Persistence, Spatial Distribution and Implications for Progression Detection of Blind Parts of the Visual Field in Glaucoma: A Clinical Cohort Study

Background: Visual field testing is an essential part of glaucoma care. It is hampered by variability related to the disease itself, response errors and fatigue. In glaucoma, blind parts of the visual field contribute to the diagnosis but - once established - not to progression detection; they only increase testing time. The aims of this study were to describe the persistence and spatial distribution of blind test locations in standard automated perimetry in glaucoma and to explore how the omission of presumed blind test locations would affect progression detection. Methodology/Principal Findings: Data from 221 eyes of 221 patients from a cohort study with the Humphrey Field Analyzer with 30-2 grid were used. Patients were stratified according to baseline mean deviation (MD) in six strata of 5 dB width each. For one, two, three and four consecutive <0 dB sensitivities in the same test location in a series of baseline tests, the median probabilities to observe <0 dB again in the concerning test location in a follow-up test were 76, 86, 88 and 90%, respectively. For <10 dB, the probabilities were 88, 95, 97 and 98%, respectively. Median (interquartile range) percentages of test locations with three consecutive <0 dB sensitivities were 0(0-0), 0(0-2), 4(0-9), 17(8-27), 27(20-40) and 60(50-70)% for the six MD strata. Similar percentages were found for a subset of test locations within 10 degree eccentricity (P>0.1 for all strata). Omitting test locations with three consecutive <0 dB sensitivities at baseline did not affect the performance of the MD-based Nonparametric Progression Analysis progression detection algorithm. Conclusions/Significance: Test locations that have been shown to be reproducibly blind tend to display a reasonable blindness persistence and do no longer contribute to progression detection. There is no clinically useful universal MD cut-off value beyond which testing can be limited to 10 degree eccentricity.