Analysis Of Plasma D-Dimer Behavior After A HIIT Session By Machine Learning Exploratory Technique

Sport omics has sought to understand immunometabolism. Fifteen athletes of MMA were submitted to HIIT to evaluate acute stress and the kinetics of D-dimer. After applying the Euclidean dissimilarity measure, two dendrograms were proposed that presented three clusters of d-dimer behavior. Cohen’s d and r were calculated for the three clusters formed, confirming the choice. The network plot with the Fruchterman algorithm identified that the cluster formed by athletes 4, 7, 15, and 16 had a more differentiated behavior than the other two clusters. The D-dimer does not show similar kinetics, even in a highly homogeneous group subjected to the same type, time, and intensity of stress, presenting itself as a potentially more sensitive biomarker for stress, going far beyond a vascular marker, as perceived during the COVID-19 pandemic. The use of exploratory machine learning techniques for analysis D-Dimer has been suggested since its behavior is highly individual, not allowing analysis only by means.

Keywords:Sportomics; Data mining; Sports Medicine