Etiological and prognostic studies always directly reported effect size with its 95% confidence interval, hence, data transformation was needed when performing meta-analysis based on these studies. Using the data of risk ratio, hazard ratio, odds ratio and 95% confidence interval as an example, this paper introduces the process of using RevMan 5.3 software to convert data and perform meta-analysis.
Risk ratio (RR) and hazard ratio (HR) are two common effect measures in prospective studies. When describing the magnitude of clinical effects in the original study and meta-analysis, they cannot be used interchangeably. Selecting an appropriate measures and interpreting them correctly is critical in clinical research. In this study, we summarized similarities and differences between risk and hazard, compared differences between RR and HR in estimation methods and clinical interpretation. The magnitude of RR and HR estimated from the same studies were compared, and two feasible formulas converting between RR and HR were presented for meta-analysis.
