meta4diag: Bayesian Bivariate Meta-analysis of Diagnostic Test Studies for Routine Practice

TL;DR

meta4diag is an R package that facilitates Bayesian bivariate meta-analysis of diagnostic test studies, providing accurate inference, flexible priors, and an interactive GUI for routine practice.

Contribution

It introduces a user-friendly R package that leverages INLA for Bayesian bivariate meta-analysis, including novel penalised complexity priors and an interactive interface.

Findings

Accurate posterior distributions for sensitivity and specificity obtained without MCMC.

Supports flexible prior choices, including penalised complexity priors.

Provides comprehensive graphical outputs like SROC curves for interpretation.

Abstract

This paper introduces the \proglang{R} package \pkg{meta4diag} for implementing Bayesian bivariate meta-analyses of diagnostic test studies. Our package \pkg{meta4diag} is a purpose-built front end of the \proglang{R} package \pkg{INLA}. While \pkg{INLA} offers full Bayesian inference for the large set of latent Gaussian models using integrated nested Laplace approximations, \pkg{meta4diag} extracts the features needed for bivariate meta-analysis and presents them in an intuitive way. It allows the user a straightforward model-specification and offers user-specific prior distributions. Further, the newly proposed penalised complexity prior framework is supported, which builds on prior intuitions about the behaviours of the variance and correlation parameters. Accurate posterior marginal distributions for sensitivity and specificity as well as all hyperparameters, and covariates are directly obtained without Markov chain Monte Carlo sampling. Further, univariate estimates of interest, such as odds ratios, as well as the SROC curve and other common graphics are directly available for interpretation. An interactive graphical user interface provides the user with the full functionality of the package without requiring any \proglang{R} programming. The package is available through CRAN \url{https://cran.r-project.org/web/packages/meta4diag/} and its usage will be illustrated using three real data examples.