Predictive Modelling of Training Loads and Injury in Australian Football

@article{Carey2018PredictiveMO,
  title={Predictive Modelling of Training Loads and Injury in Australian Football},
  author={David L. Carey and K-L. Ong and Rod Whiteley and Kay M. Crossley and Justin Crow and Meg E. Morris},
  journal={International Journal of Computer Science in Sport},
  year={2018},
  volume={17},
  pages={49 - 66}
}
  • D. Carey, K-L. Ong, M. Morris
  • Published 14 June 2017
  • Environmental Science
  • International Journal of Computer Science in Sport
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… 

Figures and Tables from this paper

Predictive Modeling of Hamstring Strain Injuries in Elite Australian Footballers
TLDR
Risk factor data cannot be used to identify athletes at an increased risk of HSI with any consistency and the large ranges in AUC highlight the fragility of the data.
Predictive Analytic Techniques to Identify Hidden Relationships between Training Load, Fatigue and Muscle Strains in Young Soccer Players
This study aimed to analyze different predictive analytic techniques to forecast the risk of muscle strain injuries (MSI) in youth soccer based on training load data. Twenty-two young soccer players
A Machine Learning Approach to Assess Injury Risk in Elite Youth Football Players
TLDR
The machine learning algorithm was able to predict injury and to distinguish overuse from acute injuries with reasonably high accuracy based on preseason measures and could be applied in the development and improvement of injury risk management strategies to identify youth players with the highest injury risk.
Modeling Training Loads and Injuries: The Dangers of Discretization
TLDR
Evaluating common modeling strategies in training load and injury risk research when modeling continuous variables and interpreting continuous risk estimates shows discrete models were inferior to continuous methods for fitting the true injury risk profiles in the data.
New Machine Learning Approach for Detection of Injury Risk Factors in Young Team Sport Athletes.
TLDR
Predictive machine learning methods can be utilized for detecting sport injury risk factors in a data-driven manner and can be used for finding new hypotheses for risk factors and confirming the predictive power of previously recognized ones.
Prediction of Hamstring Injuries in Australian Football Using Biceps Femoris Architectural Risk Factors Derived From Soccer
TLDR
Applying cut points derived from previously published data in soccer to a dataset from Australian football identified older age and prior HSIs, but none of the modifiable HSI risk factors, to be associated with an injury.
Monitoring Variables Influence on Random Forest Models to Forecast Injuries in Short-Track Speed Skating
Injuries limit the athletes' ability to participate fully in their training and competitive process. They are detrimental to performance, affecting the athletes psychologically while limiting
The Individual and Combined Effects of Multiple Factors on the Risk of Soft Tissue Non-contact Injuries in Elite Team Sport Athletes
TLDR
Information from athlete monitoring practices in team sports should be interpreted collectively and used as a part of the injury prevention decision-making process along with consideration of individual differences in risk.
Greater Association of Relative Thresholds Than Absolute Thresholds With Noncontact Lower-Body Injury in Professional Australian Rules Footballers: Implications For Sprint Monitoring.
TLDR
Monitoring sprinting volume relative to an athlete's maximal velocity should be incorporated into athlete-monitoring systems to ensure greater accuracy in determining sprint workloads and associated injury risk.
Detecting Injury Risk Factors with Algorithmic Models in Elite Women's Pathway Cricket.
TLDR
Algorithmic models identified novel injury risk factors in this population, which can guide practice and future confirmatory studies can now investigate.
...
...

References

SHOWING 1-10 OF 42 REFERENCES
Accelerometer and GPS-Derived Running Loads and Injury Risk in Elite Australian Footballers
TLDR
Findings support consideration of several GPS/accelerometer running load variables in Australian football players, with 3-weekly loads most indicative of a greater injury risk across both seasonal phases.
Importance of Various Training-Load Measures in Injury Incidence of Professional Rugby League Athletes.
TLDR
The individual RF models showed that the importance of the TL variables in injury incidence varied between athletes, suggesting that robust machine-learning techniques can appropriately monitor injury risk in professional team-sport athletes.
Training loads and injury risk in Australian football—differing acute: chronic workload ratios influence match injury risk
TLDR
For Australian football, the ratio of moderate speed running in a 3-day or 6-day acute time window and a 21-day chronic time window best explained injury risk.
Running exposure is associated with the risk of hamstring strain injury in elite Australian footballers
TLDR
An association exists between absolute and relative running exposure variables and elite Australian footballers' risk of subsequent HSI, with the association strongest when examining data within 7–14 days, despite this, the use ofRunning exposure variables displayed limited clinical utility to predict HSI at the individual level.
The Development and Application of an Injury Prediction Model for Noncontact, Soft-Tissue Injuries in Elite Collision Sport Athletes
  • T. Gabbett
  • Education
    Journal of strength and conditioning research
  • 2010
TLDR
An injury prediction model based on planned and actual training loads was developed and implemented to determine if noncontact, soft-tissue injuries could be predicted and therefore prevented in elite collision sport athletes and provide information on the training dose-response relationship and a scientific method of monitoring and regulating training load in elite collisions sport athletes.
Effect of high-speed running on hamstring strain injury risk
TLDR
Exposing players to large and rapid increases in HSR distances above their 2-yearly session average increased the odds of HSI, however, reducing HSR in week −1 may offset HSI risk.
The reliability of MinimaxX accelerometers for measuring physical activity in Australian football.
TLDR
The reliability of the MinimaxX accelerometer is acceptable both within and within devices under controlled laboratory conditions, and between devices during field testing, suggesting that accelerometers can detect changes or differences in physical activity during Australian football.
Calculating acute:chronic workload ratios using exponentially weighted moving averages provides a more sensitive indicator of injury likelihood than rolling averages
TLDR
It is demonstrated that large spikes in workload are associated with an increased injury risk using both models, although the EWMA model is more sensitive to detect increases in injury risk with higher ACWR.
How do training and competition workloads relate to injury? The workload—injury aetiology model
TLDR
An updated injury aetiology model is proposed which includes the effects of workloads and describes how this model explains the load—injury relationships for total workloads, acute:chronic workload ratios and the training load-injury paradox.
...
...