Prevalence and determinants of unintended pregnancy in Ethiopia: narrative synthesis and meta-analysis

Background: Unintended pregnancy has enormous health, social and psychological impacts. Thus, comprehensive local evidence is required to guide interventions to prevent the occurrence and consequences of unintended pregnancy. This systematic review was conducted to examine the prevalence and determinants of unintended pregnancy in Ethiopia. Methods: The review was done following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and Synthesis Without Meta-analysis (SWiM) guideline. Electronic databases including Medline/ PubMed, Cochrane Library, CINAHL, Google scholar, and African journal online were searched to retrieve studies published from January 1/1990 to October 30/2020. Grey literatures were accessed from the online libraries of academic institutions in Ethiopia using the Google search engine. The qualities of the studies were assessed using Joanna Briggs Institute critical appraisal checklists. The retrieved studies were analyzed using STATA software version 13. The prevalence of unintended pregnancy was pooled using the random-effects model. The evidences on the determinants of unintended pregnancy were summarized in a narrative format. The statistical heterogeneity between studies was quantified by using the I-square values. Sub-group analysis and meta-regressions were done to identify the sources of heterogeneity among studies. Results: A total of 250 studies were retrieved of which 25 studies with 23,030 women were included for metaanalysis. Only 24 studies scrutinized the determinants of unintended pregnancy. The overall prevalence of unintended pregnancy was 30 % (95% CI; 27-33 %) with high heterogeneity among studies (I-2 = 95.06 %). The pooled prevalence of unwanted and mistimed pregnancy was 12 &17% respectively. The study region was the source of heterogeneity whereas study setting, study year, sample size, and study quality score were not the sources of heterogeneity (p > 0.1). Unintended pregnancy was positively associated with a low level of education, poverty, multiparity, rural residence, extreme ages, being unmarried, lack of decision-making power, inaccessibility of health facilities, poor knowledge, and non-use of contraceptives. Conclusions: The pooled prevalence of unintended pregnancy in Ethiopia was high. Empowering women and ensuring the accessibility of quality family planning services can reduce the prevailing high prevalence of unintended pregnancy. Interventions that target rural, poor, unmarried, multiparous, less-educated, and adolescent women are also important to avert untended pregnancy in Ethiopia.