Zhang SC, Sun J, Liu CB, et al. - This study was intended to construct an anteroposterior pelvic radiograph deep learning system for diagnosing developmental dysplasia of the hip (DDH) in children and analyze the feasibility of its application. Researchers retrospectively collected a total, 10,219 anteroposterior pelvic radiographs from April 2014 to December 2018. A receiver operating characteristic curve was applied to ascertain the accuracy of the deep learning system, and the consistency of acetabular index measurements was assessed applying Bland-Altman plots. In comparison with clinician-led diagnoses, the deep learning system was highly consistent, more convenient, and more effective for diagnosing DDH. The data demonstrate that when diagnosing DDH, deep learning systems should be considered for the analysis of anteroposterior pelvic radiographs. The findings recognize that the deep learning system will improve the current artificially complicated screening referral process.