AUTHOR=Liu Hao TITLE=Value evaluation of knee joint sports injury detection model-aided diagnosis based on machine learning JOURNAL=Frontiers in Physics VOLUME=Volume 11 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2023.1166275 DOI=10.3389/fphy.2023.1166275 ISSN=2296-424X ABSTRACT=The knee joint plays an essential role in people's daily life. The knee joint is relatively fragile and easy to be injured or causes arthritis. The structural relationship of the knee joint is very complex. Due to its weight bearing and a large amount of exercise, it is easy to be injured. This paper aimed to analyze and discuss the auxiliary diagnosis of knee joint sports injury detection models based on machine learning. In this paper, the treatment methods for knee joint injuries were described and a machine learning algorithm was proposed. Based on this research, the auxiliary diagnosis experiment of the knee joint sports injury detection model was analyzed. The experimental results in this paper showed that after 3 months of rehabilitation training based on machine learning, table tennis players have significant differences in the length of the balance pad before and after practice. The duration of athletes on the balance pad increased, and the increase was relatively large. The average duration of female athletes' balance pads increased from 75.5 seconds before training to 141.9 seconds after training, while the average duration of male athletes' balance pads increased from 66.7 seconds before training to 136.8 seconds after training. The results showed that the rehabilitation physical training based on machine learning could significantly improve the endurance of athletes on balance pads. The rehabilitation physical training based on machine learning could improve the knee joint function score. To sum up, rehabilitation physical training based on machine learning could effectively improve knee joint injuries.