Injury Prediction in Competitive Runners With Machine Learning

in International Journal of Sports Physiology and Performance
Restricted access

Purchase article

USD  $24.95

Student 1 year online subscription

USD  $112.00

1 year online subscription

USD  $149.00

Student 2 year online subscription

USD  $213.00

2 year online subscription

USD  $284.00

Purpose: Staying injury free is a major factor for success in sports. Although injuries are difficult to forecast, novel technologies and data-science applications could provide important insights. Our purpose was to use machine learning for the prediction of injuries in runners, based on detailed training logs. Methods: Prediction of injuries was evaluated on a new data set of 74 high-level middle- and long-distance runners, over a period of 7 years. Two analytic approaches were applied. First, the training load from the previous 7 days was expressed as a time series, with each day’s training being described by 10 features. These features were a combination of objective data from a global positioning system watch (eg, duration, distance), together with subjective data about the exertion and success of the training. Second, a training week was summarized by 22 aggregate features, and a time window of 3 weeks before the injury was considered. Results: A predictive system based on bagged XGBoost machine-learning models resulted in receiver operating characteristic curves with average areas under the curves of 0.724 and 0.678 for the day and week approaches, respectively. The results of the day approach especially reflect a reasonably high probability that our system makes correct injury predictions. Conclusions: Our machine-learning-based approach predicts a sizable portion of the injuries, in particular when the model is based on training-load data in the days preceding an injury. Overall, these results demonstrate the possible merits of using machine learning to predict injuries and tailor training programs for athletes.

Lövdal and Azzopardi are with the Bernoulli Inst for Mathematics, Computer Science and Artificial Intelligence, Faculty of Science and Engineering, and Den Hartigh, the Dept of Psychology, Faculty of Behavioral and Social Sciences, University of Groningen, Groningen, the Netherlands.

Azzopardi (g.azzopardi@rug.nl) is corresponding author.
  • 1.

    Raysmith BP, Drew MK. Performance success or failure is influenced by weeks lost to injury and illness in elite Australian track and field athletes: a 5-year prospective study. J Sci Med Sport. 2016;19(10):778783. PubMed ID: 26839047 doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 2.

    D’souza D. Track and field athletics injuries–a one-year survey. Br J Sports Med. 1994;28:197202. PubMed ID: 8000821 doi:

  • 3.

    Soligard T, Schwellnus M, Alonso J-M, et al. How much is too much? (Part 1) International Olympic Committee consensus statement on load in sport and risk of injury. Br J Sports Med. 2016;50(17):10301041. PubMed ID: 27535989 doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 4.

    Brink MS, Visscher C, Arends S, Zwerver J, Post WJ, Lemmink KAPM. Monitoring stress and recovery: new insights for the prevention of injuries and illnesses in elite youth soccer players. Br J Sports Med. 2010;44(11):809815. PubMed ID: 20511621 doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 5.

    Cross MJ, Williams S, Trewartha G, Kemp SPT, Stokes KA. The influence of in-season training loads on injury risk in professional rugby union. Int J Sports Physiol Perform. 2016;11(3):350355. doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 6.

    Dennis R, Farhart R, Goumas C, Orchard J. Bowling workload and the risk of injury in elite cricket fast bowlers. J Sci Med Sport. 2003;6(3):359367. PubMed ID: 14609154 doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 7.

    Huxley DJ, O’Connor D, Healey PA. An examination of the training profiles and injuries in elite youth track and field athletes. Eur J Sport Sci. 2014;14(2):185192. PubMed ID: 23777449 doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 8.

    Jaspers A, Op De Beéck T, Brink MS, et al. Relationships between the external and internal training load in professional soccer: what can we learn from machine learning? Int J Sports Physiol Perform. 2018;13(5):625630. doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 9.

    Knobbe A, Orie J, Hofman N, Burgh B, Cachucho R. Sports analytics for professional speed skating. Data Min Knowl Disc. 2017;31(6):18721902. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 10.

    Naglah A, Khalifa F, Mahmoud A, et al. Athlete-customized injury prediction using training load statistical records and machine learning. 2018 IEEE Int Symp Signal Process Inf Technol. 2018:459464. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 11.

    Alpaydin E. Introduction to Machine Learning. Cambridge, MA: MIT Press; 2009.

  • 12.

    Raya-Gonzalez J, Nakamura FY, Castillo D, Yanci J, Fanchini M. Determining the relationship between internal load markers and noncontact injuries in young elite soccer players. Int J Sports Physiol Perform. 2019;14(4):421425. doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 13.

    Rossi A, Pappalardo L, Cintia P, Iaia FM, Fernàndez J, Medina D. Effective injury forecasting in soccer with GPS training data and machine learning. PLoS One. 2018;13(7):e0201264. PubMed ID: 30044858 doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 14.

    Talukder H, Vincent T, Foster G, et al. Preventing in-game injuries for NBA players. Paper presented at: MIT Sloan Analytics Conference, Boston MA. 2016.

    • Search Google Scholar
    • Export Citation
  • 15.

    Dower C, Rafehi A, Weber J, Mohamad R. An enhanced metric of injury risk utilizing artificial intelligence. Paper presented at: MIT Sloan Analytics Conference, Boston, MA. 2018. https://www.alerteds.com/wp-content/uploads/2016/02/MITSSAC2018-An-enhanced-metric-of-injury-risk-utilizing-Artificial-Intelligence.pdf

    • Search Google Scholar
    • Export Citation
  • 16.

    Lysholm J, Wiklander J. Injuries in runners. Am J Sports Med. 1987;15(2):168171. PubMed ID: 3578639 doi:

  • 17.

    Van Der Does HTD, Brink MS, Otter RTA, Visscher C, Lemmink KAPM. Injury risk is increased by changes in perceived recovery of team sport players. Clin J Sport Med. 2017;27(1):4651. PubMed ID: 26945309 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 18.

    Rogalski B, Dawson B, Heasman J, Gabbett TJ. Training and game loads and injury risk in elite Australian footballers. J Sci Med Sport. 2013;16(6):499503. PubMed ID: 23333045 doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 19.

    Nielsen , Parner ET, Nohr EA, Sørensen H, Lind M, Rasmussen S. Excessive progression in weekly running distance and risk of running-related injuries: an association which varies according to type of injury. J Orthop Sports Phys Ther. 2014;44(10):739747. PubMed ID: 25155475 doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 20.

    Chen T, Guestrin C. Xgboost: A scalable tree boosting system. Paper presented at: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining; 2016:785794. doi:.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 21.

    Nielsen D. Tree Boosting With XGBoost-Why Does XGBoost Win” Every” Machine Learning Competition? [Master’s thesis]. Trondheim, Norway: Norwegian University of Science and Technology; 2016.

    • Search Google Scholar
    • Export Citation
  • 22.

    Alsahaf A, Azzopardi G, Ducro B, Hanenberg E, Veerkamp R, Petkov N. Estimation of muscle scores of live pigs using a kinect camera. IEEE Access. 2019;7:5223852245. doi:.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 23.

    Farrugia S, Ellul J, Azzopardi G. Detection of illicit accounts over the Ethereum blockchain. Expert Syst Appl. 2020;150:113318. doi:

  • 24.

    Developers XGBoost. XGBoost v0.9 Documentation. 2016. https://xgboost.readthedocs.io/en/release_0.90/. Accessed July 26, 2019.

  • 25.

    Steyerberg EW, Vergouwe Y. Towards better clinical prediction models: seven steps for development and an ABCD for validation. Eur Heart J. 2014;35(29):19251931. PubMed ID: 24898551 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 26.

    Menaspa P, Sassi A, Impellizzeri FM. Aerobic fitness variables do not predict the professional career of young cyclists. Med Sci Sports Exerc. 2010;42(4):805812. PubMed ID: 19952851 doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 27.

    Hulin BT, Gabbett TJ, Lawson DW, et al. The acute:chronic workload ratio predicts injury: high chronic workload may decrease injury risk in elite rugby league players. Br J Sports Med. 2016;50(4):231236. PubMed ID: 26511006 doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 28.

    Heidari J, Beckmann J, Bertollo M, et al. Multidimensional monitoring of recovery status and implications for performance. Int J Sports Physiol Perform. 2019;14(1):28. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 29.

    Op De Beéck T, Jaspers A, Brink MS, et al. Predicting future perceived wellness in professional soccer: the role of preceding load and wellness. Int J Sports Physiol Perform. 2019;14(8):10741080. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 30.

    Lieli RP, Hsu YC. Using the area under an estimated ROC curve to test the adequacy of binary predictors. J Nonparametr Stat. 2019;31(1):100130. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 31.

    Memmert D, Lemmink KAPM, Sampaio J. Current approaches to tactical performance analyses in soccer using position data. Sports Med. 2017;47(1):110. PubMed ID: 27251334 doi:

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 641 641 199
Full Text Views 30 30 6
PDF Downloads 18 18 5