作者: Constantine Gatsonis , Prashni Paliwal
DOI: 10.2214/AJR.06.0226
关键词:
摘要: OBJECTIVE. Interest in evidence-based diagnosis is growing rapidly as diagnostic and screening techniques proliferate. In this article we provide an overview of systematic reviews performance discuss detail statistical methods for the most common variant problem: meta-analysis studies which a pair estimates sensitivity specificity reported. The need to account possible variations threshold test positivity across led formulation Summary ROC (SROC) curve method. We graphical model-based ways estimate, summarize, compare SROC curves, present example from data on staging cervical cancer. also brief survey methodologic literature addressing heterogeneity, correlated data, multiple thresholds per study, studies. conclude with discussion significant challenges that continue face investigator...