Application of Big Data Analysis in Model Construction to Prevent Athlete Injury in Training

Abstract

Sports injury is a hot issue in the field of exercise science and sports medicine and a practical problem that needs to be solved urgently. Based on big data analysis, this paper proposes an Ada-RF prediction model that integrates the fusion of the Adaboost algorithm and Random Forest algorithm by studying five machine learning algorithms: logistic regression, k-nearest neighbor, plain Bayes, Adaboost algorithm, and Random Forest and evaluates experiments through the model evaluation criteria. The influence factors of injury risk in adolescent male basketball players were explored in terms of demographic information, training load, subjective perceived health, and assessment of athletic quality. By screening the important factors as independent variables, the risk of athlete injury and illness as dependent variables were applied to the model constructed in this paper and the models built by five traditional machine learning classification algorithms. The prediction effects of multiple models are compared. The experimental results show that the accuracy, recall, specificity, F1 score, sensitivity, and AUC value of the Ada-RF model constructed in this paper are 0.869, 0.885, 0.755, 0.683, 0.754, and 0.789, respectively, which indicate that the Ada-RF integrated model outperforms the single prediction model, and can be used for the early prevention and early treatment of athletes’ injuries and illnesses. It shows that the Ada-RF integrated model outperforms the single prediction model and can provide scientific and accurate auxiliary information for the early prevention and treatment of injuries and diseases in athletes.