Yes, rolling averages are a good way to assess training load for injury prevention. Is there a better way? Probably, but we have not seen the evidence

Data Mining Paths for Standard Weekly Training Load in Sub-Elite Young Football Players: A Machine Learning Approach

The aim of this study was to test a machine learning (ML) model to predict high-intensity actions and body impacts during youth football training. Sixty under-15, -17, and -19 sub-elite Portuguese football players were monitored over a 6-week period. External training load data were collected from the target variables of accelerations (ACCs), decelerations (DECs), and dynamic stress load (DSL) using an 18 Hz global positioning system (GPS). Additionally, we monitored the perceived exertion and biological characteristics using total quality recovery (TQR), rating of perceived exertion (RPE), session RPE (sRPE), chronological age, maturation offset (MO), and age at peak height velocity (APHV). The ML model was computed by a feature selection process with a linear regression forecast and bootstrap method. The predictive analysis revealed that the players' MO demonstrated varying degrees of effectiveness in predicting their DEC and ACC across different ranges of IQR. After predictive analysis, the following performance values were observed: DEC (x¯predicted = 41, β = 3.24, intercept = 37.0), lower IQR (IQRpredicted = 36.6, β = 3.24, intercept = 37.0), and upper IQR (IQRpredicted = 46 decelerations, β = 3.24, intercept = 37.0). The player's MO also demonstrated the ability to predict their upper IQR (IQRpredicted = 51, β = 3.8, intercept = 40.62), lower IQR (IQRpredicted = 40, β = 3.8, intercept = 40.62), and ACC (x¯predicted = 46 accelerations, β = 3.8, intercept = 40.62). The ML model showed poor performance in predicting the players' ACC and DEC using MO (MSE = 2.47-4.76; RMSE = 1.57-2.18: R2 = -0.78-0.02). Maturational concerns are prevalent in football performance and should be regularly checked, as the current ML model treated MO as the sole variable for ACC, DEC, and DSL. Applying ML models to assess automated tracking data can be an effective strategy, particularly in the context of forecasting peak ACC, DEC, and bodily effects in sub-elite youth football training.

A Cherry, Ripe for Picking: The Relationship Between the Acute-Chronic Workload Ratio and Health Problems

OBJECTIVE

To investigate whether the relationship between the acute-chronic workload ratio (ACWR) and health problems varies when different methodological approaches are used to quantify it.

DESIGN

Prospective cohort study.

METHODS

An online questionnaire was used to collect daily health and training information from 86 elite youth footballers for 105 days. The relationship between players' training load and health was analyzed using a range of different definitions of ACWR and health problems. We used 21-day and 28-day chronic periods, coupled and uncoupled calculations, and the exponentially weighted moving average and rolling average. Acute-chronic workload ratio data were categorized as low, medium, or high, using predefined categories and z scores. We compared medium to high, medium to low, and low to high categories. The outcome was defined in 3 ways: "all health problems," "all injuries," and "new noncontact injuries." We performed random-effects logistic regression analyses of all combinations, for a total of 108 analyses.

RESULTS

We recorded 6250 athlete-days and 196 health problems. Of the 108 analyses performed, 23 (21%) identified a statistically significant (P<.05) association between the ACWR and health problems. A greater proportion of significant associations were identified when using an exponentially weighted moving average (44% of analyses), when comparing low to high categories (33%), and when using the "all health problems" definition (33%).

CONCLUSION

The relationship between the ACWR and health problems was dependent on methodological approach. J Orthop Sports Phys Ther 2021;51(4):162-173. Epub 20 Jan 2021. doi:10.2519/jospt.2021.9893.

What Role Do Chronic Workloads Play in the Acute to Chronic Workload Ratio? Time to Dismiss ACWR and Its Underlying Theory

AIM

The aim of this study was to examine the associations between the injury risk and the acute (AL) to chronic (CL) workload ratio (ACWR) by substituting the original CL with contrived values to assess the role of CL (i.e., the presence and implications of statistical artefacts).

METHODS

Using previously published data, we generated a contrived ACWR by dividing the AL by fixed and randomly generated CLs, and we compared these results to real data. We also reproduced previously reported subgroup analyses, including dichotomising players' data above and below the median CL. Our analyses follow the same, previously published modelling approach.

RESULTS

The analyses with original data showed effects compatible with higher injury risk for ACWR only (odd ratios, OR: 2.45, 95% CI 1.28-4.71). However, we observed similar effects by dividing AL by the "contrived" fixed and randomly generated CLs: OR 1.95 (1.18-3.52) dividing by 1510 (average CL); and OR ranging from 1.16 to 2.07, using random CL 1.53 (mean). Random ACWRs reduced the variance relative to the original AL and further inflated the ORs (mean OR 1.89, from 1.42 to 2.70). ACWR causes artificial reclassification of players compared to AL alone. Finally, neither ACWR nor AL alone confer a meaningful predictive advantage to an intercept-only model, even within the training sample (c-statistic 0.574/0.544 vs. 0.5 in both ACWR/AL and intercept-only models, respectively).

DISCUSSION

ACWR is a rescaling of the explanatory variable (AL, numerator), in turn magnifying its effect estimates and decreasing its variance despite conferring no predictive advantage. Other ratio-related transformations (e.g., reducing the variance of the explanatory variable and unjustified reclassifications) further inflate the OR of AL alone with injury risk. These results also disprove the etiological theory behind this ratio and its components. We suggest ACWR be dismissed as a framework and model, and in line with this, injury frameworks, recommendations, and consensus be updated to reflect the lack of predictive value of and statistical artefacts inherent in ACWR models.

Robust Exponential Decreasing Index (REDI): adaptive and robust method for computing cumulated workload

Objective

The purpose of this study was to define a new index the Robust Exponential Decreasing Index (REDI), which is capable of an improved analysis of the cumulative workload. This allows for precise control of the decreasing influence of load over time. Additionally, REDI is robust to missing data that are frequently present in sport.

Methods

200 cumulative workloads were simulated in two ways (Gaussian and uniform distributions) to test the robustness and flexibility of the REDI, as compared with classical methods (acute:chronic workload ratio and exponentially weighted moving average). Theoretical properties have been highlighted especially around the decreasing parameter.

Results

The REDI allows practitioners to consistently monitor load with missing data as it remains consistent even when a significant portion of the dataset is absent. Adjusting the decreasing parameter allows practitioners to choose the weight given to each daily workload.

Discussion

Computation of cumulative workload is not easy due to many factors (weekends, international training sessions, national selections and injuries). Several practical and theoretical drawbacks of the existing indices are discussed in the paper, especially in the context of missing data; the REDI aims to settle some of them. The decreasing parameter may be modified according to the studied sport. Further research should focus on methodology around setting this parameter.

Conclusion

The robust and adaptable nature of the REDI is a credible alternative for computing a cumulative workload with decreasing weight over time.

Towards a complex systems approach in sports injury research: simulating running-related injury development with agent-based modelling

OBJECTIVES

There have been recent calls for the application of the complex systems approach in sports injury research. However, beyond theoretical description and static models of complexity, little progress has been made towards formalising this approach in way that is practical to sports injury scientists and clinicians. Therefore, our objective was to use a computational modelling method and develop a dynamic simulation in sports injury research.

METHODS

Agent-based modelling (ABM) was used to model the occurrence of sports injury in a synthetic athlete population. The ABM was developed based on sports injury causal frameworks and was applied in the context of distance running-related injury (RRI). Using the acute:chronic workload ratio (ACWR), we simulated the dynamic relationship between changes in weekly running distance and RRI through the manipulation of various 'athlete management tools'.

RESULTS

The findings confirmed that building weekly running distances over time, even within the reported ACWR 'sweet spot', will eventually result in RRI as athletes reach and surpass their individual physical workload limits. Introducing training-related error into the simulation and the modelling of a 'hard ceiling' dynamic resulted in a higher RRI incidence proportion across the population at higher absolute workloads.

CONCLUSIONS

The presented simulation offers a practical starting point to further apply more sophisticated computational models that can account for the complex nature of sports injury aetiology. Alongside traditional forms of scientific inquiry, the use of ABM and other simulation-based techniques could be considered as a complementary and alternative methodological approach in sports injury research.

Prediction of running-induced Achilles tendinopathy with pain sensitivity - a 1-year prospective study

Background and aims Achilles tendinopathy is common among runners, but the etiology remains unclear. High mechanical pain sensitivity may be a predictor of increased risk of developing Achilles tendinopathy in this group. The purpose of this study was to investigate whether local pain sensitivity could predict the development of Achilles tendinopathy in recreational male runners. The overall hypothesis was that high pain sensitivity would be related to a higher risk of developing Achilles tendinopathy among recreational male runners. Methods Ninety-nine recreational male runners were recruited and followed prospectively for 1 year. At baseline and after 500 km of running the pressure pain threshold (PPT) was assessed at the infraspinatus and at the Achilles tendon (AT-PPT). Based on the AT-PPT at baseline, a median split was used to divide the runners into two groups. The high pain sensitivity groups was defined as runners displaying a pain pressure threshold below 441 kPa on the Achilles tendon, while the low pain sensitivity group was defined as runners displaying a pain pressure threshold above 441 kPa on the Achilles tendon, respectively. Subsequently, the cumulative risk difference between the two groups was assessed by using the pseudo-observation method. Results High pain sensitivity runners sustained 5%-point (95% CI: -0.18 to 0.08) more Achilles tendinopathy episodes during the first 1,500 km. No significant group differences in risk were found at 100, 250, 500, 1,000 and 1,500 km of running. Conclusions No significant association was found between mechanical pain sensitivity in the Achilles tendon and the risk of developing Achilles tendinopathy. However, the risk difference indicated a association between a high mechanical pain sensitivity and an increased risk of developing Achilles tendinopathy. It is plausible that changes in pain sensitivity were masked by unmeasured covariates, such as the differences in progression/regression of training volume and running speed between the two groups. This study was limited in size, which limited the possibility to account for covariates, such as differences in progression/regression of running speed between runners. With the limitations in mind, future studies should control the training volume, speed and running shoes in the design or account for it in the analysis. Implications Pain sensitivity of the Achilles tendon seems not to be related to an increased risk of developing Achilles pain in relation to running.

Time-to-event analysis for sports injury research part 1: time-varying exposures

BACKGROUND

'How much change in training load is too much before injury is sustained, among different athletes?' is a key question in sports medicine and sports science. To address this question the investigator/practitioner must analyse exposure variables that change over time, such as change in training load. Very few studies have included time-varying exposures (eg, training load) and time-varying effect-measure modifiers (eg, previous injury, biomechanics, sleep/stress) when studying sports injury aetiology.

AIM

To discuss advanced statistical methods suitable for the complex analysis of time-varying exposures such as changes in training load and injury-related outcomes.

CONTENT

Time-varying exposures and time-varying effect-measure modifiers can be used in time-to-event models to investigate sport injury aetiology. We address four key-questions (i) Does time-to-event modelling allow change in training load to be included as a time-varying exposure for sport injury development? (ii) Why is time-to-event analysis superior to other analytical concepts when analysing training-load related data that changes status over time? (iii) How can researchers include change in training load in a time-to-event analysis? and, (iv) Are researchers able to include other time-varying variables into time-to-event analyses? We emphasise that cleaning datasets, setting up the data, performing analyses with time-varying variables and interpreting the results is time-consuming, and requires dedication. It may need you to ask for assistance from methodological peers as the analytical approaches presented this paper require specialist knowledge and well-honed statistical skills.

CONCLUSION

To increase knowledge about the association between changes in training load and injury, we encourage sports injury researchers to collaborate with statisticians and/or methodological epidemiologists to carefully consider applying time-to-event models to prospective sports injury data. This will ensure appropriate interpretation of time-to-event data.

The Individual and Combined Effects of Multiple Factors on the Risk of Soft Tissue Non-contact Injuries in Elite Team Sport Athletes

Aim: Relationships between athlete monitoring-derived variables and injury risk have been investigated predominantly in isolation. The aim of this study was to evaluate the individual and combined effects of multiple factors on the risk of soft-tissue non-contact injuries in elite team sport athletes. Methods: Fifty-five elite Australian footballers were prospectively monitored over two consecutive seasons. Internal and external training load was quantified using the session rating of perceived exertion and GPS/accelerometry, respectively. Cumulative load and acute-to-chronic workload ratios were derived using rolling averages and exponentially weighted moving averages. History of injuries in the current and previous seasons was recorded along with professional experience, weekly musculoskeletal screening, and subjective wellness scores for individual athletes. Individual and combined effects of these variables on injury risk were evaluated with generalized linear mixed models. Results: High cumulative loads and acute-to-chronic workload ratios were associated with increased risk of injuries. The effects for measures derived using exponentially weighted moving averages were greater than those for rolling averages. History of a recent injury, long-term experience at professional level, and substantial reductions in a selection of musculoskeletal screening and subjective wellness scores were associated with increased risk. The effects of high cumulative loads were underestimated by ~20% before adjusting for previous injuries, whereas the effects of high acute-to-chronic workload ratios were overestimated by 10-15%. Injury-prone players, identified via player identity in the mixed model, were at > 5 times higher risk of injuries compared to robust players (hazard ratio 5.4, 90% confidence limits 3.6-12) despite adjusting for training load and previous injuries. Combinations of multiple risk factors were associated with extremely large increases in risk; for example, a hazard ratio of 22 (9.7-52) was observed for the combination of high acute load, recent history of a leg injury, and a substantial reduction in the adductor squeeze test score. Conclusion: On the basis of our findings with an elite team of Australian footballers, the 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.