Cervical ripening agents in the second trimester of pregnancy in women with a scarred uterus: a systematic review and metaanalysis of observational studies

OBJECTIVE: The aim of this systematic review and metaanalysis was to determine the efficacy and safety of cervical ripening agents in the second trimester of pregnancy in patients with previous cesarean delivery. STUDY DESIGN: Data sources were PubMed, EMBASE, CINAHL, LILACS, Google Scholar, and clinicaltrials.gov (1983 through 2015). Eligibility criteria were cohort or cross-sectional studies that reported on efficacy and safety of cervical ripening agents in patients with previous cesarean delivery. Efficacy was determined based on the proportion of patients achieving vaginal delivery and vaginal delivery within 24 hours following administration of a cervical ripening agent. Safety was assessed by the risk of uterine rupture and complications such as retained placental products, blood transfusion requirement, and endometritis, when available, as secondary outcomes. Of the 176 studies identified, 38 met the inclusion criteria. Of these, 17 studies were descriptive and 21 studies compared the efficacy and safety of cervical ripening agents between patients with previous cesarean and those with no previous cesarean. From included studies, we abstracted data on cervical ripening agents and estimated the pooled risk differences and risk ratios with 95% confidence intervals. To account for between-study heterogeneity, we estimated risk ratios based on underlying random effects analyses. Publication bias was assessed via funnel plots and across-study heterogeneity was assessed based on the I 2 measure. RESULTS: The most commonly used agent was PGE1. In descriptive studies, PGE1 was associated with a vaginal delivery rate of 96.8%, of which 76.3% occurred within 24 hours, uterine rupture in 0.8%, retained placenta in 10.8%, and endometritis in 3.9% in patients with >= 1 cesarean. In comparative studies, the use of PGE1, PGE2, and mechanical methods (laminaria and dilation and curettage) were equally efficacious in achieving vaginal delivery between patients with and without prior cesarean (risk ratio, 0.99, and 95% confidence interval, 0.98-1.00; risk ratio, 1.00, and 95% confidence interval, 0.98-1.02; and risk ratio, 1.00, and 95% confidence interval, 0.98-1.01; respectively). In patientswith history of >= 1 cesarean the use of PGE1 was associated with higher risk of uterine rupture (risk ratio, 6.57; 95% confidence interval, 2.21-19.52) and retained placenta (risk ratio, 1.21; 95% confidence interval, 1.03-1.43) compared to women without a prior cesarean. However, the risk of uterine rupture among women with history of only 1 cesarean (0.47%) was not statistically significant (risk ratio, 2.36; 95% confidence interval, 0.39e14.32), whereas among those with history of >= 2 cesareans (2.5%) was increased as compared to those with no previous cesarean (0.08%) (risk ratio, 17.55; 95% confidence interval, 3.00-102.8). Funnel plots did not demonstrate any clear evidence of publication bias. Across-study heterogeneity ranged from 0-81%. CONCLUSION: This systematic review and metaanalysis provides evidence that PGE1, PGE2, and mechanical methods are efficacious for achieving vaginal delivery in women with previous cesarean delivery. The use of prostaglandin PGE1 in the second trimester was not associated with significantly increased risk for uterine rupture among women with only 1 cesarean; however, this risk was substantially increased among women with >= 2 cesareans although the absolute risk appeared to be relatively small.