Empirical comparisons of meta-analysis methods for diagnostic studies: a meta-epidemiological study.
epidemiology
general medicine (see internal medicine)
medical education & training
statistics & research methods
Journal
BMJ open
ISSN: 2044-6055
Titre abrégé: BMJ Open
Pays: England
ID NLM: 101552874
Informations de publication
Date de publication:
09 05 2022
09 05 2022
Historique:
entrez:
9
5
2022
pubmed:
10
5
2022
medline:
12
5
2022
Statut:
epublish
Résumé
Several methods are commonly used for meta-analyses of diagnostic studies, such as the bivariate linear mixed model (LMM). It estimates the overall sensitivity, specificity, their correlation, diagnostic OR (DOR) and the area under the curve (AUC) of the summary receiver operating characteristic (ROC) estimates. Nevertheless, the bivariate LMM makes potentially unrealistic assumptions (ie, normality of within-study estimates), which could be avoided by the bivariate generalised linear mixed model (GLMM). This article aims at investigating the real-world performance of the bivariate LMM and GLMM using meta-analyses of diagnostic studies from the Cochrane Library. We compared the bivariate LMM and GLMM using the relative differences in the overall sensitivity and specificity, their 95% CI widths, between-study variances, and the correlation between the (logit) sensitivity and specificity. We also explored their relationships with the number of studies, number of subjects, overall sensitivity and overall specificity. Among the extracted 1379 meta-analyses, point estimates of overall sensitivities and specificities by the bivariate LMM and GLMM were generally similar, but their CI widths could be noticeably different. The bivariate GLMM generally produced narrower CIs than the bivariate LMM when meta-analyses contained 2-5 studies. For meta-analyses with <100 subjects or the overall sensitivities or specificities close to 0% or 100%, the bivariate LMM could produce substantially different AUCs, DORs and DOR CI widths from the bivariate GLMM. The variation of estimates calls into question the appropriateness of the normality assumption within individual studies required by the bivariate LMM. In cases of notable differences presented in these methods' results, the bivariate GLMM may be preferred.
Identifiants
pubmed: 35534072
pii: bmjopen-2021-055336
doi: 10.1136/bmjopen-2021-055336
pmc: PMC9086644
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e055336Subventions
Organisme : NLM NIH HHS
ID : R01 LM012982
Pays : United States
Organisme : NIMH NIH HHS
ID : R03 MH128727
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR001427
Pays : United States
Informations de copyright
© Author(s) (or their employer(s)) 2022. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.
Déclaration de conflit d'intérêts
Competing interests: None declared.
Références
Biostatistics. 2007 Apr;8(2):239-51
pubmed: 16698768
J Clin Epidemiol. 2008 Nov;61(11):1095-103
pubmed: 19208372
Stat Med. 1993 Dec 30;12(24):2273-84
pubmed: 7907813
Med Decis Making. 2008 Sep-Oct;28(5):621-38
pubmed: 18591542
Med Decis Making. 1993 Oct-Dec;13(4):313-21
pubmed: 8246704
Cochrane Database Syst Rev. 2019 Oct 3;10:ED000142
pubmed: 31643080
Stat Methods Med Res. 2016 Aug;25(4):1596-619
pubmed: 23804970
Stat Med. 1993 Jul 30;12(14):1293-316
pubmed: 8210827
Stat Med. 2002 May 15;21(9):1237-56
pubmed: 12111876
BMC Med Res Methodol. 2016 Aug 12;16(1):97
pubmed: 27520527
BMJ Evid Based Med. 2020 Feb;25(1):27-32
pubmed: 31273125
Ann Intern Med. 1994 Apr 15;120(8):667-76
pubmed: 8135452
J Clin Epidemiol. 2008 Jan;61(1):41-51
pubmed: 18083461
Stat Med. 2002 Jun 15;21(11):1525-37
pubmed: 12111918
J Clin Epidemiol. 2009 Dec;62(12):1292-300
pubmed: 19447007
BMJ. 2001 Jul 21;323(7305):157-62
pubmed: 11463691
BMC Health Serv Res. 2002;2:4
pubmed: 11884248
Semin Nucl Med. 1978 Oct;8(4):283-98
pubmed: 112681
Biostatistics. 2018 Jan 1;19(1):87-102
pubmed: 28586407
BMC Med Res Methodol. 2002 Jul 03;2:9
pubmed: 12097142
Ann Intern Med. 2003 Jan 7;138(1):40-4
pubmed: 12513043
Biostatistics. 2009 Jan;10(1):201-3
pubmed: 19039031
J Clin Epidemiol. 2005 Oct;58(10):982-90
pubmed: 16168343
Med Decis Making. 2010 Jul-Aug;30(4):499-508
pubmed: 19959794
Med Decis Making. 1993 Jul-Sep;13(3):253-7
pubmed: 8412556
Biostatistics. 2009 Oct;10(4):806-7
pubmed: 19581345
J R Stat Soc Ser A Stat Soc. 2009 Jan;172(1):137-159
pubmed: 19381330
J Clin Epidemiol. 1995 Jan;48(1):119-30; discussion 131-2
pubmed: 7853038
Stat Med. 2015 Dec 20;34(29):3831-41
pubmed: 26174020
Stat Methods Med Res. 2017 Aug;26(4):1896-1911
pubmed: 26116616
Stat Methods Med Res. 2018 May;27(5):1410-1421
pubmed: 27487844
Psychol Bull. 1995 Jan;117(1):167-78
pubmed: 7870860
J Clin Epidemiol. 2003 Nov;56(11):1129-35
pubmed: 14615004
J Clin Epidemiol. 2006 Dec;59(12):1331-2; author reply 1332-3
pubmed: 17098577
BMJ. 2011 Feb 10;342:d549
pubmed: 21310794
BMC Med Res Methodol. 2007 Jan 12;7:3
pubmed: 17222330
Stat Med. 2001 Oct 15;20(19):2865-84
pubmed: 11568945
Stat Med. 2002 Feb 28;21(4):589-624
pubmed: 11836738