A Bayesian Radial Basis Function Model to Link Retinal Structure and Visual Function in Glaucoma

Glaucoma is a leading cause of irreversible blindness and requires precise measures for early detection and follow-up. However, individual clinical measures in glaucoma are highly variable. It is anticipated that this variability can be reduced by combining the independent measurements that test various aspects of the glaucomatous damage. This study proposes a mathematical framework to link retinal nerve fibre layer (RNFL) structure and visual function using the data typically acquired in the clinical management of glaucoma. The model performed and generalized well over different populations from three clinical centres. The derived structure-function relationship accorded well with RNFL anatomy, and could be applied to reduce the variability that confounds the measurement of glaucoma damage.