Multivariate mixed models for metanalysis of paired-comparison studies of two medical diagnostic tests

We have previously demonstrated Stata implementation of bivariate ramdom effects meta-analysis of the sensitivity and specificity of a single binary diagnostic test by means of the midas module (Dwamena NASUG2007; Dwamena WCSUG 2007). In this presentation we extend our work to paired-comparison studies of two binary diagnostic tests. Using a dataset of studies comparing the accuracy of positron emission tomography(PET) and x-ray computed tomography (CT) for staging lung cancer, we compare the fit(deviance) and complexity (BIC, AIC) and test performance estimates (sensitivity, specificity, dignostic odds ratios nand likelihood ratios) of 4 multivariate models : (1) bivariate binomial mixed model with test type as fixed-effect covariate; (2) bivariate binomial mixed model with test type as random-effect covariate; (3) independent test-specific bivariate binomial mixed models; and (4) correlated test-specific bivariate binomial mixed models. Estimation is performed with the Stata-native procedure xtmelogit using both the default adaptive quadrature method and its laplacian approximation (nip=1). Results are then compared with those from the user-written gllamm command (Rabe-Hesketh et al.)