Abstract
Lower extremity non-contact soft tissue (LE-ST) injuries are prevalent in elite futsal. The purpose of this study was to develop robust screening models based on pre-season measures obtained from questionnaires and field-based tests to prospectively predict LE-ST injuries after having applied a range of supervised Machine Learning techniques. One hundred and thirty-nine elite futsal players underwent a pre-season screening evaluation that included individual characteristics; measures related to sleep quality, athlete burnout, psychological characteristics related to sport performance and self-reported perception of chronic ankle instability. A number of neuromuscular performance measures obtained through three field-based tests [isometric hip strength, dynamic postural control (Y-Balance) and lower extremity joints range of motion (ROM-Sport battery)] were also recorded. Injury incidence was monitored over one competitive season. There were 25 LE-ST injuries. Only those groups of measures from two of the field-based tests (ROM-Sport battery and Y-Balance), as independent data sets, were able to build robust models [area under the receiver operating characteristic curve (AUC) score ≥0.7] to identify elite futsal players at risk of sustaining a LE-ST injury. Unlike the measures obtained from the five questionnaires selected, the neuromuscular performance measures did build robust prediction models (AUC score ≥0.7). The inclusion in the same data set of the measures recorded from all the questionnaires and field-based tests did not result in models with significantly higher performance scores. The model generated by the UnderBagging technique with a cost-sensitive SMO as the base classifier and using only four ROM measures reported the best prediction performance scores (AUC = 0.767, true positive rate = 65.9% and true negative rate = 62%). The models developed might help coaches, physical trainers and medical practitioners in the decision-making process for injury prevention in futsal.
Highlights
Lower extremity non-contact soft tissue (LE-ST) injuries are very common events in intermittent team sports such as soccer (López-Valenciano et al, 2019), futsal (Ruiz-Pérez et al, 2020), rugby (Williams et al, 2013), bat and stick sports (Panagodage Perera et al, 2018)
As base classifier building a model with area under the receiver operator characteristics (AUC) scores ≥ 0.7 (AUC = 0.701 ± 0.112). This model is comprised for 100 different C4.5 decision trees (Figure 2 shows an example of one of these C4.5 decision trees, the rest can be got upon request to the authors)
The fact that the best-performing model built with the ROM data set (DS 6) showed a significantly higher prediction performance [and less decision trees (1 vs. 100)] than its counterpart model built with the dynamic postural control data set (DS 7) (F-score = 0.450 vs. 0.388) may be due to the fact that the scores obtained thorough the Y-Balance test are widely influenced by hip and knee flexion and the ankle dorsiflexion ROM measures in the sagittal plane and to less extend by dynamic core stability and isokinetic knee flexion strength measures (Ruiz-Pérez et al, 2019)
Summary
Lower extremity non-contact soft tissue (muscle, tendon, and ligament) (LE-ST) injuries are very common events in intermittent team sports such as soccer (López-Valenciano et al, 2019), futsal (Ruiz-Pérez et al, 2020), rugby (Williams et al, 2013), bat (i.e., cricket and softball) and stick (i.e., field hockey and lacrosse) sports (Panagodage Perera et al, 2018). When several injuries are sustained, team success (Eirale et al, 2013) and club finances can suffer (Fair and Champa, 2019; Eliakim et al, 2020). Given that the risk of sustaining a LE-ST injury can be mitigated when tailored measures are delivered, development of a validated screening model to profile injury risk would be a useful tool to help practitioners address this recurrent problem in team sports. Despite the substantive efforts made by the scientific community and sport practitioners, none of the currently available screening models (based on potential risk factors) designed to identify athletes at high risk of suffering a LE-ST injury, have adequate predictive properties (i.e., accuracy, sensitivity, and specificity) (Bahr, 2016)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
