Objective:To evaluate the accuracy of an artificial intelligence (AI) model in measuring key angles on pelvic radiographs of the hip and assess its effectiveness in diagnosing developmental dysplasia of the hip (DDH) and borderline developmental dysplasia of the hip (BDDH).Methods:A retrospective analysis was conducted using anteroposterior pelvic X-ray films from 1,029 patients with suspected DDH. The data were collected from the Department of Radiology, Fourth Medical Center of the Chinese PLA General Hospital. Among the patients, 273 were male, and 756 were female, with an average age of 57.01 ± 18.16 years (range, 12-88 years). The dataset was randomly divided into a training set (720 cases), a test set (206 cases), and a validation set (103 cases). Two radiologists identified and marked key anatomical points of the hip joint to establish the training dataset, which was then used to develop a deep learning-based AI model capable of locating these key anatomical positions. Using the identified anatomical points, the AI model automatically measured and calculated the Sharp angle, center-edge (CE) angle, and T?nnis angle in the test dataset. The measurement results from the AI model were compared with those of the radiologists to evaluate the model's accuracy. The validation set was used to optimize model parameters, and the test dataset was used to evaluate the diagnostic performance of DDH. Receiver operating characteristic (ROC) curves were employed to assess the diagnostic efficacy of the AI model for DDH and BDDH.Results:The accuracy rates of the AI model in measuring the left Sharp angle, CE angle, and T?nnis angle for diagnosing DDH were 89.8%, 90.1%, and 86.8%, respectively. For the right side, the accuracy rates were 93.7%, 92.2%, and 80.5%, respectively. There were no statistically significant differences in the mean values of the Sharp, T?nnis, and CE angles between manual and AI measurements ( P>0.05). Pearson correlation tests and intraclass correlation coefficient (ICC) analyses revealed high consistency between AI and manual measurements of the Sharp angle, T?nnis angle, and CE angle, with r-values and ICC values exceeding 0.75. Additionally, the AI model performed measurements significantly faster (1.7±0.1 s) than radiologists (88.1±8.4 s and 90.3±7.4 s, P<0.001). The areas under the ROC curves (AUCs) for diagnosing DDH using the Sharp angle, CE angle, and T?nnis angle measured by the AI model were 0.883, 0.922, and 0.908 (left side) and 0.924, 0.871, and 0.922 (right side), respectively. For diagnosing BDDH, the AUCs of the left and right CE angles measured by the AI model were 0.787 and 0.676, respectively. Kappa test results indicated good agreement between the AI model and manual measurements as well as final clinical diagnoses. For the CE angle, the κ value of the AI model was 0.663, while κ values for the Sharp and T?nnis angles were all greater than 0.800. Conclusion:The convolutional neural network-based AI model effectively and automatically measures the Sharp, CE, and T?nnis angles and demonstrates high diagnostic efficacy for DDH and BDDH.