An Artificial Intelligence Approach to Detect Visual Field Progression in Glaucoma Based on Spatial Pattern Analysis.

Authors

Mengyu Wang, Harvard Medical School
Lucy Q. Shen, Harvard Medical School
Louis R. Pasquale, Harvard Medical School
Paul Petrakos, Harvard Medical School
Sydney Formica, Harvard Medical School
Michael V. Boland, Johns Hopkins University School of Medicine
Sarah R. Wellik, University of Miami School of Medicine
Carlos Gustavo De Moraes, Columbia University Medical Center
Jonathan S. Myers, Wills Eye Hospital, Thomas Jefferson UniversityFollow
Osamah Saeedi, University of Maryland School of Medicine
Hui Wang, Harvard Medical School; Jilin University of Finance and Economics
Neda Baniasadi, Harvard Medical School
Dian Li, Harvard Medical School
Jorryt Tichelaar, Harvard Medical School
Peter J. Bex, Northeastern University
Tobias Elze, Harvard Medical School; Max Planck Institute for Mathematics in the Sciences

Document Type

Article

Publication Date

1-2-2019

Comments

This article has been peer reviewed. It is the author’s final published version in Investigative Ophthalmology & Visual Science, Volume 60, Issue 1, January 2019, Pages 365-375.

The published version is available at https://doi.org/10.1167/iovs.18-25568. Copyright © Wang et al.

Abstract

Purpose: To detect visual field (VF) progression by analyzing spatial pattern changes.

Methods: We selected 12,217 eyes from 7360 patients with at least five reliable 24-2 VFs and 5 years of follow-up with an interval of at least 6 months. VFs were decomposed into 16 archetype patterns previously derived by artificial intelligence techniques. Linear regressions were applied to the 16 archetype weights of VF series over time. We defined progression as the decrease rate of the normal archetype or any increase rate of the 15 VF defect archetypes to be outside normal limits. The archetype method was compared with mean deviation (MD) slope, Advanced Glaucoma Intervention Study (AGIS) scoring, Collaborative Initial Glaucoma Treatment Study (CIGTS) scoring, and the permutation of pointwise linear regression (PoPLR), and was validated by a subset of VFs assessed by three glaucoma specialists.

Results: In the method development cohort of 11,817 eyes, the archetype method agreed more with MD slope (kappa: 0.37) and PoPLR (0.33) than AGIS (0.12) and CIGTS (0.22). The most frequently progressed patterns included decreased normal pattern (63.7%), and increased nasal steps (16.4%), altitudinal loss (15.9%), superior-peripheral defect (12.1%), paracentral/central defects (10.5%), and near total loss (10.4%). In the clinical validation cohort of 397 eyes with 27.5% of confirmed progression, the agreement (kappa) and accuracy (mean of hit rate and correct rejection rate) of the archetype method (0.51 and 0.77) significantly (P < 0.001 for all) outperformed AGIS (0.06 and 0.52), CIGTS (0.24 and 0.59), MD slope (0.21 and 0.59), and PoPLR (0.26 and 0.60).

Conclusions: The archetype method can inform clinicians of VF progression patterns.

Recommended Citation

Wang, Mengyu; Shen, Lucy Q.; Pasquale, Louis R.; Petrakos, Paul; Formica, Sydney; Boland, Michael V.; Wellik, Sarah R.; De Moraes, Carlos Gustavo; Myers, Jonathan S.; Saeedi, Osamah; Wang, Hui; Baniasadi, Neda; Li, Dian; Tichelaar, Jorryt; Bex, Peter J.; and Elze, Tobias, "An Artificial Intelligence Approach to Detect Visual Field Progression in Glaucoma Based on Spatial Pattern Analysis." (2019). Wills Eye Hospital Papers. Paper 93.
https://jdc.jefferson.edu/willsfp/93

Creative Commons License

This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

PubMed ID

30682206

Language

English