Clinical implementation of AI for vertebral fracture detection in CT aligned with fracture liaison services: high prevalence of undiagnosed vertebral fractures
Authors' conclusion
AI-based opportunistic screening for VF is feasible and effective in routine clinical practice.
Study context
- Population
- Patients aged ≥ 50 years with non-skeletal CT scans covering thorax and/or abdomen over a four-month period at one hospital (catchment area ≈250,000)
- Participants
- 3,971 patients5,147 CT scans
- Outcome
- Feasibility and efficacy of AI-based opportunistic VF screening in CT aligned to a local FLS
Methodological detailssingle-centre, opportunistic screening, integrated with fracture liaison service (FLS)
- Single-centre
- Opportunistic screening
- Integrated with FLS
Main finding
As reported in the abstract
VFs identified by AI
All patients
14%
566 events
Observational data: associations, not effects.
Further findings
In need of further osteoporosis evaluation/treatment after clinical triage, among patients with AI-identified vertebral fracture (VFs)
- Considered in need of further osteoporosis evaluation/treatment after clinical triage
- 49%
- Remainder either terminally ill/died shortly after CT or considered correctly handled before
Original publication
Clinical implementation of AI for vertebral fracture detection in CT aligned with fracture liaison services: high prevalence of undiagnosed vertebral fractures. Osteoporos Int. Published 10 March 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →