The online version of this article (https://doi.org/10.1186/s12874-017-0454-x) contains supplementary material, which is available to authorized users.
Different confounder adjustment strategies were used to estimate odds ratios (ORs) in case-control study, i.e. how many confounders original studies adjusted and what the variables are. This secondary data analysis is aimed to detect whether there are potential biases caused by difference of confounding factor adjustment strategies in case-control study, and whether such bias would impact the summary effect size of meta-analysis.
We included all meta-analyses that focused on the association between breast cancer and passive smoking among non-smoking women, as well as each original case-control studies included in these meta-analyses. The relative deviations (RDs) of each original study were calculated to detect how magnitude the adjustment would impact the estimation of ORs, compared with crude ORs. At the same time, a scatter diagram was sketched to describe the distribution of adjusted ORs with different number of adjusted confounders.
Substantial inconsistency existed in meta-analysis of case-control studies, which would influence the precision of the summary effect size. First, mixed unadjusted and adjusted ORs were used to combine individual OR in majority of meta-analysis. Second, original studies with different adjustment strategies of confounders were combined, i.e. the number of adjusted confounders and different factors being adjusted in each original study. Third, adjustment did not make the effect size of original studies trend to constringency, which suggested that model fitting might have failed to correct the systematic error caused by confounding.
The heterogeneity of confounder adjustment strategies in case-control studies may lead to further bias for summary effect size in meta-analyses, especially for weak or medium associations so that the direction of causal inference would be even reversed. Therefore, further methodological researches are needed, referring to the assessment of confounder adjustment strategies, as well as how to take this kind of bias into consideration when drawing conclusion based on summary estimation of meta-analyses.
Stangl DK, Berry DA. Meta-analysis in medicine and health policy. New York: Marcel Dekker; 2000. CrossRef
Glass G. Primary, secondary, and meta-analysis of research. American Educational Research Association: US; 1976.
Stephen BH, Steven RC, Warren SB, Deborah GG, Thomas BN. Designing clinical research. 4th ed. USA: Lippincott Williams & Wilkins; 2013.
Ma J, Shi BL, Zuo WS. Meta-analysis of the relationship between passive smoking and breast cancer. Chin Cancer. 2011;20:525–8. [In Chinese]
Sadri G, Mahjub H. Passive or active smoking, which is more relevant to breast cancer. Saudi Med J. 2007;28(2):254–8. PubMed
Zhou XB, Zhang J. Meta-analysis of the relationship between passive smoking and female breast cancer in China. Chin J Clin Rehab. 2006;10:6–8. [in Chinese]
Khuder SA, Simon VJ. Is there an association between passive smoking and breast cancer? Eur J Epidemiol. 2001;16:1117–21. CrossRef
Egger M, Davey SG, Schneider M. Systematic reviews in health care: meta-analysis in context. 2nd ed. London: BMJ Publishing Group; 2001. CrossRef
- Can statistic adjustment of OR minimize the potential confounding bias for meta-analysis of case-control study? A secondary data analysis
- BioMed Central
Neu im Fachgebiet AINS
Meistgelesene Bücher aus dem Fachgebiet AINS
Mail Icon II