Purpose The aim of this study was to quantify and predict relationships between RPE and GPS training load variables in professional Australian Football (AF) players using group and individualised modelling approaches. Methods Training load data (GPS and RPE) for 41 professional AF players was obtained over a period of 27 weeks. A total of 2711 training observations were analysed with a total of 66 13 sessions per player (range; 39 to 89).Separate generalised estimating equations (GEE) and artificial neural network analyses (ANN) were conducted to determine the ability to predict RPE from training load variables (i.e. session distance, high-speed running (HSR), high-speed running %, m·min Further, importance plots generated from the ANN revealed session distance was most predictive of RPE in 36 of the 41 players, whereas, HSR was predictive of RPE in just 3 players and m . min -1 as predictive as session distance in just 2 players. Conclusions This study demonstrates that machine learning approaches may outperform more traditional methodologies with respect to predicting athlete responses to training load. These approaches enable further individualisation of load monitoring, leading to more accurate training prescription and evaluation.

Elite team sport athletes can undertake a limited amount of training each week. Consequently, designing training drills that improve both skilled and physical performance concurrently and efficiently is of high importance. This study developed three training drill classification systems using physical and skill-related data obtained from Australian Rules football training. Forty professional male athletes from a single elite Australian Rules football club were recruited for this study. All wore a 10 Hz Global Positioning System unit for six matches and 17 training sessions, which included a total of 35 different drills. High intensity running per minute, metres per minute and high intensity running as a percentage of total distance were obtained to provide a representation of each drill's physical requirements. Velocity at kick (moving or stationary), time in possession (greater or less than 2 seconds) and the presence of pressure was manually coded upon each kick to provide a representation of the constraints relating to each training drill. For the first prescription system, two k-means clustering algorithms were run on physical and skill data separately to identify similarities between training drills. For the second system, z-scores were calculated for each physical and skill characteristic in each training drill to compare directly with match conditions. For the third system, a 'Specificity Index' was calculated using the absolute average of the pooled z-scores for physical and skilled characteristics respectively. The three systems developed in this study can be used to aid training prescription in elite Australian Rules football.

By using a cost-effective monitoring tool, this study provides information about the intensity, duration, and intensity distribution of all training types across different phases of a season, thus allowing a greater understanding of the training and competition demands of Australian footballers.

Little is known about the effect of preceding endurance-exercise bouts on subsequent resistance-training (RT) performance in team-sport players. Purpose: To examine the effect of prior skills/endurance training and different recovery time periods on subsequent same-day RT performance in professional Australian football players. Methods: Sport-specific endurance-running loads (duration [in minutes], total distance [in meters], mean speed [in meters per minute], high-speed running >15 km·h−1, and relative high-speed running [>75% and >85% of maximal velocity]) were obtained for 46 professional Australian football players for each training session across an entire competitive season. RT was prescribed in 3 weekly mesocycles with tonnage (in kilograms) lifted recorded as RT performance. Endurance and RT sessions were interspersed by different recovery durations: ∼20 min and 1, 2, and 3 h. Fixed- and mixed-effect linear models assessed the influence of skills/endurance-running loads on RT performance. Models also accounted for season period (preseason vs in-season) and recovery duration between concurrent training bouts. Results: An increase in high-speed running and distance covered >75% and >85% of maximal velocity had the greatest reductions on RT performance. In-season total distance covered displayed greater negative effects on subsequent RT performance compared with preseason, while ∼20-min recovery between skills/endurance and RT was associated with greater reductions in RT performance, compared with 1-, 2-, and 3-h recovery. Conclusions: Sport-specific endurance-running loads negatively affect subsequent same-day RT performance, and this effect is greater in-season and with shorter recovery durations between bouts.

Sprint capacity is an important attribute for team-sport athletes, yet the most appropriate method to analyze it is unclear. Purpose: To examine the relationship between sprint workloads using relative versus absolute thresholds and lower-body soft-tissue and bone-stress injury incidence in professional Australian rules football. Methods: Fifty-three professional Australian rules football athletes’ noncontact soft-tissue and bone-stress lower-body injuries (N = 62) were recorded, and sprint workloads were quantified over ∼18 months using the global positioning system. Sprint volume (m) and exposures (n) were determined using 2 methods: absolute (>24.9 km·h−1) and relative (≥75%, ≥80%, ≥85%, ≥90%, ≥95% of maximal velocity). Relationships between threshold methods and injury incidence were assessed using logistic generalized additive models. Incidence rate ratios and model performances’ area under the curve were reported. Results: Mean (SD) maximal velocity for the group was 31.5 (1.4), range 28.6 to 34.9 km·h−1. In comparing relative and absolute thresholds, 75% maximal velocity equated to ~1.5 km·h−1 below the absolute speed threshold, while 80% and 85% maximal velocity were 0.1 and 1.7 km·h−1 above the absolute speed threshold, respectively. Model area under the curve ranged from 0.48 to 0.61. Very low and very high cumulative sprint loads ≥80% across a 4-week period, when measured relatively, resulted in higher incidence rate ratios (2.54–3.29), than absolute thresholds (1.18–1.58). Discussion: Monitoring sprinting volume relative to an athlete’s maximal velocity should be incorporated into athlete monitoring systems. Specifically, quantifying the distance covered at >80% maximal velocity will ensure greater accuracy in determining sprint workloads and associated injury risk.

Context: Exercise in hot environments increases body temperature and thermoregulatory strain. However, little is known regarding the magnitude of effect that ambient temperature (Ta), relative humidity (RH), and solar radiation individually have on team-sport athletes. Purpose: To determine the effect of these individual heat-stress variables on team-sport training performance and recovery. Methods: Professional Australian Rules Football players (N = 45) undertook 8-wk preseason training producing a total of 579 outdoor field-based observations with Ta, RH, and solar radiation recorded at every training session. External load (distance covered, in m/min; percentage high-speed running [%HSR] >14.4 km/h) was collected via a global positioning system. Internal load (ratings of perceived exertion and heart rate) and recovery (subjective ratings of well-being and heart-rate variability [root mean square of the successive differences]) were monitored throughout the training period. Mixed-effects linear models analyzed relationships between variables using standardized regression coefficients. Results: Increased solar-radiation exposure was associated with reduced distance covered (−19.7 m/min, P < .001), %HSR (−10%, P < .001) during training and rMSSD 48 h posttraining (−16.9 ms, P = .019). Greater RH was associated with decreased %HSR (−3.4%, P = .010) but increased percentage duration >85% HRmax (3.9%, P < .001), ratings of perceived exertion (1.8 AU, P < .001), and self-reported stress 24 h posttraining (−0.11 AU, P = .002). In contrast, higher Ta was associated with increased distance covered (19.7 m/min, P < .001) and %HSR (3.5%, P = .005). Conclusions: The authors show the importance of considering the individual factors contributing to thermal load in isolation for team-sport athletes and that solar radiation and RH reduce work capacity during team-sport training and have the potential to slow recovery between sessions.

The aim of this study was to determine physiological and perceptual responses and performance outcomes when completing high-intensity exercise in outdoor and indoor hot environments with contrasting solar radiation exposure. Seven cyclists and 9 Australian Football League (AFL) players undertook cycling trials in hot conditions ($30 ˚C) outdoors and indoors. Cyclists completed 5 3 4 minutes intervals (;80% peak power output [PPO]) with 2 minutes recovery (;40% PPO) before a 20-km self-paced ride. Australian Football League players completed a standardized 20 minutes warm-up (;65% mean 4-minute power output) then 5 3 2 minutes maximal effort intervals. Heart rate (HR), PO, ratings of perceived exertion (RPE), thermal comfort (TC), and thermal sensation (TS) were recorded. Core (T c ) and skin temperature (T sk ) were monitored in cyclists alone. In both studies, ambient temperature, relative humidity, and solar radiation were monitored outdoors and matched for ambient temperature and relative humidity indoors, generating different wet bulb globe temperature (WBGT) for cyclists, but the similar WBGT for AFL players through higher relative humidity indoors. The statistical significance was set at p # 0.05. Cyclists' HR (p 5 0.05), T c (p 5 0.03), and T sk (p 5 0.03) were higher outdoors with variable effects for increased RPE, TS, and TC (d 5 0.2-1.3). Power output during intervals was not different between trials, but there were small-moderate improvements in cyclists' PO and 20-km time indoors (d 5 0.3-0.6). There was a small effect (d 5 0.2) for AFL players' mean PO to increase outdoors for interval 4 alone (p 5 0.04); however, overall there were small-moderate effects for lower RPE and TS indoors (d 5 0.2-0.5). Indoor training in hot conditions without solar radiation may promote modest reductions in physiological strain and improve performance capacity in well-trained athletes.

No abstract