Background The presence of deleterious mutations in breast cancer 1 gene (BRCA1) or breast cancer 2 gene (BRCA2) significantly increases the risk of developing some cancers, such as breast and high-grade serous cancer (HGSC) of ovarian, tubal and peritoneal origin. Risk reducing salpingo-oophorectomy (RRSO) is usually recommended to BRCA1 or BRCA2 carriers after completion of childbearing. Despite prior systematic reviews and meta-analyses on the role of RRSO in reducing the mortality and incidence of breast, HGSC and other cancers, RRSO is still an area of debate and it is unclear whether RRSO differs in effectiveness by type of mutation carried. Objectives To assess the benefits and harms of RRSO in women with BRCA1 or BRCA2 mutations. Search methods We searched the Cochrane Central Register of Controlled Trials (CENTRAL; 2017, Issue 7) in The Cochrane Library, MEDLINE Ovid, Embase Ovid and trial registries, with no language restrictions up to July 2017. We handsearched abstracts of scientific meetings and other relevant publications. Selection criteria We included non-randomised trials (NRS), prospective and retrospective cohort studies, and case series that used statistical adjustment for baseline case mix using multivariable analyses comparing RRSO versus no RRSO in women without a previous or coexisting breast, ovarian or fallopian tube malignancy, in women with or without hysterectomy, and in women with a risk-reducing mastectomy (RRM) before, with or after RRSO Data collection and analysis We extracted data and performed meta-analyses of hazard ratios (HR) for time-to-event variables and risk ratios (RR) for dichotomous outcomes, with 95% confidence intervals (CI). To assess bias in the studies, we used the ROBINS-I 'Risk of bias' assessment tool. We quantified inconsistency between studies by estimating the I' statistic. We used random-effects models to calculate pooled effect estimates. Main results We included 10 cohort studies, comprising 8087 participants (2936 (36%) surgical participants and 5151 (64%) control participants who were BRCA1 or BRCA2 mutation carriers. All the studies compared RRSO with or without RRM versus no RRSO (surveillance). The certainty of evidence by GRADE assessment was very low due to serious risk of bias. Nine studies, including 7927 women, were included in the meta-analyses. The median follow-up period ranged from 0.5 to 27.4 years. Main outcomes: overall survival was longer with RRSO compared with no RRSO (HR 0.32, 95% CI 0.19 to 0.54; P < 0.001; 3 studies, 2548 women; very low-certainty evidence). HGSC cancer mortality (HR 0.06, 95% CI 0.02 to 0.17; I-2 = 69%; P < 0.0001; 3 studies, 2534 women; very low-certainty evidence) and breast cancer mortality (HR 0.58, 95% CI 0.39 to 0.88; I-2 = 65%; P = 0.009; 7 studies, 7198 women; very low-certainty evidence) were lower with RRSO compared with no RRSO. None of the studies reported bone fracture incidence. There was a difference in favour of RRSO compared with no RRSO in terms of ovarian cancer risk perception quality of life (MD 15.40, 95% CI 8.76 to 22.04; P < 0.00001; 1 study; very low-certainty evidence). None of the studies reported adverse events. Subgroup analyses for main outcomes: meta-analysis showed an increase in overall survival among women who had RRSO versus women without RRSO who were BRCA1 mutation carriers (HR 0.30, 95% CI 0.17 to 0.52; P < 0001; I-2 = 23%; 3 studies; very low certainty evidence) and BRCA2 mutation carriers (HR 0.44, 95% CI 0.23 to 0.85; P = 0.01; I-2 = 0%; 2 studies; very low-certainty evidence). The meta-analysis showed a decrease in HGSC cancer mortality among women with RRSO versus no RRSO who were BRCA1 mutation carriers (HR 0.10, 95% CI 0.02 to 0.41; I-2 = 54%; P = 0.001; 2 studies; very low-certainty evidence), but uncertain for BRCA2 mutation carriers due to low frequency of HGSC cancer deaths in BRCA2 mutation carriers. There was a decrease in breast cancer mortality among women with RRSO versus no RRSO who were BRCA1 mutation carriers (HR 0.45, 95% CI 0.30 to 0.67; I-2 = 0%; P < 0.0001; 4 studies; very low-certainty evidence), but not for BRCA2 mutation carriers (HR 0.88, 95% CI 0.42 to 1.87; I-2 = 63%; P = 0.75; 3 studies; very low-certainty evidence). One study showed a difference in favour of RRSO versus no RRSO in improving quality of life for ovarian cancer risk perception in women who were BRCA1 mutation carriers (MD 10.70, 95% CI 2.45 to 18.95; P = 0.01; 98 women; very low-certainty evidence) and BRCA2 mutation carriers (MD 13.00, 95% CI 3.59 to 22.41; P = 0.007; very low-certainty evidence). Data from one study showed a difference in favour of RRSO and RRM versus no RRSO in increasing overall survival (HR 0.14, 95% CI 0.02 to 0.98; P = 0.0001; I-2 = 0%; low-certainty evidence), but no difference for breast cancer mortality (HR 0.78, 95% CI 0.51 to 1.19; P = 0.25; very low-certainty evidence). The risk estimates for breast cancer mortality according to age at RRSO (50 years of age or less versus more than 50 years) was not protective and did not differ for BRCA1 (HR 0.85, 95% CI 0.64 to 1.11; I-2 = 16%; P = 0.23; very low-certainty evidence) and BRCA2 carriers (HR 0.88, 95% CI 0.42 to 1.87; I-2 = 63%; P = 0.75; very low-certainty evidence). Authors' conclusions There is very low-certainty evidence that RRSO may increase overall survival and lower HGSC and breast cancer mortality for BRCA1 and BRCA2 carriers. Very low-certainty evidence suggests that RRSO reduces the risk of death from HGSC and breast cancer in women with BRCA1 mutations. Evidence for the effect of RRSO on HGSC and breast cancer in BRCA2 carriers was very uncertain due to low numbers. These results should be interpreted with caution due to questionable study designs, risk of bias profiles, and very low-certainty evidence. We cannot draw any conclusions regarding bone fracture incidence, quality of life, or severe adverse events for RRSO, or for effects of RRSO based on type and age at risk-reducing surgery. Further research on these outcomes is warranted to explore differential effects for BRCA1 or BRCA2 mutations.
