Author:
López Malo Vázquez de Lara Aurelio,Bhandari Parash Mani,Wu Yin,Levis Brooke,Thombs Brett,Benedetti Andrea,Sun Ying,He Chen,Krishnan Ankur,Neupane Dipika,Negeri Zelalem,Imran Mahrukh,Rice Danielle B.,Riehm Kira E.,Saadat Nazanin,Azar Marleine,Boruff Jill,Cuijpers Pim,Gilbody Simon,Ioannidis John P. A.,Kloda Lorie A.,McMillan Dean,Patten Scott B.,Shrier Ian,Ziegelstein Roy C.,Akena Dickens H.,Arroll Bruce,Ayalon Liat,Baradaran Hamid R.,Beraldi Anna,Bombardier Charles H.,Butterworth Peter,Carter Gregory,Chagas Marcos H.,Chan Juliana C. N.,Cholera Rushina,Chowdhary Neerja,Clover Kerrie,Conwell Yeates,de Man-van Ginkel Janneke M.,Delgadillo Jaime,Fann Jesse R.,Fischer Felix H.,Fung Daniel,Gelaye Bizu,Goodyear-Smith Felicity,Greeno Catherine G.,Hall Brian J.,Härter Martin,Hegerl Ulrich,Hides Leanne,Hobfoll Stevan E.,Hudson Marie,Hyphantis Thomas,Inagaki Masatoshi,Ismail Khalida,Jetté Nathalie,Khamseh Mohammad E.,Kiely Kim M.,Kwan Yunxin,Lamers Femke,Liu Shen-Ing,Lotrakul Manote,Loureiro Sonia R.,Löwe Bernd,Marsh Laura,McGuire Anthony,Mohd Sidik Sherina,Munhoz Tiago N.,Muramatsu Kumiko,Osório Flávia L.,Patel Vikram,Pence Brian W.,Persoons Philippe,Picardi Angelo,Reuter Katrin,Rooney Alasdair G.,Santos Iná S.,Shaaban Juwita,Sidebottom Abbey,Simning Adam,Stafford Lesley,Sung Sharon C.,Tan Pei Lin Lynnette,Turner Alyna,van der Feltz-Cornelis Christina M.,van Weert Henk C.,Vöhringer Paul A.,White Jennifer,Whooley Mary A.,Winkley Kirsty,Yamada Mitsuhiko,Zhang Yuying,
Abstract
AbstractThe diagnostic accuracy of a screening tool is often characterized by its sensitivity and specificity. An analysis of these measures must consider their intrinsic correlation. In the context of an individual participant data meta-analysis, heterogeneity is one of the main components of the analysis. When using a random-effects meta-analytic model, prediction regions provide deeper insight into the effect of heterogeneity on the variability of estimated accuracy measures across the entire studied population, not just the average. This study aimed to investigate heterogeneity via prediction regions in an individual participant data meta-analysis of the sensitivity and specificity of the Patient Health Questionnaire-9 for screening to detect major depression. From the total number of studies in the pool, four dates were selected containing roughly 25%, 50%, 75% and 100% of the total number of participants. A bivariate random-effects model was fitted to studies up to and including each of these dates to jointly estimate sensitivity and specificity. Two-dimensional prediction regions were plotted in ROC-space. Subgroup analyses were carried out on sex and age, regardless of the date of the study. The dataset comprised 17,436 participants from 58 primary studies of which 2322 (13.3%) presented cases of major depression. Point estimates of sensitivity and specificity did not differ importantly as more studies were added to the model. However, correlation of the measures increased. As expected, standard errors of the logit pooled TPR and FPR consistently decreased as more studies were used, while standard deviations of the random-effects did not decrease monotonically. Subgroup analysis by sex did not reveal important contributions for observed heterogeneity; however, the shape of the prediction regions differed. Subgroup analysis by age did not reveal meaningful contributions to the heterogeneity and the prediction regions were similar in shape. Prediction intervals and regions reveal previously unseen trends in a dataset. In the context of a meta-analysis of diagnostic test accuracy, prediction regions can display the range of accuracy measures in different populations and settings.
Funder
Mitacs Globalink Research Internship Program
Research Institute of the McGill University Health Centre
Fonds de recherche du Québec - Santé (FRQS) Postdoctoral Training Fellowships
FRQS researcher salary award
Canadian Institutes of Health Research
Publisher
Springer Science and Business Media LLC