Bladder cancer is the most common cancer of the urinary tract. A quarter of bladder cancer patients presenting with muscle-invasive bladder cancer (MIBC) suffer significant morbidity and succumb to the disease. MicroRNA (miRNA) from tissue, urine or blood samples of MIBC patients have been demonstrated to differ from healthy individuals, and possibly have diagnostic value. The aim of the present meta-analysis was to access the overall diagnostic accuracy comprehensively and quantitatively. Systematic searching in PubMed, Web of Science, Embase and Chinese National Knowledge Infrastructure database was conducted. The pooled sensitivity, specificity, positive and negative likelihood ratios (PLR and NLR) and diagnostic odds ratio (DOR) were calculated via the random effects model to evaluate the overall test performance. Deeks' funnel plot asymmetry test was used to test the publication bias. A total of 10 studies were included in the meta-analysis, with a total of 577 patients and 412 controls. The pooled sensitivity and specificity were 0.78 [95% confidence interval (CI), 0.69-0.86] and 0.77 (95% CI, 0.72-0.81), respectively. The pooled PLR was 2.9 (95% CI, 2.1-3.8), the NLR was 0.31 (95% CI, 0.27-0.35), the DOR was 7 (95% CI, 4-13) and the pooled AUC was 0.80 (95% CI, 0.69-0.87). In conclusion, the current miRNA assays support their use as markers for MIBC diagnosis.