Literature DB >> 30887438

Real-world Performance of Meta-analysis Methods for Double-Zero-Event Studies with Dichotomous Outcomes Using the Cochrane Database of Systematic Reviews.

Yanan Ren1, Lifeng Lin2, Qinshu Lian1, Hui Zou3, Haitao Chu4.   

Abstract

BACKGROUND: Meta-analysis combines multiple independent studies, which can increase power and provide better estimates. However, it is unclear how best to deal with studies with zero events; such studies are also known as double-zero-event studies (DZS). Several statistical methods have been proposed, but the agreement among different approaches has not been systematically assessed using real-world published systematic reviews.
METHODS: The agreement of five commonly used methods (i.e., the inverse-variance, Mantel-Haenszel, Peto, Bayesian, and exact methods) was assessed using the Cohen's κ coefficients using 368 meta-analyses with rare events selected from the Cochrane Database of Systematic Reviews. Three continuity corrections, including the correction of a constant 0.5, the treatment arm continuity correction (TACC), and the empirical (EMP) correction, were used to handle DZS when applying inverse-variance and Mantel-Haenszel methods.
RESULTS: When the proportion of DZS studies was lower than 50% in a meta-analysis, different methods had moderately high agreement. However, when this proportion was increased to be over 50%, the agreement among the methods decreased to different extents. For the Bayesian, exact, and Peto methods and the inverse-variance and Mantel-Haenszel methods using the EMP correction, their agreement coefficients with the inverse-variance and Mantel-Haenszel methods using a constant 0.5 and TACC decreased from larger than 0.70 to smaller than 0.30. In contrast, the agreement coefficients only decreased slightly among the Bayesian, exact, and Peto methods and the inverse-variance and Mantel-Haenszel methods using the EMP correction.
CONCLUSIONS: To utilize all available information and reduce research waste and avoid overestimating the effect, meta-analysts should incorporate DZS, rather than simply removing them. The Peto and other conventional methods with continuity correction should be avoided when the proportion of DZS is extremely high. The exact and Bayesian methods are highly recommended, except when none of the included studies have an event in one or both treatment arms.

Keywords:  Cochrane Database of Systematic Reviews; Cohen’s κ coefficient; double-zero-event studies; meta-analysis; rare event

Year:  2019        PMID: 30887438      PMCID: PMC6544742          DOI: 10.1007/s11606-019-04925-8

Source DB:  PubMed          Journal:  J Gen Intern Med        ISSN: 0884-8734            Impact factor:   5.128


  28 in total

Review 1.  Publication bias in meta-analysis: its causes and consequences.

Authors:  A Thornton; P Lee
Journal:  J Clin Epidemiol       Date:  2000-02       Impact factor: 6.437

2.  Statistical aspects of the analysis of data from retrospective studies of disease.

Authors:  N MANTEL; W HAENSZEL
Journal:  J Natl Cancer Inst       Date:  1959-04       Impact factor: 13.506

3.  What to add to nothing? Use and avoidance of continuity corrections in meta-analysis of sparse data.

Authors:  Michael J Sweeting; Alexander J Sutton; Paul C Lambert
Journal:  Stat Med       Date:  2004-05-15       Impact factor: 2.373

4.  Much ado about nothing: a comparison of the performance of meta-analytical methods with rare events.

Authors:  Michael J Bradburn; Jonathan J Deeks; Jesse A Berlin; A Russell Localio
Journal:  Stat Med       Date:  2007-01-15       Impact factor: 2.373

5.  Making sense of odds and odds ratios.

Authors:  David A Grimes; Kenneth F Schulz
Journal:  Obstet Gynecol       Date:  2008-02       Impact factor: 7.661

6.  Should meta-analyses of interventions include observational studies in addition to randomized controlled trials? A critical examination of underlying principles.

Authors:  Ian Shrier; Jean-François Boivin; Russell J Steele; Robert W Platt; Andrea Furlan; Ritsuko Kakuma; James Brophy; Michel Rossignol
Journal:  Am J Epidemiol       Date:  2007-08-21       Impact factor: 4.897

7.  Haloperidol versus chlorpromazine for treatment of schizophrenia.

Authors:  C Leucht; M Kitzmantel; L Chua; J Kane; S Leucht
Journal:  Schizophr Bull       Date:  2008-07-24       Impact factor: 9.306

8.  Exact and efficient inference procedure for meta-analysis and its application to the analysis of independent 2 x 2 tables with all available data but without artificial continuity correction.

Authors:  Lu Tian; Tianxi Cai; Marc A Pfeffer; Nikita Piankov; Pierre-Yves Cremieux; L J Wei
Journal:  Biostatistics       Date:  2008-10-14       Impact factor: 5.899

9.  Inclusion of zero total event trials in meta-analyses maintains analytic consistency and incorporates all available data.

Authors:  Jan O Friedrich; Neill K J Adhikari; Joseph Beyene
Journal:  BMC Med Res Methodol       Date:  2007-01-23       Impact factor: 4.615

Review 10.  Recent developments in meta-analysis.

Authors:  Alexander J Sutton; Julian P T Higgins
Journal:  Stat Med       Date:  2008-02-28       Impact factor: 2.373

View more
  9 in total

1.  Reply to the Letter to the Editor: "Newer-Generation Antidepressants and Suicide Risk: Thoughts on Hengartner and Plöderl's Re-Analysis".

Authors:  Michael P Hengartner; Martin Plöderl
Journal:  Psychother Psychosom       Date:  2019-09-05       Impact factor: 17.659

Review 2.  Should We Use High-Flow Nasal Cannula in Patients Receiving Gastrointestinal Endoscopies? Critical Appraisals through Updated Meta-Analyses with Multiple Methodologies and Depiction of Certainty of Evidence.

Authors:  Chi Chan Lee; Teressa Reanne Ju; Pei Chun Lai; Hsin-Ti Lin; Yen Ta Huang
Journal:  J Clin Med       Date:  2022-07-03       Impact factor: 4.964

3.  Updating insights into rosiglitazone and cardiovascular risk through shared data: individual patient and summary level meta-analyses.

Authors:  Joshua D Wallach; Kun Wang; Audrey D Zhang; Deanna Cheng; Holly K Grossetta Nardini; Haiqun Lin; Michael B Bracken; Mayur Desai; Harlan M Krumholz; Joseph S Ross
Journal:  BMJ       Date:  2020-02-05

4.  Aristolochic acid-associated urinary tract cancers: an updated meta-analysis of risk and oncologic outcomes after surgery and systematic review of molecular alterations observed in human studies.

Authors:  Yu-Chan Kang; Ming-Hong Chen; Chung-Ying Lin; Chih-Yun Lin; Yen-Ta Chen
Journal:  Ther Adv Drug Saf       Date:  2021-03-21

5.  Effects of perioperative erythropoietin administration on acute kidney injury and red blood cell transfusion in patients undergoing cardiac surgery: A systematic review and meta-analysis.

Authors:  Hyeon Ju Shin; Eunji Ko; Injae Jun; Hyun Jung Kim; Choon Hak Lim
Journal:  Medicine (Baltimore)       Date:  2022-03-04       Impact factor: 1.817

6.  Effects of lithium on suicide and suicidal behaviour: a systematic review and meta-analysis of randomised trials.

Authors:  Zainab Nabi; Jacki Stansfeld; Martin Plöderl; Lisa Wood; Joanna Moncrieff
Journal:  Epidemiol Psychiatr Sci       Date:  2022-09-16       Impact factor: 7.818

7.  Meta-analysis with zero-event studies: a comparative study with application to COVID-19 data.

Authors:  Jia-Jin Wei; En-Xuan Lin; Jian-Dong Shi; Ke Yang; Zong-Liang Hu; Xian-Tao Zeng; Tie-Jun Tong
Journal:  Mil Med Res       Date:  2021-07-03

8.  Laplace approximation, penalized quasi-likelihood, and adaptive Gauss-Hermite quadrature for generalized linear mixed models: towards meta-analysis of binary outcome with sparse data.

Authors:  Ke Ju; Lifeng Lin; Haitao Chu; Liang-Liang Cheng; Chang Xu
Journal:  BMC Med Res Methodol       Date:  2020-06-11       Impact factor: 4.615

9.  Bayesian Methods for Meta-Analyses of Binary Outcomes: Implementations, Examples, and Impact of Priors.

Authors:  Fahad M Al Amer; Christopher G Thompson; Lifeng Lin
Journal:  Int J Environ Res Public Health       Date:  2021-03-27       Impact factor: 3.390

  9 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.