Premium
A comparison of bivariate, multivariate random‐effects, and Poisson correlated gamma‐frailty models to meta‐analyze individual patient data of ordinal scale diagnostic tests
Author(s) -
Simoneau Gabrielle,
Levis Brooke,
Cuijpers Pim,
Ioannidis John P. A.,
Patten Scott B.,
Shrier Ian,
Bombardier Charles H.,
de Lima Osório Flavia,
Fann Jesse R.,
Gjerdingen Dwenda,
Lamers Femke,
Lotrakul Manote,
Löwe Bernd,
Shaaban Juwita,
Stafford Lesley,
Weert Henk C. P. M.,
Whooley Mary A.,
Wittkampf Karin A.,
Yeung Albert S.,
Thombs Brett D.,
Benedetti Andrea
Publication year - 2017
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.201600184
Subject(s) - bivariate analysis , multivariate statistics , ordinal data , ordinal scale , statistics , context (archaeology) , bivariate data , poisson distribution , ordinal regression , correlation , multivariate analysis , random effects model , mathematics , univariate , generalization , sensitivity (control systems) , scale (ratio) , econometrics , computer science , meta analysis , medicine , paleontology , mathematical analysis , geometry , physics , quantum mechanics , electronic engineering , engineering , biology
Individual patient data (IPD) meta‐analyses are increasingly common in the literature. In the context of estimating the diagnostic accuracy of ordinal or semi‐continuous scale tests, sensitivity and specificity are often reported for a given threshold or a small set of thresholds, and a meta‐analysis is conducted via a bivariate approach to account for their correlation. When IPD are available, sensitivity and specificity can be pooled for every possible threshold. Our objective was to compare the bivariate approach, which can be applied separately at every threshold, to two multivariate methods: the ordinal multivariate random‐effects model and the Poisson correlated gamma‐frailty model. Our comparison was empirical, using IPD from 13 studies that evaluated the diagnostic accuracy of the 9‐item Patient Health Questionnaire depression screening tool, and included simulations. The empirical comparison showed that the implementation of the two multivariate methods is more laborious in terms of computational time and sensitivity to user‐supplied values compared to the bivariate approach. Simulations showed that ignoring the within‐study correlation of sensitivity and specificity across thresholds did not worsen inferences with the bivariate approach compared to the Poisson model. The ordinal approach was not suitable for simulations because the model was highly sensitive to user‐supplied starting values. We tentatively recommend the bivariate approach rather than more complex multivariate methods for IPD diagnostic accuracy meta‐analyses of ordinal scale tests, although the limited type of diagnostic data considered in the simulation study restricts the generalization of our findings.