AI-enhanced DXA achieves AUC ~0.90 for fracture prediction, outperforming FRAX

AI applied to DXA yields superior fracture prediction (AUC ~0.90) versus standard BMD or FRAX, enabling earlier osteoporosis detection, per a narrative review.

• Narrative review summarizing AI integration into DXA; no original patient sample analyzed.
• AI-driven models, including CNNs, also improve trabecular bone score estimation and reduce operator variability (exact figures not reported in source).
• As a review, evidence synthesis is based on studies with heterogeneous designs; prospective external validation of individual AI models may be limited.

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