A random forest model combining multiple monitored variables significantly improved injury forecasting performance compared to a training load-only model, achieving a Matthews Correlation Coefficient of 0.13 versus -0.02 (p<0.01).
Observational (n=11)
No
Does a random forest model combining multiple monitored variables improve injury forecasting compared to a model using only training load in elite female short-track speed skaters?
Combining a wide array of monitored variables significantly improves the injury forecasting performance of random forest models compared to using training load alone in elite female speed skaters.
Estimación del efecto: Cohen d > 1
Tasa de eventos absoluta: 0.13% vs -0.02%
valor p: p=<0.01
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 physiological adaptations and long-term development. This study aims to present a framework for developing random forest classifier models, forecasting injuries in the upcoming 1 to 7 days, to assist the performance support staff in reducing injuries and maximizing performance within the Canadian National Female Short-Track Speed Skating Program. Forty different variables monitored daily over two seasons (2018–2019 and 2019–2020) were used to develop two sets of forecasting models. One includes only training load variables (TL), and a second (ALL) combines a wide array of monitored variables (neuromuscular function, heart rate variability, training load, psychological wellbeing, past injury type, and location). The sensitivity (ALL: 0.35 ± 0.19, TL: 0.23 ± 0.03), specificity (ALL: 0.81 ± 0.05, TL: 0.74 ± 0.03) and Matthews Correlation Coefficients (MCC) (ALL: 0.13 ± 0.05, TL: −0.02 ± 0.02) were computed. Paired T -test on the MCC revealed statistically significant ( p 0.01) and large positive effects (Cohen d 1) for the ALL forecasting models' MCC over every forecasting window (1 to 7 days). These models were highly determined by the athletes' training completion, lower limb and trunk/lumbar injury history, as well as sFatigue, a training load marker. The TL forecasting models' MCC suggests they do not bring any added value to forecast injuries. Combining a wide array of monitored variables and quantifying the injury etiology conceptual components significantly improve the injury forecasting performance of random forest models. The ALL forecasting models' performances are promising, especially on one time windows of one or two days, with sensitivities and specificities being respectively above 0.5 and 0.7. They could add value to the decision-making process for the support staff in order to assist the Canadian National Female Team Short-Track Speed Skating program in reducing the number of incomplete training days, which could potentially increase performance. On longer forecasting time windows, ALL forecasting models' sensitivity and MCC decrease gradually. Further work is needed to determine if such models could be useful for forecasting injuries over three days or longer.
Briand et al. (Thu,) realizaron un estudio observacional en lesiones deportivas (n=11). Se evaluó un modelo de bosque aleatorio combinando múltiples variables monitoreadas (ALL) frente a un modelo de bosque aleatorio que utiliza solo variables de carga de entrenamiento (TL) en base al Coeficiente de Correlación de Matthews (MCC) para predecir lesiones durante 1 a 7 días (Cohen d > 1, p=<0.01). Un modelo de bosque aleatorio que combina múltiples variables monitoreadas mejoró significativamente el rendimiento de la predicción de lesiones en comparación con un modelo basado solo en la carga de entrenamiento, logrando un Coeficiente de Correlación de Matthews de 0.13 frente a -0.02 (p<0.01).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: