Algorithm to Predict the Outcome of Microvascular Decompression for Hemifacial Spasm: A Data-Mining Analysis Using a Decision Tree.

OBJECTIVE: Although microvascular decompression (MVD) is the primary treatment for hemifacial spasm (HFS), the postoperative course is variable. This study aimed to develop a prediction model of the outcome of MVD in patients with HFS by investigating influential factors. METHODS: Electronic medical records of 1624 patients with HFS who underwent MVD from July 2004 to January 2015 were reviewed. The relationships between patient-related, disease-related, and surgery-related factors and postoperative outcome were analyzed using multinomial logistic regression. A predictive model for MVD outcome was developed using decision tree analysis. RESULTS: The mean follow-up duration after surgery was 30.2 months (median, 23.5 months; range, 6.0-133.3 months). For the 1624 patients, the overall improvement rate was 90.5%. Overall, 984 patients (60.6%) showed improvement of spasm immediately after surgery, 486 (29.9%) experienced delayed improvement, and 154 (9.5%) showed persistence of spasm. Outcome of patients with HFS after MVD was predicted by 4 items: postoperative delayed facial palsy, degree of preoperative spasm, intraoperative indentation on the facial nerve, and sex. The patients were classified into 6 categories and improvement of spasm immediately after surgery showed 35%-91%, delayed improvement 6%-46%, and persistence of spasm 0%-59%. The accuracy of the developed prediction model was 0.608. CONCLUSIONS: Male sex, mild degree of preoperative spasm, intraoperative indentation on the facial nerve, and postoperative delayed facial palsy were better favorable prognostic factors of MVD in patients with HFS. This novel algorithm may be useful to predict the outcome of MVD in these patients.