Body / AbdominalMusculoskeletal (MSK)AI / InformaticsResearch

Meta-analysis: AI screening for osteoporosis on abdominal CT achieves pooled AUC of 0.931

Radiology AI literature (PubMed)Jun 29

AI algorithms applied to abdomen/lumbar-spine CT scans show excellent performance for opportunistic osteoporosis screening, with a pooled AUC of 0.931 (95% CI 0.926-0.936). Screening for spine fractures was also strong at AUC 0.863 (0.73-0.936). DXA served as the reference. Most…

  • Systematic review and meta-analysis of 31 studies (26 for osteoporosis, 5 for fracture) using CT with DXA as reference.
  • For abdomen/L-spine osteoporosis/non-osteoporosis screening, pooled sensitivity and specificity were not reported; heterogeneity was moderate (I²=47.24%).
  • Majority of studies were retrospective and not externally validated; fracture screening analysis showed high heterogeneity (I²=64.8%).

Automated summary

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