AI Matches Orthopedic Surgeon for Clavicle Fracture Detection on Plain Films

An AI system detected clavicle fractures on AP radiographs with 95.8% sensitivity, 98.9% specificity, and AUC 0.95—performance comparable to an experienced orthopedic surgeon in a single-center retrospective study of 367 exams. Second-plane view results were similarly high.

• Retrospective diagnostic-accuracy study (n=367 radiographs, mean age 44.6 yr, 59.4 % male); reference standard was a senior radiologist's confirmed finding.
• On AP views, AI achieved accuracy 97.3 %, kappa 0.95, F1 0.97; second-plane performance matched AP and the surgeon's reads.
• Key limitation: single-center, retrospective design; no external or prospective validation was performed.

RadPigeon summaries are original and for information only. They are not clinical advice.