Saturday, June 22, 2024

Radiomics Shows Promise in Osteoporosis Diagnosis: A Systematic Review and Meta-Analysis

Similar articles

In a groundbreaking meta-analysis, researchers have evaluated the effectiveness of radiomic techniques in diagnosing osteoporosis and abnormal bone mass. This comprehensive review, which analyzed data from ten retrospective studies, provides compelling evidence supporting the accuracy of radiomics in this medical application. The study also highlights the necessity for future research to validate these findings through more rigorous, multicenter prospective studies.

Study Methodology and Inclusion Criteria

The research team conducted an extensive search of PubMed, EMBASE, Web of Science, and Cochrane Library databases up until June 1, 2023. The inclusion criteria focused on studies that applied radiomic techniques for diagnosing osteoporosis or abnormal bone mass. The quality and risk of bias for the included studies were appraised using multiple tools: the Radiomics Quality Score (RQS), METhodological RadiomICs Score (METRICS), and the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2).

Ten retrospective studies, encompassing a total of 5926 participants, were selected for the systematic review and meta-analysis. The overall risk of bias and applicability concerns were generally low, although one study exhibited a high risk of flow and time bias. The mean METRICS score across these studies was 70.1%, ranging from 49.6% to 83.2%.

Diagnostic Accuracy and Sources of Heterogeneity

The meta-analysis revealed moderate heterogeneity across the included studies. Meta-regression identified several sources of this heterogeneity, including differences in imaging modality, feature selection methods, and classifiers used in the studies. Despite these variations, the pooled diagnostic odds ratio (DOR) under the bivariate random effects model was 57.22, with a 95% confidence interval ranging from 27.62 to 118.52.

The pooled sensitivity and specificity of the radiomic models were both 87%, while the area under the summary receiver operating characteristic curve (AUC) was an impressive 0.94, ranging from 0.8 to 0.98. These results indicate that radiomics techniques are highly accurate in diagnosing osteoporosis and abnormal bone mass.

Key Insights for Clinical Practice

– Radiomics techniques show high diagnostic accuracy for osteoporosis, with both sensitivity and specificity at 87%.
– Moderate heterogeneity exists across studies, influenced by imaging modalities, feature selection, and classifiers.
– The area under the ROC curve (AUC) for radiomic models is 0.94, indicating strong diagnostic performance.
– Future research should focus on prospective, multicenter studies to validate these findings and adhere to rigorous guidelines.

The study concludes that radiomic techniques hold promise for the accurate diagnosis of osteoporosis and abnormal bone mass. However, it underscores the need for further prospective studies that rigorously adhere to existing guidelines and include multicenter validation to confirm these initial findings.

Original Article: Osteoporos Int. 2024 May 27. doi: 10.1007/s00198-024-07136-y. Online ahead of print.

You can follow our news on our Telegram and LinkedIn accounts.

Subscribe to our newsletter

To be updated with all the latest news, offers and special announcements.

Latest article