Online Program

EMBRACE: an EM-based Bias Reduction Approach through Copas-Model Estimation for Quantifying the Evidence of Selective Publishing in Network Meta-analysis (307897)

Yong Chen, University of Pennsylvania 
Ruan Duan, University of Pennsylvania 
Mary Gibbons, University of Pennsylvania 
Chongliang Luo, University of Pennsylvania 
*Arielle Kimberly Marks-Anglin, University of Pennsylvania 
Jing Ning, The University of Texas MD Anderson Cancer Center  
Jin Piao, The University of Texas School of Public Health  
Christopher Henry Schmid, Brown University 

Keywords: network meta analysis, evidence synthesis, evidence-based medicine, EM algorithm, publication bias

Systematic reviews and meta-analyses synthesize results from well-conducted studies to optimize healthcare decision-making. Network meta-analysis (NMA) is particularly useful for improving precision, drawing new comparisons and ranking multiple interventions. However, recommendations can be misled if published results are a selective sample of what has been collected by trialists, particularly when publication status is related to the significance of the findings. Unfortunately, the missing-not-at-random nature of this problem and the numerous parameters involved in modeling NMAs pose unique computational challenges to quantifying and correcting for publication bias, such that sensitivity analysis is used in practice. Motivated by this important methodological gap, we developed a novel and stable EM algorithm to correct for publication bias in the network setting. We validate the method through simulation studies and show that it achieves bias reduction in small to moderately sized NMAs. We also calibrate the method against a `gold standard' analysis of published and unpublished trials from a recent NMA comparing antidepressants for major depressive disorder in adults.