Search

Sport scientists could benefit from knowing about the processes underpinning machine learning (ML) and its practical applications, as it has substantial implications for our field. ML has already h...

Classification algorithms determine the similarity of an observation to defined classes, e.g., injured or healthy athletes, and can highlight treatment targets or assess progress of a treatment. The primary aim was to cross-validate a previously developed classification algorithm using a different sample, while a secondary aim was to examine its ability to predict future ACL injuries. The examined outcome measure was 'healthy-limb' class membership probability, which was compared between a cohort of athletes without previous or future (No Injury) previous (PACL) and future ACL injury (FACL). The No Injury group had significantly higher probabilities than the PACL (p < 0.001; medium effect) and FACL group (p ≤ 0.045; small effect). The ability to predict group membership was poor for the PACL (area under curve [AUC]; 0.61

The effectiveness of vertical drop jumps (VDJs) to screen for non-contact ACL injuries is unclear. This may be contributed to by discrete point analysis, which does not evaluate patterns of movement. Also, limited research exists on the second landing of VDJs, potential lower limb performance asymmetries and the effect of fatigue. Statistical parametric mapping investigated the main effects of landing, limb dominance and a high intensity, intermittent exercise protocol (HIIP) on VDJ biomechanics. Twenty-two male athletes (21.9 ± 1.1 years, 180.5 ± 5.5 cm, 79.4 ± 7.8 kg) performed VDJs pre- and post-HIIP. Repeated measures ANOVA identified pattern differences during the eccentric phases of the first and second landings bilaterally. The first landing displayed greater (internal) knee flexor (η2 = 0.165), external rotator (η2 = 0.113) and valgus (η2 = 0.126) moments and greater hip (η2 = 0.062) and knee (η2 = 0.080) flexion. The dominant limb generated greater knee flexor (η2 = 0.062), external rotator (η2 = 0.110) and valgus (η2 = 0.065) moments. The HIIP only had one effect, increased thoracic flexion relative to the pelvis (η2 = 0.088). Finally, the dominant limb demonstrated greater knee extensor moments during the second landing (η2 = 0.100). ACL injury risk factors were present in both landings of VDJs with the dominant limb at potentially greater injury risk. Therefore, VDJ screenings should analyse both landings bilaterally.