Abstract
Tests for disease often produce a continuous measure, such as the concentration of some biomarker in a blood sample. In clinical practice, a threshold C is selected such that results, say, greater than C are declared positive and those less than C negative. Measures of test accuracy such as sensitivity and specificity depend crucially on C, and the optimal value of this threshold is usually a key question for clinical practice. Standard methods for metaanalysis of test accuracy (i) do not provide summary estimates of accuracy at each threshold, precluding selection of the optimal threshold, and furthermore, (ii) do not make use of all available data. We describe a multinomial metaanalysis model that can take any number of pairs of sensitivity and specificity from each study and explicitly quantifies how accuracy depends on C. Our model assumes that some prespecified or BoxCox transformation of test results in the diseased and diseasefree populations has a logistic distribution. The BoxCox transformation parameter can be estimated from the data, allowing for a flexible range of underlying distributions. We parameterise in terms of the means and scale parameters of the two logistic distributions. In addition to credible intervals for the pooled sensitivity and specificity across all thresholds, we produce prediction intervals, allowing for betweenstudy heterogeneity in all parameters. We demonstrate the model using two case study metaanalyses, examining the accuracy of tests for acute heart failure and preeclampsia. We show how the model can be extended to explore reasons for heterogeneity using studylevel covariates.
Original language  English 

Pages (fromto)  47894803 
Number of pages  15 
Journal  Statistics in Medicine 
Volume  38 
Issue number  24 
Early online date  30 Sept 2019 
DOIs  
Publication status  Published  30 Oct 2019 
Keywords
 BoxCox transformation
 evidence synthesis
 ROC curve
 sensitivity
 specificity
 test cutoff
Fingerprint
Dive into the research topics of 'Quantifying how diagnostic test accuracy depends on threshold in a metaanalysis'. Together they form a unique fingerprint.Profiles

Professor Nicky J Welton
 Bristol Medical School (PHS)  Professor in Statistical and Health Economic Modelling
 Bristol Population Health Science Institute
 Health Protection Research Unit (HPRU)
 Centre for Academic Primary Care
Person: Academic , Member