Statistical Analysis

We used the random-effects model described by DerSimonian and Laird to calculate summary point prevalence and 95% confidence interval (CI).²⁶ Rates of PI-IBS in patients exposed to IE were compared with non-exposed individuals to estimate summary relative risk (RR) and 95% CI. To identify risk factors associated with PI-IBS, we pooled maximally adjusted odds ratio (OR; to account for confounding variables), where reported, using random-effects model. To estimate what proportion of total variation across studies was due to heterogeneity rather than chance, I² statistic was calculated. In this, a value of <30%, 30%–59%, 60%–75% and >75% were suggestive of low, moderate, substantial and considerable heterogeneity, respectively.²⁷ Once heterogeneity was noted, between-study sources of heterogeneity were investigated using a priori defined subgroup analyses by stratifying original estimates according to study characteristics (as described above). In this analysis, a p-value for differences between subgroups (P_interaction) of <0.10 was considered statistically significant, i.e., significant differences in summary estimates (either point prevalence of PI-IBS or relative risk of PI-IBS) were observed in different subgroup categories. Publication bias for PI-IBS prevalence and RR was assessed qualitatively using funnel plot, and quantitatively, using Egger’s test.²⁸

All p values were two tailed. For all tests (except for heterogeneity), a probability level <0.05 was considered statistically significant. All calculations and graphs were performed using Comprehensive Meta-Analysis (CMA) version 2 (Biostat, Englewood, NJ).