Calculating acute:chronic workload ratios using exponentially weighted moving averages provides a more sensitive indicator of injury likelihood than rolling averages

Murray, Nicholas P.; Gabbett, Tim J.; Townshend, Andrew D.; Blanch, Peter

doi:10.1136/bjsports-2016-097152

Cited by 137 publications

(204 citation statements)

References 30 publications

Supporting

Mentioning

185

Contrasting

Unclassified

Order By: Relevance

“…We reproduce the ACWR methodology for each of the 12 workload features used in our study, using the ACWR groups suggested by Murray et al [26]. They compute the ACWR for a set of (high); (5) ACWR > 2.00 (very high).…”

Section: S2 Appendix the Acwr Methodsmentioning

confidence: 99%

“…Then, the injury likelihood (IL) is estimated in every ACWR group as the ratio between the number of players who get injured after the training session assigned to that ACWR group and the number of players who do not. Murray et al [26] observe that players whose training sessions result in ACWR > 2 have a higher injury risk than the players in the other groups (i.e., a high IL). In contrast with the literature, we do not find any individual training session resulting in ACWR > 2 (see S2 Fig), while we observe that players whose individual training sessions result in ACWR < 1 have the highest injury risk (S2 Fig).…”

Section: S2 Appendix the Acwr Methodsmentioning

confidence: 99%

“…We also replicate the experiment by using ACWR groups defined by the quintiles of the ACWR distribution instead of the pre-defined groups proposed by Murray et al [26]. S3 Fig shows the injury likelihood (IL) for every ACWR quintile for all the 12 workload features.…”

Section: S2 Appendix the Acwr Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Effective injury forecasting in soccer with GPS training data and machine learning

et al. 2018

View full text Add to dashboard Cite

Injuries have a great impact on professional soccer, due to their large influence on team performance and the considerable costs of rehabilitation for players. Existing studies in the literature provide just a preliminary understanding of which factors mostly affect injury risk, while an evaluation of the potential of statistical models in forecasting injuries is still missing. In this paper, we propose a multi-dimensional approach to injury forecasting in professional soccer that is based on GPS measurements and machine learning. By using GPS tracking technology, we collect data describing the training workload of players in a professional soccer club during a season. We then construct an injury forecaster and show that it is both accurate and interpretable by providing a set of case studies of interest to soccer practitioners. Our approach opens a novel perspective on injury prevention, providing a set of simple and practical rules for evaluating and interpreting the complex relations between injury risk and training performance in professional soccer.

show abstract

Section: S2 Appendix the Acwr Methodsmentioning

confidence: 99%

Section: S2 Appendix the Acwr Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Effective injury forecasting in soccer with GPS training data and machine learning

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The most common timeframe used was a 1-week acute training load and 4-week chronic training load. [9][10][11]17,18,[20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36] Other timeframes included a 3-day acute load and a 21 daychronic load, 19 or varying timeframes. [37][38][39][40] One study examined various timeframes for calculating ACWR, 37 utilizing 2-9 days for acute loads, and chronic loads varying from 14 to 35 days, while the other study ranged from 1 to 2 weeks for acute loads, and 3-8 weeks for chronic loads, but only utilized the 1:4 week ratio for relationship to injury.…”

Section: Study Characteristicsmentioning

confidence: 99%

“…[37][38][39][40] One study examined various timeframes for calculating ACWR, 37 utilizing 2-9 days for acute loads, and chronic loads varying from 14 to 35 days, while the other study ranged from 1 to 2 weeks for acute loads, and 3-8 weeks for chronic loads, but only utilized the 1:4 week ratio for relationship to injury. 38 Five studies utilized exponentially weighted moving averages (EWMA) for their calculation of ACWR 17,27,29,36,39 and four articles studied a combination of ACWR and chronic workload. 11,30,38,39 Lastly, one study examined ACWR in combination with recent lower limb injuries, 36 while another evaluated the effects of fitness on the relationship between ACWR and injury risk.…”

Section: Study Characteristicsmentioning

confidence: 99%

<p>The Relationship Between Acute: Chronic Workload Ratios and Injury Risk in Sports: A Systematic Review</p>

Maupin¹,

Schram²,

Canetti³

et al. 2020

OAJSM

View full text Add to dashboard Cite

Purpose: Low injury rates have previously been correlated with sporting team success, highlighting the importance of injury prevention programs. Recent methods, such as acute: chronic workload ratios (ACWR) have been developed in an attempt to predict and manage injury risk; however, the relation between these methods and injury risk is unclear. The aim of this systematic review was to identify and synthesize the key findings of studies that have investigated the relationship between ACWR and injury risk. Methods: Included studies were critically appraised using the Downs and Black checklist, and a level of evidence was determined. Relevant data were extracted, tabulated, and synthesized. Results: Twenty-seven studies were included for review and ranged in percentage quality scores from 48.2% to 64.3%. Almost perfect interrater agreement (κ = 0.885) existed between raters. This review found a high variability between studies with different variables studied (total distance versus high speed running), as well as differences between ratios analyzed (1.50-1.80 versus ≥1.50), and reference groups (a reference group of 0.80-1.20 versus ≤0.85). Conclusion: Considering the high variability, it appears that utilizing ACWR for external (eg, total distance) and internal (eg, heart rate) loads may be related to injury risk. Calculating ACWR using exponentially weighted moving averages may potentially result in a more sensitive measure. There also appears to be a trend towards the ratios of 0.80-1.30 demonstrating the lowest risk of injury. However, there may be issues with the ACWR method that must be addressed before it is confidently used to mitigate injury risk. Utilizing standardized approaches will allow for more objective conclusions to be drawn across multiple populations.

show abstract

Team's average acute:chronic workload ratio correlates with injury risk in NCAA men's soccer team

Bakal

Friedrich

Keane

et al. 2023

PM&R

View full text Add to dashboard Cite

BackgroundResearch in multiple sports has shown that an individual's acute:chronic workload ratio (ACWR) correlates with injury. However, tailoring team trainings to each individual's ACWR is technically challenging and has not been found to decrease injury risk.ObjectiveTo establish a more feasible method of utilizing the ACWR for injury prevention in soccer. In a National Collegiate Athletic Association (NCAA) men's soccer team, we assessed whether the team's average ACWR, as opposed to that of each individual, correlated with injuries sustained throughout the season.DesignInjury and workload data were retrospectively evaluated for all players (n = 23) of an NCAA men's soccer team during one 18‐week season. Workload data for five global positioning system (GPS)‐derived workload variables (total distance, high‐speed distance, accelerations, player load, and average velocity) were used to calculate the team's average daily acute and chronic workloads (accumulated load for each variable during the past 3 and 28 days, respectively), and uncoupled ACWRs (acute workload divided by chronic workload for each variable). A retrospective cohort design was used to compare the team's workloads and ACWRs on days where ≥1 injury occurred versus days where zero injuries occurred using binary logistic regression models.ResultsTrainings/games with injuries had higher acute workloads, lower chronic workloads, and higher ACWRs for all five workload variables. In multivariable analysis, risk factors for injury included a low chronic workload for total distance (odds ratio [OR] 7.23, p = .024) and an ACWR >1.4 for accelerations (OR 4.34, p = .029).ConclusionsThe team's injury risk was greater with low distance accumulation during the chronic period and with an elevated ACWR for accelerations. Future intervention‐based studies aimed at using ACWR load‐management principles as a method of decreasing injury risk in soccer can consider tracking the team's average values with the goal of maintaining a consistent chronic workload for total distance and avoiding elevations in the ACWR for accelerations.

show abstract

Calculating acute:chronic workload ratios using exponentially weighted moving averages provides a more sensitive indicator of injury likelihood than rolling averages

Abstract: These findings demonstrate 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.

Cited by 137 publications

References 30 publications

Effective injury forecasting in soccer with GPS training data and machine learning

Effective injury forecasting in soccer with GPS training data and machine learning

<p>The Relationship Between Acute: Chronic Workload Ratios and Injury Risk in Sports: A Systematic Review</p>

Team's average acute:chronic workload ratio correlates with injury risk in NCAA men's soccer team

Contact Info

Product

Resources

About