A Computed Tomography-based Radiomics Nomogram for Predicting Osteoporotic Vertebral Fractures: A Longitudinal Study
Authors' conclusion
Bone radiomics is associated with OVF, and the nomogram based on radiomics signature and muscle provides a tool for the prediction of OVF.
Study context
- Population
- Individuals >50 years without OVF who underwent computed tomography (CT) scans 2016–2019, followed until 2021enrolled cohort
- Participants
- 7,906 individuals
- Comparison
- New OVF cases vs controls without OVF
- OVFn = 72
- Controlsn = 144reference
- Outcome
- Predictive performance of CT radiomics-based nomogram for OVF
Main finding
As reported in the abstract
CT value of vertebra, aHR
2.04 (1.07-3.89) (95% CI)
Radiomics score, aHR
6.56 (3.47-12.38) (95% CI)
Area of erector spinae, aHR
1.68 (1.02-2.78) (95% CI)
Nomogram C-index
0.82 (0.77-0.87) (95% CI)
Observational data: associations, not effects.
Further findings
Severe OVF
- Radscore, aHR
- 6.00 (2.78-12.93) (95% CI)
AUC for 3-year and 4-year fracture risk
- AUC of nomogram and radscore both higher than osteoporosis + muscle area
- P < 0.05
Decision curve
- Radiomics nomogram was useful
Original publication
A Computed Tomography-based Radiomics Nomogram for Predicting Osteoporotic Vertebral Fractures: A Longitudinal Study. J Clin Endocrinol Metab. Published 10 December 2022. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →