Retrospective registration of a completed systematic review and bivariate meta-analysis of the diagnostic accuracy of AI for fracture detection on plain radiographs. PubMed, CNKI and Wanfang Data were searched on 24 October 2026 for studies published from 2021 to 2025. Outcomes: stand-alone AI sensitivity and specificity, AI versus clinicians, and the effect of AI assistance on clinicians. Methods: QUADAS-2, GRADE, bivariate (Reitsma)/HSROC model, meta-regression and the Deeks test; reported per PRISMA 2020 and PRISMA-DTA.
No takes yet. Share an insight, caveat, or question.
humera rana (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: