Opportunistic assessment of osteoporosis using hip and pelvic X-rays with OsteoSight™: validation of an AI-based tool in a US population
Authors' conclusion
The results demonstrate that OsteoSight is accurate in identifying patients with low BMD.
Study context
- Population
- US population with routine hip and pelvic X-rays
- Comparison
- OsteoSight™ AI analysis of hip and pelvic X-rays vs DXA
- Outcome
- Diagnostic accuracy in identifying low BMD vs DXA
Methodological detailsvalidation study, pre-specified acceptance criteria
- Validation study
- Pre-specified acceptance criteria
Performance
As reported in the abstract
Identification of patients at risk of low BMD
| Test or model | AUC | Specificity | Sensitivity |
|---|---|---|---|
| OsteoSight | 0.834 [0.789-0.880] | 0.852 [0.783-0.930] | 0.628 [0.538-0.743] |
OsteoSight
AUC0.834 [0.789-0.880]
Specificity0.852 [0.783-0.930]
Sensitivity0.628 [0.538-0.743]
Further findings
Pre-processing pipeline
- Successfully excluded unsuitable cases including incorrect body parts, metalwork, and unacceptable femur positioning
Original publication
Opportunistic assessment of osteoporosis using hip and pelvic X-rays with OsteoSight™: validation of an AI-based tool in a US population. Osteoporos Int. Published 22 April 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →