Figure 2. Oral nutritional interventions and mortality meta-analysis. The plot shows the raw data for mortality in each arm together with the total number of participants and risk ratio (squares) with 95% confidence intervals (CIs) (horizontal bars) analyzed using the Mantel–Haenszel (M-H) fixed effects method of meta-analysis. Data on mortality were extracted for the intervention and comparison groups for each study and combined to obtain a pooled estimate of the overall risk ratio for all studies (diamond). The I2 statistic was used to test for the presence of heterogeneity across studies. The overall effect is given by the Z score. All tests were two-sided. Data were available for several intervention groups and one comparison group in the study by