Predicting Glaucoma Development With Longitudinal Deep Learning Predictions From Fundus Photographs.

Journal Article (Journal Article)


To assess whether longitudinal changes in a deep learning algorithm's predictions of retinal nerve fiber layer (RNFL) thickness based on fundus photographs can predict future development of glaucomatous visual field defects.


Retrospective cohort study.


This study included 1,072 eyes of 827 glaucoma-suspect patients with an average follow-up of 5.9 ± 3.8 years. All eyes had normal standard automated perimetry (SAP) at baseline. Additional SAP and fundus photographs were acquired throughout follow-up. Conversion to glaucoma was defined as repeatable glaucomatous defects on SAP. An OCT-trained deep learning algorithm (machine to machine, M2M) was used to predict RNFL thicknesses from fundus photographs. Joint longitudinal survival models were used to assess whether baseline and longitudinal change in M2M's RNFL thickness estimates could predict development of visual field defects.


A total of 196 eyes (18%) converted to glaucoma during follow-up. The mean rate of change in M2M's predicted RNFL thickness was -1.02 μm/y for converters and -0.67 μm/y for non-converters (P < .001). Baseline and rate of change of predicted RNFL thickness were significantly predictive of conversion to glaucoma, with hazard ratios in the multivariable model of 1.56 per 10 μm lower at baseline (95% CI, 1.33-1.82; P < .001) and 1.99 per 1 μm/y faster loss in thickness during follow-up (95% CI, 1.36-2.93; P < .001).


Longitudinal changes in a deep learning algorithm's predictions of RNFL thickness measurements based on fundus photographs can be used to predict risk of glaucoma conversion in eyes suspected of having the disease.

Full Text

Duke Authors

Cited Authors

  • Lee, T; Jammal, AA; Mariottoni, EB; Medeiros, FA

Published Date

  • May 1, 2021

Published In

Volume / Issue

  • 225 /

Start / End Page

  • 86 - 94

PubMed ID

  • 33422463

Pubmed Central ID

  • PMC8239478

Electronic International Standard Serial Number (EISSN)

  • 1879-1891

International Standard Serial Number (ISSN)

  • 0002-9394

Digital Object Identifier (DOI)

  • 10.1016/j.ajo.2020.12.031


  • eng