BACKGROUND: Fluorescence in situ hybridization (FISH) has become a popular biomarker for subsequent monitoring the recurrence of non-muscle invasive bladder cancer (NMIBC), several studies have investigated the ability of FISH to detect recurrence in the surveillance of NMIBC. However, the results were inconsistent. METHODS: We conducted a systematic literature search extensively on authenticated databases including PubMed/Medline, Embase, Web of Science, Ovid, and Cochrane Library. Meta-analysis was performed to find out the sensitivity and specificity of FISH in predicting recurrence of NMIBC. RESULTS: 15 studies were ultimately included in this meta-analysis, a total of 2941 FISH evaluations from 2385 NMIBC patients were available. The pooled sensitivity of FISH was 68% (95% CI: 0.58-0.76), and the pooled specificity was 64% (95% CI: 0.53-0.74). Subgroup analyses were performed in 7 studies without Bacillus Calmette-Guerin (BCG) treatment, the pooled sensitivity was 82% (95% CI: 0.68-0.90), and the pooled specificity was 63% (95% CI: 0.37-0.82). And in 9 studies using `UroVysion standard` to define positive FISH results showed a pooled sensitivity of 60% (95% CI: 0.50-0.70) and specificity of 70% (95% CI: 0.61-0.78). CONCLUSIONS: The findings of this study indicate that FISH has a satisfactory sensitivity (68%) and specificity (64%) and could be a potential biomarker in the surveillance of NMIBC. Moreover, BCG treatment and different FISH methods may have an impact on the sensitivity and specificity, these factors should be taken into account when making clinical strategy.