Background: The concept of predicting injury risk has been criticised (Bahr, 2016), however research using machine learning methods has demonstrated that it is possible to predict injury risk in basketball (Talukder 2016a) and soccer (Talukder 2016b). Player load is by far the strongest injury risk factor (Rossi 2018), however player load data may not always be available for analysis and the prediction of risk. The aim of this study was to investigate whether player characteristics alone, could be used to predict injury risk in the first five seasons of an Australian football player’s professional career. Methods: The data represented 1033 unique AFL players, who sustained 4762 injuries in seasons 1997-2016. Player characteristics (height, body mass, age, playing position, indigenousness & natural kicking foot) and the injury characteristics of the previous season, were used in models to predict injury risk. Results: A Naïve Bayes model that was based on player characteristics alone was able to classify injury risk category (low, medium, high) over 5 years, 1.3 times better than random chance. The characteristics of; playing position, height and body mass contributed to 97% of the prediction of injury risk category. A Decision Tree model that classified injury risk category in a single season, based on the characteristics of a player and their injuries in the previous season, performed 1.4 times better than random chance. When the models were used to predict whether a player would be in the highest risk category, the performance of both models increased to 1.9 and 2.2 times better than random chance. Taller and heavier key position players who sustained hamstring strain and groin strain/osteitis pubis injuries in the previous season had a higher injury risk than shorter and lighter non-key position players who remained injury-free in the previous season. Discussion: The injury prediction models reported here did not perform as well previously reported models that were based on training load. Nevertheless, they demonstrate how player characteristics affect injury risk and the models themselves can be used “live” to stratify injury risk, which can then be used to help clinicians make decisions about risk mitigation strategies such as prehabilitation. Conflict of interest statement: My co-authors and I acknowledge that we have no conflict of interest of relevance to the submission of this abstract.

Objectives To determine the rates of muscle strain injury recurrence over time after return to play in Australian football and to quantify risk factors. Methods We analysed Australian Football League player data from 1992 to 2014 for rates of the four major muscle strain injury types (hamstring, quadriceps, calf and groin) diagnosed by team health professionals. Covariates for analysis were: recent history (≤8 weeks) of each of the four muscle strains; non-recent history (>8 weeks) of each; history of hip, knee anterior cruciate ligament, knee cartilage, ankle sprain, concussion or lumbar injury; age; indigenous race; match level and whether a substitute rule was in place. Results 3647 (1932 hamstring, 418 quadriceps, 458 calf and 839 groin) muscle strain injuries occurred in 272 759 player matches. For all muscle strains combined, the risk of injury recurrence gradually reduced, with recurrence risks of 9% (hamstring), 5% (quadriceps), 2% (calf) and 6% (groin) in the first match back and remaining elevated for 15 weeks after return to play. The strongest risk factor for each muscle injury type was a recent history of the same injury (hamstring: adjusted OR 13.1, 95% CI 11.5 to 14.9; calf OR 13.3, 95% CI 9.6 to 18.4; quadriceps: OR 25.2, 95% CI 18.8 to 33.8; groin OR 20.6, 95% CI 17.0 to 25.0), followed by non-recent history of the same injury (hamstring: adjusted OR 3.5, 95% CI 3.2 to 3.9; calf OR 4.4, 95% CI 3.6 to 5.4; quadriceps OR 5.2, 95% CI 4.2 to 6.4; groin OR 3.5, 95% CI 3.0 to 4.0). Age was an independent risk factor for calf muscle strains (adjusted OR 1.6, 95% CI 1.3 to 2.0). Recent hamstring injury increased the risk of subsequent quadriceps (adjusted OR 1.8, 95% CI 1.2 to 2.7) and calf strains (OR 1.8, 95% CI 1.2 to 2.6). During the ‘substitute rule’ era (2011–2014), hamstring (adjusted OR 0.76, 95% CI 0.67 to 0.86), groin (OR 0.78, 95% CI 0.65 to 0.93) and quadriceps (OR 0.70, 95% CI 0.53 to 0.92) strains were less likely than outside of that era but calf (OR 1.6, 95% CI 1.3 to 1.9) strains were more likely than before the substitute rule era. Conclusion Recent injury is the greatest risk factor for the four major muscle strains, with increased risk persisting for 15 weeks after return to play.

Objectives To determine whether specific injury measures were associated with team performance in the Australian Football League (AFL). Methods 15 289 injuries caused players from 18 teams to miss 51 331 matches between 1997 and 2016. Data were aggregated to the team level. We analysed the associations among injury measures and team performance (reaching finals/playoffs and specific ladder/table position). Injury measures per team included: injury incidence, injury severity, injury burden, player match availability and percentage of the full player roster injured. We also weighted injury measures by five measures of player value. Results AFL teams' injury burden and player match availability were associated with final table position (r(2)=0.03, p<0.05). Player value weighted injury burden was different between finalists and non-finalists (mean difference=-8, p<0.001) and explained 12% of the variation in the table position of teams (p<0.001). For a team, nine missed matches due to injury (burden weighted by a best and fairest player rating system) was associated with one lower table position. Player match availability weighted by player value was higher for finalists than non-finalists (mean difference=1.7, p<0.01) and explained 7% of the variation in the table position of teams (p<0.001). Discussion and potential implications The impact of injury (burden weighted by best and fairest) explained up to 12% of the variation in final table position-this is particularly relevant to making/not making playoffs as well as home ground/travel advantages for those teams that make the one-game format of AFL playoffs (not home-away or best of seven format).

Background: Injury surveillance has been used to quantify the scope of the injury burden in Australian football. However, deeper statistical analyses are required to identify major factors that contribute to the injury risk and to understand how these injury patterns change over time. Purpose: To compare Australian Football League (AFL) injury incidence, severity, prevalence, and recurrence by setting, site, and time span from 1997 to 2016. Study Design: Descriptive epidemiology study. Methods: A total of 15,911 injuries and medical illnesses recorded by team medical staff at each club were obtained from the AFL’s injury surveillance system and analyzed using linear mixed models with 3 fixed effects (setting, time span, site) and 1 random effect (club). All types of injuries and medical illnesses were included for analysis, provided that they caused the player to miss at least 1 match during the regular season or finals. Five-season time spans (1997-2001, 2002-2006, 2007-2011, and 2012-2016) were used for comparisons. Incidence rates were expressed at the player level. Recurrences were recoded to quantify recurrent injuries across multiple seasons. Results: Compared with training injuries, match injuries had a 2.8 times higher incidence per season per club per player (matches: 0.070 ± 0.093; training: 0.025 ± 0.043; P < .001). Match injuries resulted in 1.9 times more missed matches per club per season (matches: 17.2 ± 17.0; training: 9.1 ± 10.5; P < .001). and were more likely to be recurrences (matches: 11.6% ± 20.0%; training: 8.6% ± 21.8%; P < .001). From the 1997-2001 to 2007-2011 time spans, overall injury severity increased from a mean of 3.2 to 3.7 missed matches ( P ≤ .01). For the most recent 2012-2016 time span, injuries resulted in 3.6 missed matches, on average. Hip/groin/thigh injuries had the highest incidence (0.125 ± 0.120) and prevalence (19.2 ± 16.4) rates, and recurrences (29.3% ± 27.9%) were 15% more likely at this site than any other injury site. Conclusion: The risks of match injuries are significantly higher than those of training injuries in the AFL. Compared with the 1997-2001 time span, injuries became more severe during the 2007-2011 time span.

Introduction: Injury surveillance has been used to quantify the scope of the injury burden in Australian football. However, deeper statistical analyses are required to identify major factors that contribute to injury risk and to understand how these injury patterns change over time. The aim of this study was to compare whether Australian Football League injury characteristics (incidence, severity, prevalence, and recurrence) differed by setting, site, and time span from 1997 to 2016.

Background: The increasing focus on international sporting success has led to many countries introducing sport schools and academies. Limited empirical evidence exists that directly compares student-athletes from different continents. This study investigated whether male Australian and Qatari student-athletes differ in anthropometry, physical fitness and biological maturity. Methods: 150 male student-athletes (72 Qatari, 78 Australian; age = 11.8 - 18.6 y) completed a fitness testing session involving anthropometric (standing height, sitting height, leg length, body mass, peak height velocity (PHV) measures) and physical capacity (40 m sprint, countermovement jump (CMJ), predicted maximal oxygen uptake (VO2 max) tests. Differences were assessed using a one-way multivariate analysis of variance (MANOVA), effect size (Cohen’s d) and regression coefficients. Results: The Australian student-athletes possessed a greater standing height and body mass (P < 0.01) at their age at PHV (APHV) and had an increased rate of leg length development (P < 0.05) in contrast to the sitting height of the Qataris (P < 0.01). The Qatari student-athletes had significantly (P < 0.01) faster 40 m sprint times (mean ± SD: 5.88 ± 0.53 vs 6.19 ± 0.44 s) and greater CMJ heights (36.9 ± 7.2 vs 34.0 ± 6.0 cm) than their Australian counterparts. Although not statistically different, the Qatari student-athletes also matured earlier (APHV: d = 0.35) and had greater aerobic power results (predicted VO2 max: d = 0.22). Conclusions: Despite lower stature and body mass values, Qatari student-athletes exhibited physical fitness ascendancy over their Australian counterparts.