A meta-analysis was performed to evaluate the accuracy of optical coherence tomography (OCT) for diagnostic accuracy studies in bladder cancer patients. English language studies reporting the diagnostic accuracy of OCT for bladder cancer were retrieved from the PubMed, EMBASE and Cochrane Library databases in December 2014. Histopathology was a reference standard. Sensitivities, specificities, positive likelihood ratios and negative likelihood ratios were calculated, and summary receiver operating characteristic curves were drawn to determine the diagnostic accuracy of OCT. Finally, 9 eligible studies (468 patients) were included in our meta-analysis. The pooled sensitivity, specificity, positive likelihood ratio and negative likelihood ratio of OCT were 0.96 [95% confidence interval (CI): 0.94-0.98], 0.82 (95% CI: 0.80-0.85), 6.83 (95% CI: 3.24-14.1) and 0.05 (95% CI: 0.02-0.16), respectively. The summary diagnostic odds ratio was 138.88 (95% CI: 29.63-650.89) and the overall area under the curve was 0.9735. These results suggest that OCT has excellent diagnostic performance in patients with bladder cancer and recurrent lesions.