NEURAL NETWORKS TO IDENTIFY GLAUCOMA WITH STRUCTURAL AND FUNCTIONAL MEASUREMENTS

PURPOSE: Neural networks can recognize patterns and classify complex v ariables, We assessed the ability of neural networks to discriminate b etween normal and glaucomatous eyes by using structural and functional measurements. METHODS: Several neural network algorithms were tested with a database of 185 eyes of patients with early glaucomatous visual field loss (average mean defect, 4.5 dB) and 54 eyes of age-matched n ormal control subjects. The information used included automated visual field indices (mean defect, corrected loss variance, and short-term f luctuation) and structural data (cup/disk ratio, rim area, cup volume, and nerve fiber layer height) from computerized image analysis. RESUL TS: A back propagation network with two intermediate layers assigned a n estimated probability of being glaucomatous to each eye and correctl y identified 88% of all eyes with 90% sensitivity and 84% specificity. The same neural network trained with only structural data correctly i dentified 80% of the eyes with 87% sensitivity and 56% specificity, an d when trained with functional data only, if correctly identified 84% of the eyes with 84% sensitivity and 86% specificity. CONCLUSION: Anal ysis of several optic nerve and visual field variables by neural netwo rks can help identify early glaucomatous damage and assign an estimate d probability that early damage is present in individual patients.