Objective: To investigate the musculoskeletal ultrasonographic features of patients with rotator cuff injury, analyze the prognostic factors of rotator cuff injury and construct a prediction model for the prognosis. Methods: A retrospective analysis was conducted on the clinical data of 82 patients who were suspected of rotator cuff injury and admitted to the hospital from February 2021 to June 2023. The musculoskeletal ultrasonographic features and the consistency between musculoskeletal ultrasonography and arthroscopy were analyzed. Univariate analysis and multivariate logistic regression analysis were conducted to screen the prognostic factors of rotator cuff injury and a prediction model was constructed. Results: Arthroscopy diagnosed 73 cases of rotator cuff injury. Musculoskeletal ultrasonography showed continuous interruption of rotator cuff tendon, with broken end retracting and discontinuous rotator cuff fibers. Ultrasound showed no echo or hypoecho. The sensitivity, specificity and accuracy of musculoskeletal ultrasonography for diagnosing rotator cuff injury were 90.41%, 88.89% and 90.24%. The consistency between musculoskeletal ultrasonography and arthroscopy was at a middle level (kappa=0.614). Among 73 patients with rotator cuff injury, 59 patients had good prognosis and 14 patients had poor prognosis. Age ≥ 60 years (OR=1.634), degree of rotator cuff tear (OR=2.869) and degree of rotator cuff muscle atrophy (OR=2.389) were risk factors for poor prognosis in patients with rotator cuff injury (P<0.05). The prediction model for the prognosis of patients with rotator cuff injury was P=ex/(1+ex), X=-4.337+0.491×age+1.054×degree of rotator cuff tear+0.871×degree of rotator cuff muscle atrophy. The area under the ROC curve of the prediction model was 0.805 (95% CI=0.691-0.919, P<0.001). Its sensitivity and specificity were 71.43% and 77.97%. Conclusion: Musculoskeletal ultrasonography has relatively high diagnostic value for rotator cuff injury and can provide reference for preoperative diagnosis. Age, degree of rotator cuff tear and degree of rotator cuff muscle atrophy are influencing factors of poor prognosis in patients with rotator cuff injury. The prediction model constructed in this study has high accuracy and has certain significance for predicting the prognosis of rotator cuff injury.