Long-term outcomes of needle revision of trabeculectomy blebs with mitomycin C and 5-fluorouracil: a comparative safety and efficacy report

Abstract

Purpose: To report the long-term comparative outcomes for needle revision with 5-fluorouracil (5-FU) and mitomycin C (MMC) of failed trabeculectomy blebs.

Patients and methods: A retrospective database search was made for all patients who had needle revision with subconjunctival antimetabolite injections on the slit lamp from August 2001 to April 2006. Needle revisions were augmented with MMC instead of 5-FU from December 2003. Ninety-eight eyes of 95 consecutive patients (45 with MMC and 53 with 5-FU) with a minimum follow-up of 1 year were included. 5-FU (5 mg) or MMC (0.02 mg), with 0.1 mL of 2% lignocaine was injected subconjunctivally at least 10 minutes before the revision procedure in the clinic. No patient from the MMC group received subsequent 5-FU injections.

Results: The 5-FU group had significantly longer mean follow-ups (P<0.001) of 53.0+/-18.12 months compared with 33.3+/-9.0 months in the MMC group. The 5-FU group had a significantly higher number of needle revisions than MMC group (1.9+/-1.0 vs. 1.2+/-0.5, P=0.001). Twenty-five eyes (47%) of the 5-FU group and 36 eyes (80%) of the MMC group had a single needle revision (P=0.009). The probability of maintaining intraocular pressure between 5 and 16 mm Hg with no glaucoma medication or further surgical procedure was 71% (62%-88%) and 45% (33%-60%) at 1 year and 61% (49%-78%) and 30% (20%-46%) at 2 years in the MMC and 5-FU groups, respectively. MMC use (hazard ratio=2.18, 95% confidence interval, 1.25-3.81, P=0.006) and intraocular pressure drop immediately after needling as a continuous variable (hazard ratio=1.06, 95% confidence interval, 1.00-1.13.8, P=0.03) were significantly associated with success. Twelve eyes (22.6%) with failed 5-FU needling had subsequent MMC needle revisions, 5 of which were successful by the study criterion. Eyes with 5-FU needle revision were more likely to fail within the first 6 months (P=0.02). Serious complications included blebitis in 3 (5.7%) and 1 (2.2%), delayed bleb leaks in 9 (17.0%) and 1 (2.2%) eyes in the 5-FU and MMC groups, respectively. There was no statistical difference in the complication rates between the groups. Aqueous misdirection was observed in 1 (2.2%) eye of MMC group and delayed suprachoroidal hemorrhage in 1 (1.9%) eye of 5-FU group.

Conclusions: This study suggests that MMC is more effective than 5-FU for needle revision of failed trabeculectomy blebs.