%) and external load in specified speed zones (57%).

CONCLUSION

This systematic review has identified moving averages to be the most appropriate method for identifying the peak match demands in the football codes. Practitioners and researchers should choose the most relevant duration-specific period and microtechnology-derived variable for their specific needs. The code specific peak match demands revealed can be used for the prescription of conditioning drills and training intensity.

Validity of a Microsensor-Based Algorithm for Detecting Scrum Events in Rugby Union

PURPOSE

Commercially available microtechnology devices containing accelerometers, gyroscopes, magnetometers, and global positioning technology have been widely used to quantify the demands of rugby union. This study investigated whether data derived from wearable microsensors can be used to develop an algorithm that automatically detects scrum events in rugby union training and match play.

METHODS

Data were collected from 30 elite rugby players wearing a Catapult OptimEye S5 (Catapult Sports, Melbourne, Australia) microtechnology device during a series of competitive matches (n = 46) and training sessions (n = 51). A total of 97 files were required to "train" an algorithm to automatically detect scrum events using random forest machine learning. A further 310 files from training (n = 167) and match-play (n = 143) sessions were used to validate the algorithm's performance.

RESULTS

Across all positions (front row, second row, and back row), the algorithm demonstrated good sensitivity (91%) and specificity (91%) for training and match-play events when the confidence level of the random forest was set to 50%. Generally, the algorithm had better accuracy for match-play events (93.6%) than for training events (87.6%).

CONCLUSIONS

The scrum algorithm was able to accurately detect scrum events for front-row, second-row, and back-row positions. However, for optimal results, practitioners are advised to use the recommended confidence level for each position to limit false positives. Scrum algorithm detection was better with scrums involving ≥5 players and is therefore unlikely to be suitable for scrums involving 3 players (eg, rugby sevens). Additional contact- and collision-detection algorithms are required to fully quantify rugby union demands.

Automatic detection of one-on-one tackles and ruck events using microtechnology in rugby union

OBJECTIVES

To automate the detection of ruck and tackle events in rugby union using a specifically-designed algorithm based on microsensor data.

DESIGN

Cross-sectional study.

METHODS

Elite rugby union players wore microtechnology devices (Catapult, S5) during match-play. Ruck (n=125) and tackle (n=125) event data was synchronised with video footage compiled from international rugby union match-play ruck and tackle events. A specifically-designed algorithm to detect ruck and tackle events was developed using a random forest classification model. This algorithm was then validated using 8 additional international match-play datasets and video footage, with each ruck and tackle manually coded and verified if the event was correctly identified by the algorithm.

RESULTS

The classification algorithm's results indicated that all rucks and tackles were correctly identified during match-play when 79.4±9.2% and 81.0±9.3% of the random forest decision trees agreed with the video-based determination of these events. Sub-group analyses of backs and forwards yielded similar optimal confidence percentages of 79.7% and 79.1% respectively for rucks. Sub-analysis revealed backs (85.3±7.2%) produced a higher algorithm cut-off for tackles than forwards (77.7±12.2%).

CONCLUSIONS

The specifically-designed algorithm was able to detect rucks and tackles for all positions involved. For optimal results, it is recommended that practitioners use the recommended cut-off (80%) to limit false positives for match-play and training. Although this algorithm provides an improved insight into the number and type of collisions in which rugby players engage, this algorithm does not provide impact forces of these events.

A Narrative Review of the Physical Demands and Injury Incidence in American Football: Application of Current Knowledge and Practices in Workload Management

The sport of American football (AmF) exposes athletes to high-velocity movements and frequent collisions during competition and training, placing them at risk of contact and non-contact injury. Due to the combative nature of the game, the majority of injuries are caused by player contact; however, a significant number are also non-contact soft-tissue injuries. The literature suggests that this mechanism of injury can be prevented through workload monitoring and management. The recent introduction of microtechnology into AmF allows practitioners and coaches to quantify the external workload of training and competition to further understand the demands of the sport. Significant workload differences exist between positions during training and competition; coupling this with large differences in anthropometric and physical characteristics between and within positions suggests that the training response and physiological adaptations will be highly individual. Effective athlete monitoring and management allows practitioners and coaches to identify how athletes are coping with the prescribed training load and, subsequently, if they are prepared for competition. Several evidence-based principles exist that can be adapted and applied to AmF and could decrease the risk of injury and optimise athletic performance.

Modelling Movement Energetics Using Global Positioning System Devices in Contact Team Sports: Limitations and Solutions

Quantifying the training and competition loads of players in contact team sports can be performed in a variety of ways, including kinematic, perceptual, heart rate or biochemical monitoring methods. Whilst these approaches provide data relevant for team sports practitioners and athletes, their application to a contact team sport setting can sometimes be challenging or illogical. Furthermore, these methods can generate large fragmented datasets, do not provide a single global measure of training load and cannot adequately quantify all key elements of performance in contact team sports. A previous attempt to address these limitations via the estimation of metabolic energy demand (global energy measurement) has been criticised for its inability to fully quantify the energetic costs of team sports, particularly during collisions. This is despite the seemingly unintentional misapplication of the model's principles to settings outside of its intended use. There are other hindrances to the application of such models, which are discussed herein, such as the data-handling procedures of Global Position System manufacturers and the unrealistic expectations of end users. Nevertheless, we propose an alternative energetic approach, based on Global Positioning System-derived data, to improve the assessment of mechanical load in contact team sports. We present a framework for the estimation of mechanical work performed during locomotor and contact events with the capacity to globally quantify the work done during training and matches.

Machine and deep learning for sport-specific movement recognition: a systematic review of model development and performance

Objective assessment of an athlete's performance is of importance in elite sports to facilitate detailed analysis. The implementation of automated detection and recognition of sport-specific movements overcomes the limitations associated with manual performance analysis methods. The object of this study was to systematically review the literature on machine and deep learning for sport-specific movement recognition using inertial measurement unit (IMU) and, or computer vision data inputs. A search of multiple databases was undertaken. Included studies must have investigated a sport-specific movement and analysed via machine or deep learning methods for model development. A total of 52 studies met the inclusion and exclusion criteria. Data pre-processing, processing, model development and evaluation methods varied across the studies. Model development for movement recognition were predominantly undertaken using supervised classification approaches. A kernel form of the Support Vector Machine algorithm was used in 53% of IMU and 50% of vision-based studies. Twelve studies used a deep learning method as a form of Convolutional Neural Network algorithm and one study also adopted a Long Short Term Memory architecture in their model. The adaptation of experimental set-up, data pre-processing, and model development methods are best considered in relation to the characteristics of the targeted sports movement(s).

PlayerLoad Variables: Sensitive to Changes in Direction and Not Related to Collision Workloads in Rugby League Match Play

PURPOSE

To determine (1) how change-of-direction (COD) workloads influence PlayerLoad (PL) variables when controlling total distance covered and (2) relationships among collision workloads and PL variables during rugby league match play.

METHODS

Participants completed 3 protocols (crossover design) consisting of 10 repetitions of a 60-m effort in 15 s. The difference between protocols was the COD demands required to complete 1 repetition: no COD (straight line), 1° × 180° COD, or 3° × 180° COD. During rugby league matches, relationships among collision workloads, triaxial vector-magnitude PlayerLoad (PL_VM), anteroposterior + mediolateral PL (PL_2D), and PL_VM accumulated at locomotor velocities below 2 m·s^-1 (ie, PL_SLOW) were examined using Pearson correlations (r) with coefficients of determination (R²).

RESULTS

Comparing 3° × 180° COD to straight-line drills, PL_VM·min^-1 (d = 1.50 ± 0.49, large, likelihood = 100%, almost certainly), PL_2D·min^-1 (d = 1.38 ± 0.53, large, likelihood = 100%, almost certainly), and PL_SLOW·min^-1 (d = 1.69 ± 0.40, large, likelihood = 100%, almost certainly) were greater. Collisions per minute demonstrated a distinct (ie, R² < .50) relationship from PL_VM·min^-1 (R² = .30, r = .55) and PL_2D·min^-1 (R² = .37, r = .61). Total distance per minute demonstrated a very large relationship with PL_VM·min^-1 (R² = .62, r = .79) and PL_2D·min^-1 (R² = .57, r = .76).

CONCLUSIONS

PL variables demonstrate (1) large increases as COD demands intensify, (2) separate relationships from collision workloads, and (3) moderate to very large relationships with total distance during match play. PL variables should be used with caution to measure collision workloads in team sport.

The peak duration-specific locomotor demands and concurrent collision frequencies of European Super League rugby

Understanding the most demanding passages of European Super League competition can optimise training prescription. We established positional and match half differences in peak relative distances (m·min^-1) across durations, and the number of collisions, high-speed- and very-high-speed-distance completed in the peak 10 min period. Moving-averages (10 s, 30 s, 1 min, 5 min, 10 min) of instantaneous speed (m·s^-1) were calculated from 25 professional rugby league players during 25 matches via microtechnology. Maximal m·min^-1 was taken for each duration for each half. Concurrently, collisions (n), high-speed- (5 to 7 m·s^-1; m) and very-high-speed-distance (> 7 m·s^-1; m) were coded during each peak 10 min. Mixed-effects models determined differences between positions and halves. Aside from peak 10 s, trivial differences were observed in peak m·min^-1 between positions or halves across durations. During peak 10 min periods, adjustables, full- and outside-backs ran more at high-speed and very-high-speed whilst middle- and edge-forwards completed more collisions. Peak m·min^-1 is similar between positional groups across a range of durations and are maintained between halves of the match. Practitioners should consider that whilst the overall peak locomotor "intensity" is similar, how they achieve this differs between positions with forwards also exposed to additional collision bouts.

The ball in play demands of international rugby union

OBJECTIVES

Rugby union is a high intensity intermittent sport, typically analysed via set time periods or rolling average methods. This study reports the demands of international rugby union via global positioning system (GPS) metrics expressed as mean ball in play (BiP), maximum BiP (max BiP), and whole match outputs.

DESIGN

Single cohort cross sectional study involving 22 international players, categorised as forwards and backs.

METHODS

A total of 88 GPS files from eight international test matches were collected during 2016. An Opta sportscode timeline was integrated into the GPS software to split the data into BiP periods. Metres per min (mmin^-1), high metabolic load per min (HML), accelerations per min (Acc), high speed running per min (HSR), and collisions per min (Coll) were expressed relative to BiP periods and over the whole match (>60min).

RESULTS

Whole match metrics were significantly lower than all BiP metrics (p<0.001). Mean and max BiP HML, (p<0.01) and HSR (p<0.05) were significantly higher for backs versus forwards, whereas Coll were significantly higher for forwards (p<0.001). In plays lasting 61s or greater, max BiP mmin^-1 were higher for backs. Max BiP mmin^-1, HML, HSR and Coll were all time dependant (p<0.05) showing that both movement metrics and collision demands differ as length of play continues.

CONCLUSIONS

This study uses a novel method of accurately assessing the BiP demands of rugby union. It also reports typical and maximal demands of international rugby union that can be used by practitioners and scientists to target training of worst-case scenario's equivalent to international intensity. Backs covered greater distances at higher speeds and demonstrated higher HML, in general play as well as 'worst case scenarios'; conversely forwards perform a higher number of collisions.