BackgroundTo reanimate the mimetic muscles, crossface nerve graft (CFNG) is an effective surgical option. However, muscle atrophy after facial paralysis may influence the surgical result. We analyzed the relationship between surgical result and preoperative paralysis duration. MethodsWe performed CFNG on 15 patients. The sural nerve was transferred between the affected and nonaffected sides of the zygomatic branch. Eyelid function and eyelid lid were evaluated using the modified House-Brackmann scale. The effects of age, sex, cause of facial paralysis, graft nerve length, and preoperative paralysis duration were evaluated. ResultsThe mean follow up period was 9.33.3 (range 4-14)years. Eyelid closure was excellent in four patients, good in six, fair in one, and poor in four. Statistically, no significant difference was observed between those patients with excellent or good outcomes and fair or poor outcomes regarding age (40.9 +/- 11.0years vs. 22.6 +/- 20.8; P=.067), sex (male/female=2/8 vs. 3/2; P=.250), cause (tumor/trauma=10/0 vs. 3/2; P=.095), and length of nerve graft (14.4 +/- 0.8cm vs. 13.8 +/- 1.6cm; P=.375). The average preoperative paralysis duration in the excellent/good patients was significantly shorter than that in the fair/poor patients (P=.005). All eight cases with preoperative paralysis of less than 6months showed a marked excellent/good result. Two of the seven patients with preoperative paralysis was 6months or longer marked fair/poor result. (P=.007). ConclusionsTo achieve successful results with CFNG, surgery should be performed within 6months of the onset of paralysis.