TY - JOUR
T1 - Controversy and Debate
T2 - Questionable utility of the relative risk in clinical research: Paper 2: Is the Odds Ratio “portable” in meta-analysis? Time to consider bivariate generalized linear mixed model
AU - Xiao, Mengli
AU - Chen, Yong
AU - Cole, Stephen R.
AU - MacLehose, Richard F.
AU - Richardson, David B.
AU - Chu, Haitao
N1 - Publisher Copyright:
© 2021
PY - 2022/2
Y1 - 2022/2
N2 - Objectives: A recent paper by Doi et al. advocated completely replacing the relative risk (RR) with the odds ratio (OR) as the effect measure in clinical trials and meta-analyses with binary outcomes. Besides some practical advantages of RR over OR, Doi et al.’s key assumption that the OR is “portable” in the meta-analysis, that is, study-specific ORs are likely not correlated with baseline risks, was not well justified. Study designs and settings: We summarized Spearman's rank correlation coefficient between study-specific ORs and baseline risks in 40,243 meta-analyses from the Cochrane Database of Systematic Reviews. Results: Study-specific ORs tend to be higher in studies with lower baseline risks of disease for most meta-analyses in Cochrane Database of Systematic Reviews. Using an actual meta-analysis example, we demonstrate that there is a strong negative correlation between OR (RR or RD) with the baseline risk and the conditional effects notably vary with baseline risks. Conclusions: Replacing RR or RD with OR is currently unadvisable in clinical trials and meta-analyses. It is possible that no effect measure is “portable” in a meta-analysis. In addition to the overall (or marginal) effect, we suggest presenting the conditional effect based on the baseline risk using a bivariate generalized linear mixed model.
AB - Objectives: A recent paper by Doi et al. advocated completely replacing the relative risk (RR) with the odds ratio (OR) as the effect measure in clinical trials and meta-analyses with binary outcomes. Besides some practical advantages of RR over OR, Doi et al.’s key assumption that the OR is “portable” in the meta-analysis, that is, study-specific ORs are likely not correlated with baseline risks, was not well justified. Study designs and settings: We summarized Spearman's rank correlation coefficient between study-specific ORs and baseline risks in 40,243 meta-analyses from the Cochrane Database of Systematic Reviews. Results: Study-specific ORs tend to be higher in studies with lower baseline risks of disease for most meta-analyses in Cochrane Database of Systematic Reviews. Using an actual meta-analysis example, we demonstrate that there is a strong negative correlation between OR (RR or RD) with the baseline risk and the conditional effects notably vary with baseline risks. Conclusions: Replacing RR or RD with OR is currently unadvisable in clinical trials and meta-analyses. It is possible that no effect measure is “portable” in a meta-analysis. In addition to the overall (or marginal) effect, we suggest presenting the conditional effect based on the baseline risk using a bivariate generalized linear mixed model.
KW - Baseline risk
KW - Cochrane Database of Systematic Reviews (CDSR)
KW - Correlation
KW - Meta-analysis
KW - Odds ratio
KW - Relative risks
UR - http://www.scopus.com/inward/record.url?scp=85114925774&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85114925774&partnerID=8YFLogxK
U2 - 10.1016/j.jclinepi.2021.08.004
DO - 10.1016/j.jclinepi.2021.08.004
M3 - Comment/debate
C2 - 34384876
AN - SCOPUS:85114925774
SN - 0895-4356
VL - 142
SP - 280
EP - 287
JO - Journal of Clinical Epidemiology
JF - Journal of Clinical Epidemiology
ER -