Joint NC BERD Seminar: Bayesian and machine learning spatial methods for detecting disease progression in glaucoma

In this talk, I will present novel implementations of spatial machine learning and statistical methodology in the field of glaucoma clinical research to detect disease progression from longitudinal series of visual fields. We demonstrate multiple novel Bayesian methodologies that have been developed to model the complex spatiotemporal nature of visual field data. We show that Bayesian methods provide a flexible modeling framework that permits incorporation of the underlying retinal anatomy to improve detection of visual field progression. Finally, we describe how the variational autoencoder, a generative machine learning model, can be used to model spatiotemporal data and demonstrate its utility in identifying disease progression in glaucoma. This event is being cross-promoted by the NC BERD Consortium, a collaboration of the CTSA-funded BERD cores at UNC-Chapel Hill, Wake Forest University School of Medicine, and Duke University School of Medicine.