TY - JOUR
T1 - Preseason multiple biomechanics testing and dimension reduction for injury risk surveillance in elite female soccer athletes
T2 - short-communication
AU - De la Fuente, Carlos
AU - Silvestre, Rony
AU - Yañez, Roberto
AU - Roby, Matias
AU - Soldán, Macarena
AU - Ferrada, Wilson
AU - Carpes, Felipe P.
N1 - Publisher Copyright:
© 2022 Informa UK Limited, trading as Taylor & Francis Group.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - biomechanics
KW - football
KW - machine learning
KW - non-linear reduction
KW - Sports
UR - http://www.scopus.com/inward/record.url?scp=85130906100&partnerID=8YFLogxK
U2 - 10.1080/24733938.2022.2075558
DO - 10.1080/24733938.2022.2075558
M3 - Article
C2 - 35522903
AN - SCOPUS:85130906100
SN - 2473-3938
VL - 7
SP - 183
EP - 188
JO - Science and Medicine in Football
JF - Science and Medicine in Football
IS - 2
ER -