First things first: risk model performance metrics should reflect the clinical application

DOI10.1002/SIM.7341MaRDI QIDQ6996042zbMATH OpenFDO

Authors Holly Janes

Publication date 16 April 2025

Published in Statistics in Medicine (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1002/SIM.7341

zbMATH Keywords

biomarkersincremental valuenet benefitrelative utilityrisk prediction

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10)

Cites work

• A note on the evaluation of novel biomarkers: do not rely on integrated discrimination improvement and net reclassification index
• Discrimination slope and integrated discrimination improvement -- properties, relationships and impact of calibration
• Net reclassification index at event rate: properties and relationships
• Simpson's paradox in the integrated discrimination improvement
• Testing for improvement in prediction model performance
• When does combining markers improve classification performance and what are implications for practice?

Cited in

(1)

• Authors' response to comments

This page was built for publication: First things first: risk model performance metrics should reflect the clinical application

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6996042)