Purpose: We design three new indexes of retinal nerve fiber layer thickness (RNFLT) by functional data analysis (FDA) methods and evaluate the diagnostic performance of support vector machines (SVM) based on these three new indexes and average RNFLT. Method: A total of 217 healthy eyes (122 subjects) and 88 glaucoma eyes (49 patients) were included. Three new indexes (minimum of RNFLT curve, range of derivative curve and ISNT score) of RNFLT from optical coherence tomography (OCT) and average RNFLT were used as predictors in the SVM. The sensitivity, specificity and area under the re-ceiver operating characteristic curve (AUC) were used to evaluate the diagnostic performance of the proposed and compared methods. Results: The sensitivity of the proposed method was 97.73%, 95.45%, and 79.55%, respectively, at the specificity of 90%, 95%, and 99%.A significantly larger AUC of 98.81% (95% con-fidence interval (CI), 97.84%-99.78%) was obtained using the proposed method compared with a previous study -artificial neural networks based on RNFLT of four sectors under three division methods: 93.97% (95% CI, 90.63%-97.63%) with clock sectors division, 94.55% (95% CI, 91.43%-98.58%) with ISNT (inferior -superior-nasal-temporal) sectors division and 92.90% (95% CI, 88.87%-97.62%) with planimetric sectors division. Conclusions: The three new indexes based on RNFLT curves combined with SVM can be used to distinguish glaucoma from healthy subjects with high accuracy, performing better than conventional methods.