Application of artificial intelligence in the development of personalized sports injury rehabilitation plan

Sports injury rehabilitation is a kind of physical treatment used to address musculoskeletal system disorders, injuries, and discomfort in patients of all ages. Sports rehabilitation promotes health and fitness, aids in injury recovery, and lessens pain through movement, exercise, and physical therapy. During a sports injury, rehabilitation has developed into a specialized profession that has gradually brought together sports physicians, sports physiotherapists, and orthopedic surgeons. Finding the best ways to minimize recovery time, avoid injuries, and enhance performance is crucial for sports athletes. The aim of this research is to establish a personalized sports injury rehabilitation evaluation system enabled by artificial intelligence (AI). In this study, a novel advanced penguin search optimized efficient random forest (APSO-ERF) has been proposed for sports injury athletics exercise rehabilitation. This study used exercise movement image data to develop personalized sports injury rehabilitation. The data was preprocessed using a Wiener filter for noise reduction and image restoration. Convolutional neural networks (CNN) are used to extrapolate top-level characteristics from images. The proposed method is used to evaluate physical rehabilitation by assessing patient performance during the completion of prescribed sports injury rehabilitation exercises. The proposed method is compared to other traditional algorithms. With 97.80% accuracy, 96.01% sensitivity, 97.90% specificity, 98.88% precision, 96.11% recall, and 97.50% F1-score, the APSO-ERF approach beats conventional algorithms in tailored sports injury rehabilitation. The result illustrated that the proposed method achieved high performance in the accuracy of sports injury athletics exercise rehabilitation.