Abstract

Hierarchical models such as the bivariate and hierarchical summary receiver operating characteristic (HSROC) models are recommended for meta-analysis of test accuracy studies. These models are challenging to fit when there are few studies and/or sparse data (for example zero cells in contingency tables due to studies reporting 100% sensitivity or specificity); the models may not converge, or give unreliable parameter estimates. Using simulation, we investigated the performance of seven hierarchical models incorporating increasing simplifications in scenarios designed to replicate realistic situations for meta-analysis of test accuracy studies. Performance of the models was assessed in terms of estimability (percentage of meta-analyses that successfully converged and percentage where the between study correlation was estimable), bias, mean square error and coverage of the 95% confidence intervals. Our results indicate that simpler hierarchical models are valid in situations with few studies or sparse data. For synthesis of sensitivity and specificity, univariate random effects logistic regression models are appropriate when a bivariate model cannot be fitted. Alternatively, an HSROC model that assumes a symmetric SROC curve (by excluding the shape parameter) can be used if the HSROC model is the chosen meta-analytic approach. In the absence of heterogeneity, fixed effect equivalent of the models can be applied.

Highlights

  • Meta-analysis of test accuracy studies aims to produce reliable evidence about the diagnostic accuracy of a medical test from multiple studies addressing the same question

  • The bivariate model1 and the hierarchical summary receiver operating characteristic (HSROC) model2 are the two approaches recommended for meta-analysis when a sensitivity and specificity pair is available for each study

  • The summary receiver operating characteristic (SROC) curve approach developed by Moses et al.18 accounts for possible heterogeneity in threshold

Read more

Summary

Introduction

Meta-analysis of test accuracy studies aims to produce reliable evidence about the diagnostic accuracy of a medical test from multiple studies addressing the same question. The bivariate model and the hierarchical summary receiver operating characteristic (HSROC) model are the two approaches recommended for meta-analysis when a sensitivity and specificity pair is available for each study.3–5 These hierarchical models possess theoretical advantages over simpler methods for meta-analysis of test accuracy studies but fitting them is not trivial. Solving the likelihood equations requires an iterative process and in certain circumstances, for instance when there are few studies and/or sparse data (e.g. zero cells due to perfect sensitivity and/or specificity) in a meta-analysis, the models fail to converge or they converge but give unreliable parameter estimates with one or more missing standard errors These issues are often encountered by meta-analysts and there is uncertainty about how to proceed with meta-analysis in such situations

Methods
Findings
Discussion
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.