OBJECTIVE: To systematically evaluate the diagnostic efficacy of confocal laser endomicroscopy (CLE) in detection of bladder cancer. METHODS: A systematic literature search on CLE in diagnosing bladder cancer in PubMed, Embase, and the Cochrane Library databases was performed. A bivariate meta-regression model was used for meta-analysis to evaluate the pooled diagnostic value of CLE. RESULTS: A total of 5 eligible studies involving 302 lesions were available for this meta-analysis. In a per-lesion analysis, pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and summary receiver-operating curve (SROC) area under the curve (AUC) of CLE for malignant lesions were 0.90 (95% confidence interval [CI]: 0.85-0.94), 0.72 (95% CI: 0.59-0.82), 3.20 (95% CI: 2.14-4.79), 0.14 (95% CI: 0.09-0.21), 23.27 (95% CI: 11.71-46.25), and 0.91 (95% CI: 0.89-0.94), respectively. For low-grade urothelial carcinomas, pooled sensitivity, specificity, PLR, NLR, DOR, and AUC for CLE were 0.72 (95% CI: 0.57-0.84), 0.87 (95% CI: 0.77-0.93), 5.48 (95% CI: 3.12-9.62), 0.32 (95% CI: 0.20-0.50), 17.19 (95% CI: 8.01-36.89), and 0.85 (95% CI: 0.82-0.88), respectively. For high-grade urothelial carcinomas, pooled sensitivity, specificity, PLR, NLR, DOR, and AUC for CLE were 0.82 (95% CI: 0.62-0.92), 0.84 (95% CI: 0.73-0.91), 4.96 (95% CI: 2.58-9.54), 0.22 (95% CI: 0.09-0.52), 22.49 (95% CI: 5.33-94.85), and 0.89 (95% CI: 0.86-0.91), respectively. CONCLUSION: CLE is a promising endoscopy technique for real-time tumor grading of bladder cancer.