Detecting Injury Risk Factors with Algorithmic Models in Elite Women’s Pathway Cricket

Abstract

This exploratory retrospective cohort analysis aimed to explore how algorithmic models may be able to identify important risk factors that may otherwise not have been apparent. Their association with injury was then assessed with more conventional data models. Participants were players registered on the England and Wales Cricket Board women’s international development pathway (n=17) from April 2018 to August 2019 aged between 14–23 years (mean 18.2±1.9) at the start of the study period. Two supervised learning techniques (a decision tree and random forest with traditional and conditional algorithms) and generalised linear mixed effect models explored associations between risk factors and injury. The supervised learning models did not predict injury (decision tree and random forest area under the curve [AUC] of 0.66 and 0.72 for conditional algorithms) but did identify important risk factors. The best-fitting generalised linear mixed effect model for predicting injury (Akaike Information Criteria [AIC]=843.94, conditional r-squared=0.58) contained smoothed differential 7-day load (P<0.001), average broad jump scores (P<0.001) and 20 m speed (P<0.001). Algorithmic models identified novel injury risk factors in this population, which can guide practice and future confirmatory studies can now investigate.

Key words

machine learning - cricket - player monitoring - workload - injury - risk factors

Publication History

Received: 11 December 2020

Accepted: 02 May 2021

Article published online:
24 September 2021

• References

• 1 Ruddy JD, Cormack SJ, Whiteley R. et al. Modelling the risk of team sport injuries: A narrative review of different statistical approaches. Front Psychol 2019; 10: 829
• 2 Breiman L. Statistical Modeling: The two cultures. Stat Sci 2001; 16: 199-231
• 3 Bittencourt NF, Meeuwisse WH, Mendonca LD. et al. Complex systems approach for sports injuries: moving from risk factor identification to injury pattern recognition-narrative review and new concept. Br J Sports Med 2016; 50: 1309-1314
• 4 Ruddy JD, Shield AJ, Maniar N. et al. Predictive modelling of hamstring strain injuries in elite Australian footballers. Med Sci Sports Exerc 2017; 50: 906-914
• 5 Ayala F, Lopez-Valenciano A, Martin JAG. et al. A preventative model for hamstring injuries in professional soccer: Learning algorithms. Int J Sports Med 2019; 40: 344-353
• 6 Rossi A, Pappalardo L, Cintia P. et al. Effective injury forecasting in soccer with GPS training data and machine learning. PLoS One 2018; 13: e0201264
• 7 Jauhiainen S, Kauppi JP, Leppanen M. et al. New machine learning approach for detection of injury risk factors in young team sport athletes. Int J Sports Med 2021; 42: 175-182 DOI: 10.1055/a-1231-5304.
• 8 Harriss DJ, Macsween A, Atkinson G. Ethical standards in sport and exercise science research: 2020 update. Int J Sports Med 2019; 40: 813-817
• 9 Rae K, Orchard J. The Orchard Sports Injury Classification System (OSICS) Version 10. Clin J Sport Med 2007; 17: 201-204
• 10 Foster C, Florhaug JA, Franklin J. et al. A new approach to monitoring exercise training. J Strength Cond Res 2001; 15: 109-115
• 11 Lazarus BH, Stewart AM, White KM. et al. Proposal of a global training load measure predicting match performance in an elite team sport. Front Physiol 2017; 8: 930
• 12 Tysoe A, Moore IS, Ranson C. et al. Bowling loads and injury risk in male first class county cricket: Is ‘differential load’ an alternative to the acute-to-chronic workload ration?. J Sci Med Sport 2020; 23: 569-573
• 13 Hulin BT, Gabbett TJ, Blanch P. Spikes in acute workload are associated with increased injury risk in elite cricket fast bowlers. Br J Sports Med 2014; 48: 708-712
• 14 Coyne JO, Haff GG, Coutts AJ. et al. The current state of subjective training load monitoring- a practical perspective and call to action. Sports Med Open 2018; 4: 58
• 15 Impellizzeri F, Woodcock S, McCall A. et al. The Acute-Chronic Workload Ratio-Injury Figure and its ‘Sweet Spot’ Are Flawed. 2019 In internet: https://osf.io/preprints/sportrxiv/gs8yu/. accessed 8 September 2020
• 16 Wang C, Vargas JT, Stokes T. et al. Analysing activity and injury: Lessons learned from the acute:chronic workload ratio. Sports Med 2020; 50: 1243-1254
• 17 Williams G, Culp MV, Cox E. et al. Rattle: Graphical User Interface for Data Science in R. 2020 In internet: https://cran.r-project.org/web/packages/rattle/index.html.accessed 15 July 2020
• 18 Bahr R. Why screening tests to predict injury do not work – and probably never will: A critical review. Br J Sports Med 2016; 50: 776-780
• 19 Han J, Kamber M. Chapter 6: Classification and Prediction. In: Han, J. & Kamber, M. Eds. Data Mining: Concepts and Techniques. 2nd ed. San Francisco: Elsevier; 2006
• 20 Strobl C, Boulesteix AL, Kneib T. et al. Conditional variable importance for random forests. BMC Bioinformatics 2008; 9: 307
• 21 Newbold T. GLMERSelect: Backward Stepwise Selection of Glmer Fixed Effects. 2020 In internet: https://rdrr.io/github/timnewbold/StatisticalModels/man/GLMERSelect.html,accessed 22 June 2020
• 22 Bates D, Maechler M, Bolker B. et al. Package ‘lme4’. 2020 In internet: https://cran.r-project.org/web/packages/lme4/lme4.pdf,accessed 12 July 2020
• 23 Lüdecke D, Makowski D, Waggoner P. et al. Package ‘Performance’. 2020 In internet: https://cran.r-project.org/web/packages/performance/performance.pdf,accessed 3 August 2020
• 24 Peterson CJ, Pyne D, Dawson B. et al. Movement patterns in cricket vary by both position and game format. J Sports Sci 2010; 28: 45-52
• 25 Peterson CJ, Pyne DB, Portus MR. et al. Comparison of player movement patterns between 1-day and test cricket. J Strength Cond Res 2011; 25: 1368-1373
• 26 Orchard JW, Kountouris A, Sims K. Incidence and prevalence of elite male cricket injuries using updated consensus definitions. Open Access J Sports Med 2016; 7: 187-194
• 27 Goggins L, Peirce N, Ranson C. et al Injuries in England and Wales elite men’s domestic cricket: A nine season review from 2010 to 2018. J Sci Med Sport 2020; 23: 836-840
• 28 Goggins L, Warren A, Smart D. et al. Injury and player availability in women’s international pathway cricket from 2015 to 2019. Int J Sports Med 2020; 41: 944-950
• 29 Moresi MP, Bradshaw EJ, Green D. et al. The assessment of adolescent female athletes using standing and reactive long jumps. Sports Biomech 2011; 10: 73-84
• 30 Anderson E, Lockie RG, Dawes JJ. relationship of absolute and relative lower-body strength to predictors of athletic performance in collegiate women soccer players. Sports (Basel) 2018; 6: 106
• 31 Malone S, Hughes B, Doran DA. et al. Can the workload-injury relationship be moderated by improved strength, speed and repeated-sprint qualities?. J Sci Med Sport 2019; 22: 29-34
• 32 Ranson C, Gregory PL. Shoulder injury in professional cricketers. Phys Ther Sport 2008; 9: 34-39
• 33 Carey DL, Ong K, Whitely R. et al. Predictive modelling of training loads and injury in Australian Football. Int J Comput Sci Sport 2018; 17: 49-66