Diagnostic performance of radiomics for predicting osteoporosis in adults: a systematic review and meta-analysis
Authors' conclusion
The results supported that the radiomic techniques had good accuracy in diagnosing osteoporosis or abnormal bone mass.
Study context
- Population
- Adults; studies applying radiomics to diagnosing osteoporosis or abnormal bone mass (PubMed, EMBASE, Web of Science, Cochrane Library, inception to June 1, 2023)
- Participants
- 5,926 adults10 retrospective studies
- Outcome
- Diagnostic accuracy of radiomics for predicting osteoporosis
Methodological detailsbivariate random effects model, meta-regression, radiomics quality score (RQS), METhodological RadiomICs Score (METRICS) and QUADAS-2 quality assessment
- Bivariate random effects model
- Meta-regression
- RQS, METRICS and QUADAS-2 quality assessment
Pooled result
As reported in the abstract
Pooled diagnostic accuracy of radiomics for osteoporosis or abnormal bone mass
Pooled diagnostic OR (bivariate random effects model)
57.22
95% CI 27.62–118.52
Pooled sensitivity
87%
95% CI 81–92%
Pooled specificity
87%
95% CI 77–93%
Summary ROC AUC of radiomic models
0.94
range 0.8 to 0.98
Further pooled results
Study quality: METRICS score
- Mean METRICS score
- 70.1% (range 49.6-83.2%)
Original publication
Diagnostic performance of radiomics for predicting osteoporosis in adults: a systematic review and meta-analysis. Osteoporos Int. Published 27 May 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →