Predictive Modelling of Training Loads and Injury in Australian Football

Open access

Abstract

To investigate whether training load monitoring data could be used to predict injuries in elite Australian football players, data were collected from athletes over 3 seasons at an Australian football club. Loads were quantified using GPS devices, accelerometers and player perceived exertion ratings. Absolute and relative training load metrics were calculated for each player each day. Injury prediction models (regularised logistic regression, generalised estimating equations, random forests and support vector machines) were built for non-contact, non-contact time-loss and hamstring specific injuries using the first two seasons of data. Injury predictions were then generated for the third season and evaluated using the area under the receiver operator characteristic (AUC). Predictive performance was only marginally better than chance for models of non-contact and non-contact time-loss injuries (AUC<0.65). The best performing model was a multivariate logistic regression for hamstring injuries (best AUC=0.76). Injury prediction models built using training load data from a single club showed poor ability to predict injuries when tested on previously unseen data, suggesting limited application as a daily decision tool for practitioners. Focusing the modelling approach on specific injury types and increasing the amount of training observations may improve predictive models for injury prevention

Bittencourt, N., Meeuwisse, W., Mendonça, L., Nettel-Aguirre, A., Ocarino, J., & Fonseca, S. (2016). Complex systems approach for sports injuries: moving from risk factor identification to injury pattern recognition-narrative review and new concept. British Journal of Sports Medicine, 50(21), 1309-1314

Blanch, P., & Gabbett, T. J. (2016). Has the athlete trained enough to return to play safely? The acute: chronic workload ratio permits clinicians to quantify a player's risk of subsequent injury. British Journal of Sports Medicine, 50(8), 471-475.

Bourdon, P. C., Cardinale, M., Murray, A., Gastin, P., Kellmann, M., Varley, M. C., . . . Cable, N. T. (2017). Monitoring Athlete Training Loads: Consensus Statement. Int J Sports Physiol Perform, 12(Suppl 2), S2161-S2170. doi:

Boyd, L. J., Ball, K., & Aughey, R. J. (2011). The reliability of MinimaxX accelerometers for measuring physical activity in Australian football. International Journal of Sports Physiology and Performance, 6(3), 311-321.

Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.

Buuren, S., & Groothuis-Oudshoorn, K. (2011). mice: Multivariate imputation by chained equations in R. Journal of statistical software, 45(3).

Carey, D. L., Blanch, P., Ong, K.-L., Crossley, K. M., Crow, J., & Morris, M. E. (2016). Training loads and injury risk in Australian football-differing acute: chronic workload ratios influence match injury risk. British Journal of Sports Medicine, bjsports-2016-096309. doi:

Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, 321-357.

Colby, M. J., Dawson, B., Heasman, J., Rogalski, B., & Gabbett, T. J. (2014). Accelerometer and GPS-derived running loads and injury risk in elite Australian footballers. The Journal of Strength & Conditioning Research, 28, 2244-2252.

Drew, M. K., & Finch, C. F. (2016). The Relationship Between Training Load and Injury, Illness and Soreness: A Systematic and Literature Review. Sports Medicine. doi:

Duhig, S., Shield, A. J., Opar, D., Gabbett, T. J., Ferguson, C., & Williams, M. (2016). Effect of high-speed running on hamstring strain injury risk. Br J Sports Med, 50(24), 1536-1540. doi:

Foster, C., Florhaug, J. A., Franklin, J., Gottschall, L., Hrovatin, L. A., Parker, S., . . . Dodge, C. (2001). A new approach to monitoring exercise training. The Journal of Strength & Conditioning Research, 15, 109-115.

Gabbett, T. J. (2010). The development and application of an injury prediction model for noncontact, soft-tissue injuries in elite collision sport athletes. The Journal of Strength & Conditioning Research, 24, 2593-2603.

Gabbett, T. J. (2015). Relationship Between Accelerometer Load, Collisions, and Repeated High-Intensity Effort Activity in Rugby League Players. J Strength Cond Res, 29(12), 3424-3431. doi:

Gabbett, T. J. (2016). The training-injury prevention paradox: should athletes be training smarter and harder? British Journal of Sports Medicine, 50, 273-280. doi:

Hägglund, M., Waldén, M., Magnusson, H., Kristenson, K., Bengtsson, H., & Ekstrand, J. (2013). Injuries affect team performance negatively in professional football: an 11- year follow-up of the UEFA Champions League injury study. British Journal of Sports Medicine, 47(12), 738-742.

Hulin, B. T., Gabbett, T. J., Lawson, D. W., Caputi, P., & Sampson, J. A. (2015). The acute:chronic workload ratio predicts injury: high chronic workload may decrease injury risk in elite rugby league players. British Journal of Sports Medicine, bjsports- 2015-094817. doi:

Jolliffe, I. T. (1986). Principal Component Analysis and Factor Analysis Principal component analysis (pp. 115-128): Springer.

Kuhn, M., & Johnson, K. (2013). Applied Predictive Modeling. New York, NY: Springer New York.

Liang, K.-Y., & Zeger, S. L. (1986). Longitudinal data analysis using generalized linear models. Biometrika, 73(1), 13-22.

Malone, S., Owen, A., Newton, M., Mendes, B., Collins, K. D., & Gabbett, T. J. (2016). The acute:chonic workload ratio in relation to injury risk in professional soccer. Journal of Science and Medicine in Sport. doi:

McCall, A., Fanchini, M., & Coutts, A. J. (2017). Prediction: The Modern-Day Sport-Science and Sports-Medicine "Quest for the Holy Grail". Int J Sports Physiol Perform, 12(5), 704-706. doi:

Murray, N. B., Gabbett, T. J., Townshend, A. D., & Blanch, P. (2016). Calculating acute:chronic workload ratios using exponentially weighted moving averages provides a more sensitive indicator of injury likelihood than rolling averages. British Journal of Sports Medicine, bjsports-2016-097152. doi:

Orchard, J. W., Seward, H., & Orchard, J. J. (2013). Results of 2 decades of injury surveillance and public release of data in the Australian Football League. The American Journal of Sports Medicine, 0363546513476270.

Rae, K., & Orchard, J. (2007). The Orchard sports injury classification system (OSICS) version 10. Clinical Journal of Sport Medicine, 17(3), 201-204.

Rampinini, E., Alberti, G., Fiorenza, M., Riggio, M., Sassi, R., Borges, T. O., & Coutts, A. J. (2015). Accuracy of GPS devices for measuring high-intensity running in field-based team sports. International Journal of Sports Medicine, 36(1), 49-53.

Rogalski, B., Dawson, B., Heasman, J., & Gabbett, T. J. (2013). Training and game loads and injury risk in elite Australian footballers. Journal of Science and Medicine in Sport, 16, 499-503. doi:

Ruddy, J. D., Pollard, C. W., Timmins, R. G., Williams, M. D., Shield, A. J., & Opar, D. A. (2016). Running exposure is associated with the risk of hamstring strain injury in elite Australian footballers. British Journal of Sports Medicine, bjsports-2016-096777. doi:

Soligard, T., Schwellnus, M., Alonso, J.-M., Bahr, R., Clarsen, B., Dijkstra, H. P., . . . Engebretsen, L. (2016). How much is too much? (Part 1) International Olympic Committee consensus statement on load in sport and risk of injury. British Journal of Sports Medicine, 50, 1030-1041. doi:

Thornton, H. R., Delaney, J. A., Duthie, G. M., & Dascombe, B. J. (2016). Importance of Various Training Load Measures on Injury Incidence of Professional Rugby League Athletes. International Journal of Sports Physiology and Performance, 1-17.

Vapnik, V. N., & Vapnik, V. (1998). Statistical learning theory (Vol. 1): Wiley New York.

Weaving, D., Jones, B., Till, K., Abt, G., & Beggs, C. (2017). The Case for Adopting a Multivariate Approach to Optimize Training Load Quantification in Team Sports. Front Physiol, 8, 1024. doi:

Weaving, D., Marshall, P., Earle, K., Nevill, A., & Abt, G. (2014). Combining internal- and external-training-load measures in professional rugby league. Int J Sports Physiol Perform, 9(6), 905-912. doi:

Williams, S., Trewartha, G., Cross, M., Kemp, S., & Stokes, K. (2016a). Monitoring What Matters: A Systematic Process for Selecting Training Load Measures. International Journal of Sports Physiology and Performance, 1-20.

Williams, S., West, S., Cross, M., & Stokes, K. (2016b). Better way to determine the acute:chronic workload ratio? British Journal of Sports Medicine, bjsports-2016-096589. doi:

Williamson, D. S., Bangdiwala, S. I., Marshall, S. W., & Waller, A. E. (1996). Repeated measures analysis of binary outcomes: applications to injury research. Accident Analysis & Prevention, 28(5), 571-579.

Windt, J., & Gabbett, T. J. (2017). How do training and competition workloads relate toinjury? The workload-injury aetiology model. Br J Sports Med, 51(5), 428-435.doi:

Zou, H., & Hastie, T. (2005). Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 67(2), 301-320.

Journal Information


CiteScore 2017: 0.53

SCImago Journal Rank (SJR) 2017: 0.261
Source Normalized Impact per Paper (SNIP) 2017: 0.565

Cited By

Metrics

All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 652 652 59
PDF Downloads 490 490 38