Earlier confirmation of glaucoma progression with risk-weighted visual field and OCT scheduling

Glaucoma is monitored with visual field (VF) tests of function and optical coherence tomography (OCT) of structure, but models that predict progression do not determine when each test should be repeated. Here we present GEAR (gated expected-delay allocation rule), a policy that pairs a longitudinal risk predictor with a decision layer and gives each eye separate VF and OCT intervals. In the decision layer, clinical gates define the admissible test intervals, and an explicit objective selects the intervals that minimize risk-weighted detection delay plus a penalty on expected testing, with penalties fixed to a routine-testing budget. In retrospective replay of held-out records (5,935 visits from 1,681 patients), GEAR with risk-based confirmation timing confirmed simulated progression 3.4 months earlier than annual VF and OCT testing (95% confidence interval, 2.7-4.1) at a comparable testing rate. The reduction persisted against a guideline-informed comparator and a reconstructed Kalman comparator, under an alternative onset assumption and with a VF-only adaptation in an external dataset.

Authors

Institutions

Publication Details

Journal
medRxiv
Published
2026-11-18
DOI
https://doi.org/10.64898/2026.11.16.26368187
Primary Topic
Glaucoma and retinal disorders
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Earlier confirmation of glaucoma progression with risk-weighted visual field and OCT scheduling

Mousa Moradi, Asahi Fujita, Tobias Elze, Nazlee Zebardast et al.
4 links
medRxiv
Glaucoma and retinal disorders
preprint

Earlier confirmation of glaucoma progression with risk-weighted visual field and OCT scheduling

Mousa Moradi, Asahi Fujita, Tobias Elze, Nazlee Zebardast, Mohammad Eslami, Liyin Chen
preprint en

Abstract

Glaucoma is monitored with visual field (VF) tests of function and optical coherence tomography (OCT) of structure, but models that predict progression do not determine when each test should be repeated. Here we present GEAR (gated expected-delay allocation rule), a policy that pairs a longitudinal risk predictor with a decision layer and gives each eye separate VF and OCT intervals. In the decision layer, clinical gates define the admissible test intervals, and an explicit objective selects the intervals that minimize risk-weighted detection delay plus a penalty on expected testing, with penalties fixed to a routine-testing budget. In retrospective replay of held-out records (5,935 visits from 1,681 patients), GEAR with risk-based confirmation timing confirmed simulated progression 3.4 months earlier than annual VF and OCT testing (95% confidence interval, 2.7-4.1) at a comparable testing rate. The reduction persisted against a guideline-informed comparator and a reconstructed Kalman comparator, under an alternative onset assumption and with a VF-only adaptation in an external dataset.

medRxiv
Broad Institute (US), Massachusetts Eye and Ear Infirmary (US), Harvard University (US)
Good health and well-being
Glaucoma and retinal disorders
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon