RESUMEN
BACKGROUND: Injury risk is regularly assessed during the preseason in susceptible populations like female soccer players. However, multiple outcomes (high-dimensional dataset) derived from multiple testing may make pattern recognition difficult. Thus, dimension reduction and clustering may be useful for improving injury surveillance when results of multiple assessment tools are available. AIM: To determine the influence of dimension reduction for pattern recognition followed by clustering on multiple biomechanical injury markers in elite female soccer players during preseason. METHDOLOGY: We introduced the use of dimension reduction through linear principal component analysis (PCA), non-linear kernel principal component analysis (k-PCA), t-distributed stochastic neighbor embedding (t-sne), and uniform manifold approximation and projection (umap) for injury markers via grid search. Muscle strength, muscle function, jump technique and power, balance, muscle stiffness, exercise tolerance, and running performance were assessed in an elite female soccer team (n = 21) prior to the competitive season. RESULTS: As a result, umap facilitated the injury pattern recognition compared to PCA, k-PCA, and t-sne. One of the three patterns was related to a team subgroup with acceptable muscle conditions. In contrast, the other two patterns showed higher injury risk profiles. For our dataset, umap improved injury surveillance through multiple testing characteristics. CONCLUSION: Dimension reduction and clustering techniques present as useful strategies to analyze subgroups of female soccer players who have different risk profiles for injury.
Asunto(s)
Traumatismos en Atletas , Fútbol , Humanos , Femenino , Fútbol/lesiones , Fenómenos Biomecánicos , Traumatismos en Atletas/epidemiología , Atletas , Fuerza Muscular/fisiologíaRESUMEN
BACKGROUND:: Tendon overuse injuries are an issue in elite footballers (soccer players) and may affect tendon function. Achilles and patellar tendinopathy are the most frequent pathologies. Tendon stiffness, the relationship between the force applied to a tendon and the displacement exerted, may help represent tendon function. Stiffness is affected by training and pathology. Nevertheless, information regarding this mechanical property is lacking for elite soccer athletes. HYPOTHESIS:: Achilles and patellar tendon stiffness assessed using myotonometric measurements will be greater in elite soccer athletes than in control participants. STUDY DESIGN:: Cross-sectional study. LEVEL OF EVIDENCE:: Level 4. METHODS:: Forty-nine elite soccer athletes and 49 control participants were evaluated during the 2017 preseason. A handheld device was used to measure Achilles and patellar tendon stiffness. Dominant and nondominant limbs were assessed for both groups. RESULTS:: A significantly stiffer patellar tendon was found for both the dominant and the nondominant limb in the elite soccer athletes compared with the control group. Nevertheless, no differences were found in Achilles tendon stiffness between groups. When comparing between playing positions in soccer athletes, no significant differences were found for both tendons. CONCLUSION:: Greater patellar tendon stiffness may be related to an improvement in force transmission during muscle contraction. On the other hand, it seems that after years of professional training, Achilles tendon stiffness does not change, conserving the storing-releasing function of elastic energy. The nonsignificant differences between positions may be attributable to the years of homogeneous training that the players underwent. CLINICAL RELEVANCE:: The present study shows another technique for measuring mechanical properties of tendons in soccer athletes that could be used in clinical settings. In the future, this technique may help clinicians choose the best exercise protocol to address impairments in tendon stiffness.