AI model improves detection of subtle femoral-neck fractures on radiographs

A multicenter retrospective study developed and externally tested a deep learning model, OccuNet, for detecting femoral-neck fractures on pelvic or hip radiographs, comparing it against 10 readers (musculoskeletal radiologists and emergency medicine physicians). The study reported the model achieved 97.5% sensitivity and 98.8% specificity overall (AUC 0.99), and for radiograph-negative or indeterminate fractures its sensitivity (94.7%) exceeded that of radiologists (86.2%) and emergency medicine physicians (68.8%). With AI assistance, the study reported reader sensitivity increased significantly for both radiologists and emergency medicine physicians, with reading times shortened by 14.9% and 18.9%, respectively.

Most relevant for: Clinicians evaluating adults with suspected hip trauma on pelvic or hip radiographs, particularly cases with radiograph-negative or indeterminate femoral-neck fractures.

Summary written by an AI model from the source text and dated by the source's publication date. Check the original before acting on it. How MedFollow selects and summarizes updates.

Informational only. Not medical advice. Not a substitute for clinical judgment. Always consult current guidelines and your own clinical judgment.