INTRODUCTION:
Hamstring strain injuries (HSI) remain a major concern in soccer. Yet existing prediction models fail to account for the multifactorial nature of injury risk. Key factors such as sprint kinematics, performance fatigability, and psychological influences have been largely overlooked. The aim of this study was to develop a parsimonious and multidisciplinary model to identify players at risk of HSI using a single preseason screening session. Additionally, we compared this model’s predictive accuracy to that of individual predictors.
METHODS:
A total of 120 male and female soccer players competing at regional and national levels underwent preseason assessments, including psychological, physiological, biomecanical, and behavioural variables. Injury occurrence was prospectively monitored throughout the competitive season. After variable selection, logistic regression with the Wald backward stepwise method was used to refine the model. The predictive abilities of the final model and individual variables were determined using the area under the receiver operating characteristic curve (AUC).
RESULTS:
Twenty-nine players sustained an HSI during the follow-up period. The final model included eight predictors: age, sex, HSI history, knee flexor performance fatigability, sprint performance (best sprint time and maximal theoretical velocity), perceived vulnerability to injury, and subjective norms regarding pain and fatigue in soccer. It demonstrated strong predictive accuracy (AUC = 0.82, sensitivity = 79%). No individual predictor, when considered independently, reached sufficient discriminative power (AUC ≤ 0.65).
CONCLUSION:
Assessing single risk predictors does not allow for accurate HSI prediction in soccer players. In contrast, our multidisciplinary model achieved high accuracy in identifying at-risk players. Parsimonious in its design, it highlights the interest of both multifactorial and multidisciplinary approach. Notably, knee flexor performance fatigability following repeated sprints emerged as a key predictor, emphasizing the role of fatigue in HSI occurrence. Additionaly, sprint performance and psychological variables significantly contributed to injury prediction, reinforcing the need for an integrated approach to injury prevention. If externally validated, the present model could serve as a valuable tool for injury prevention strategies. in soccer teams.