A composite likelihood method for bivariate meta-analysis in diagnostic systematic reviews.

TitleA composite likelihood method for bivariate meta-analysis in diagnostic systematic reviews.
Publication TypeJournal Article
Year of Publication2017
AuthorsChen, Yong, Yulun Liu, Jing Ning, Lei Nie, Hongjian Zhu, and Haitao Chu
JournalStat Methods Med Res
Volume26
Issue2
Pagination914-930
Date Published2017 04
ISSN1477-0334
KeywordsAnalysis of Variance, Biostatistics, Computer Simulation, Diagnostic Tests, Routine, Humans, Likelihood Functions, Linear Models, Melanoma, Meta-Analysis as Topic, Odds Ratio, Sensitivity and Specificity, Skin Neoplasms
Abstract

Diagnostic systematic review is a vital step in the evaluation of diagnostic technologies. In many applications, it involves pooling pairs of sensitivity and specificity of a dichotomized diagnostic test from multiple studies. We propose a composite likelihood (CL) method for bivariate meta-analysis in diagnostic systematic reviews. This method provides an alternative way to make inference on diagnostic measures such as sensitivity, specificity, likelihood ratios, and diagnostic odds ratio. Its main advantages over the standard likelihood method are the avoidance of the nonconvergence problem, which is nontrivial when the number of studies is relatively small, the computational simplicity, and some robustness to model misspecifications. Simulation studies show that the CL method maintains high relative efficiency compared to that of the standard likelihood method. We illustrate our method in a diagnostic review of the performance of contemporary diagnostic imaging technologies for detecting metastases in patients with melanoma.

DOI10.1177/0962280214562146
Alternate JournalStat Methods Med Res
Original PublicationA composite likelihood method for bivariate meta-analysis in diagnostic systematic reviews.
PubMed ID25512146
PubMed Central IDPMC4466215
Grant ListP30 CA016672 / CA / NCI NIH HHS / United States
P30 CA077598 / CA / NCI NIH HHS / United States
U54 MD008620 / MD / NIMHD NIH HHS / United States
R21 AI103012 / AI / NIAID NIH HHS / United States
R03 HS022900 / HS / AHRQ HHS / United States
P01 CA142538 / CA / NCI NIH HHS / United States
R01 AI130460 / AI / NIAID NIH HHS / United States
Project: