This meta-analysis evaluated the correlation between poly (adenosine diphosphate [ADP]-ribose) polymerase (PARP) expression and prognosis in patients with ovarian cancer.Eligible studies were extracted from the electronic databases of PubMed, Web of Science, and EMBASE until 1 August 2019. The included studies investigated the correlation between PARP expression and clinical outcomes in patients with ovarian cancer. Clinical outcomes are overall survival (OS) and progression free survival (PFS). The clinical data of patients, such as clinicopathologic characteristics and survival, were analyzed. The language was limited to English, and studies conducted at the cellular level, animal studies, and non-original research were excluded. The odds ratios (ORs) and hazard ratios (HRs) with 95% confidence intervals (CIs) were used for this meta-analysis.A total of 9 eligible studies involving 1230 patients were included in our meta-analysis. Based on the analysis, higher PARP expression was correlated with worse overall survival [OS] (HR,1.64; 95% CI, 1.08-2.49; P = 0.020) in the univariate analysis, whereas results from multivariate analysis indicated that PARP overexpression wasn't statistically associated with worse OS (HR, 1.36; 95% CI, 0.98-1.90; P = 0.069). Moreover, the pooled results revealed that patients with PARP overexpression were not associated with worse histologic grade (OR,2.22; 95% CI, 0.98-5.02; P = 0.06).PARP overexpression maybe associated with poor prognosis and survival in patients with ovarian cancer. The patients with PARP over expression were not tended to have a worse histologic grade. Findings require further validation.