JMIR Publications

ABSTRACT

Background:

The necessity of meta-analyses including observational studies has been discussed in the literature, but a synergistic analysis method combining randomised and observational studies has not been reported.

Objective:

This study introduces a logical method for clinical interpretation.

Methods:

Observational studies differ in validity depending on the degree of the confounders’ influence. Combining interpretations might be challenging, especially if the statistical directions are similar but the magnitude of the pooled results are different, between randomised and observational studies (grey zone). We designed a stepwise-hierarchical pooled analysis, a method of analysing distribution trends as well as individual pooled results by dividing included studies into at least three stages (e.g. all studies, balanced studies, and randomised studies), to overcome such hindrances.

Results:

According to the model, the validity of hypothesis are mostly based on the pooled results of randomised studies (the highest stage). In addition, ascending patterns where effect size and statistical significance increase gradually with stage, strengthen the validity of the hypothesis; in this case, the effect size of observational studies is lower than that of the true effect (e.g. because of uncontrolled effect of negative confounders). Descending patterns where decreasing effect size and statistical significance gradually weaken the validity of the hypothesis suggest that the effect size and statistical significance of observational studies is larger than the true effect (e.g. because of researchers’ bias). These are described in more detail in the main text as four descriptive patterns.

Conclusions:

We recommend using the stepwise-hierarchical pooled analysis for meta-analyses involving randomised and observational studies. Clinical Trial: NA