What type of study is this?

This is a Systematic Review study (also classified as: Meta-Analysis).

September 10, 2025Cancer ImagingOpen Access

Machine Learning–Driven radiomics on 18 F-FDG PET for glioma diagnosis: a systematic review and meta-analysis

View Full Paper

Ask AI

Bookmark

Authors

ASAli ShahriariZabol University SASasan Ghazanfar AhariTabriz University of Medical Sciences AMAli MousaviTabriz University of Medical Sciences

Discussion

Member takes

Implication

Systematic review and meta-analysis demonstrate robust diagnostic accuracy of ML models for glioma, suggesting methodological improvements are essential.

Key Points

ML models based on 18F-FDG PET radiomics achieve a pooled accuracy of 92.6%, showcasing their diagnostic potential for glioma classification.
The meta-analysis included data from 12 studies with 2,321 patients, revealing significant heterogeneity and the influence of ML model type on results.
Random-effects models analyzed diagnostic metrics, including AUC of 0.95 and sensitivity of 85.4%, indicating strong performance across various ML approaches.
High methodological heterogeneity calls for standardized reporting and validation methods before clinical application of these models.

Cite This Study

Shahriari et al. (2025) studied this question.

synapsesocial.com/papers/68c1d24654b1d3bfb60f8607 https://doi.org/10.1186/s40644-025-00915-8

View Full Paper

Ask AI

Bookmark

September 10, 2025Cancer ImagingOpen Access

Machine Learning–Driven radiomics on 18 F-FDG PET for glioma diagnosis: a systematic review and meta-analysis

View Full Paper

Ask AI

Bookmark

Authors

ASAli ShahriariZabol University SASasan Ghazanfar AhariTabriz University of Medical Sciences AMAli MousaviTabriz University of Medical Sciences

Discussion

Member takes

Implication

Systematic review and meta-analysis demonstrate robust diagnostic accuracy of ML models for glioma, suggesting methodological improvements are essential.

Key Points

ML models based on 18F-FDG PET radiomics achieve a pooled accuracy of 92.6%, showcasing their diagnostic potential for glioma classification.
The meta-analysis included data from 12 studies with 2,321 patients, revealing significant heterogeneity and the influence of ML model type on results.
Random-effects models analyzed diagnostic metrics, including AUC of 0.95 and sensitivity of 85.4%, indicating strong performance across various ML approaches.
High methodological heterogeneity calls for standardized reporting and validation methods before clinical application of these models.

Cite This Study

Shahriari et al. (2025) studied this question.

synapsesocial.com/papers/68c1d24654b1d3bfb60f8607 https://doi.org/10.1186/s40644-025-00915-8

Also Consider

Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark