The research on sports injury has long relied on traditional statistical methods, which often have obvious limitations when dealing with high-dimensional, nonlinear and multi-modal data. With the development of artificial intelligence technology, machine learning provides a new way to solve these complex problems. This paper systematically reviews the progress and application of machine learning in sports injury research. Firstly, the development of different machine learning methods in sports injury research was summarized. Secondly, we focus on five core applications of machine learning in the field of sports injury: data feature selection and dimensionality reduction, injury risk prediction, injury symptoms and signs classification, risk monitoring based on wearable devices, and imaging data analysis. Research shows that machine learning models show significant advantages in dealing with complex data patterns, improving prediction accuracy and achieving real-time dynamic intervention. However, research in related fields still faces challenges such as insufficient data quality and quantity, poor model interpretability, and barriers to multidisciplinary cooperation. Through the summary, it can be seen that future research in this field should focus on constructing standardized shared datasets, developing more interpretable models, and strengthening the cooperation and communication between multi-disciplines, and finally promoting the application of machine learning in sports injury prevention, diagnosis and rehabilitation.