Evidence map›Paper›PMID 41258693›Full record

ArticleTranslational vision science & technology2025

Performance of General-Purpose Vision Language Models and Ophthalmology Foundation Models in Glaucoma Detection and Function Prediction.

Jalil Jalili, Justin Huynh, Evan Walker, Benton Gabriel Chuter, Christopher Bowd, Anna Heinke, Akram Belghith, Michael Henry Goldbaum, Massimo Antonio Fazio, Christopher A Girkin and 6 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in Translational vision science & technology, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.

0numbers the graph read from it
0cells of the map it votes in
1citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

1 citing paper in PubMed.

  1. Article
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

16 authors.

Jalil JaliliDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.
Justin HuynhDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.
Evan WalkerDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.
Benton Gabriel ChuterDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.
Christopher BowdDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.
Anna HeinkeDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.
Akram BelghithDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.
Michael Henry GoldbaumDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.
Massimo Antonio FazioDepartment of Ophthalmology and Vision Sciences, University of Alabama at Birmingham, Birmingham, AL, USA.
Christopher A GirkinDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.
Carlos Gustavo De MoraesDepartment of Ophthalmology, Harkness Eye Institute, Bernard and Shirlee Brown Glaucoma Research Laboratory, New York, NY, USA.
Jeffrey M LiebmannDepartment of Ophthalmology, Harkness Eye Institute, Bernard and Shirlee Brown Glaucoma Research Laboratory, New York, NY, USA.
Sally L BaxterDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.
Robert N WeinrebDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.
Linda M ZangwillDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.
Mark ChristopherDivision of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, CA, USA.

Funding

Bridge2AI:Salutogenesis Data Generation ProjectOT2OD032644 · OD · WASHINGTON UNIVERSITY · PI AYYAGARI, RADHA, BAHMANI, AMIR · 2022 to 2025
$32.7M
Vision BiostatisticsP30EY022589 · NEI · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI Dirk-Uwe G Bartsch · 2012 to 2026
$10.3M
San Diego Biomedical Informatics Education & Research (SABER)T15LM011271 · NLM · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI SHAMIM NEMATI · 2012 to 2026
$9.7M
Diagnostic Innovations in Glaucoma:Structural AssessmentR01EY011008 · NEI · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI ZANGWILL, LINDA M · 1995 to 2015
$8.7M
xADAGES III: Contribution of genotype to glaucoma phenotype in African AmericansR01EY023704 · NEI · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI ROTTER, JEROME I, WEINREB, ROBERT N · 2013 to 2017
$6.3M
Diagnostic Innovations in Glaucoma Study (DIGS): High Myopia and Advanced DiseaseR01EY027510 · NEI · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI LINDA M ZANGWILL · 2017 to 2026
$5.3M
Diagnosis and Monitoring of Glaucoma with Optical Coherence Tomography AngiographyR01EY029058 · NEI · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI WEINREB, ROBERT N · 2018 to 2024
$4.2M
Diagnostic Innovations in Glaucoma Study (DIGS): Functional ImpairmentR01EY021818 · NEI · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI MEDEIROS, FELIPE · 2011 to 2015
$3.4M
African Descent and Glaucoma Evaluation (ADAGES) II: Glaucoma ProgressionR01EY019869 · NEI · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI ZANGWILL, LINDA M · 2010 to 2014
$2.8M
Predicting and Detecting Glaucomatous Progression Using Pattern RecognitionR01EY022039 · NEI · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI BOWD, CHRISTOPHER · 2012 to 2015
$1.5M
Translational Vision Research Training at UCSDT32EY026590 · NEI · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI ZANGWILL, LINDA M · 2016 to 2025
$854k
Deep Learning Approaches to Detect Glaucoma and Predict Progression from Spectral Domain Optical Coherence TomographyR00EY030942 · NEI · UNIVERSITY OF CALIFORNIA, SAN DIEGO · PI CHRISTOPHER, MARK · 2023 to 2025
$747k
NEI NIH HHS P30 EY022589NEI NIH HHS R00 EY030942NEI NIH HHS R01 EY011008NEI NIH HHS R01 EY019869NEI NIH HHS R01 EY021818NEI NIH HHS R01 EY022039NEI NIH HHS R01 EY023704NEI NIH HHS R01 EY027510NEI NIH HHS R01 EY029058NEI NIH HHS R21 EY027945NEI NIH HHS T32 EY026590NEI NIH HHS T35 EY033704NIH HHS OT2 OD032644NLM NIH HHS T15 LM011271
6 · The paper itself

Abstract

Purpose: To evaluate the performance of vision-language models (VLMs), in glaucoma detection and visual field (VF) mean deviation (MD) prediction tasks using optical coherence tomography (OCT) images. Methods: A total of 27,610 SPECTRALIS OCT images from 1025 participants (1690 eyes), collected between 2008 and 2021 as part of the Diagnostic Innovations in Glaucoma Study (DIGS) and the African Descent and Glaucoma Evaluation Study (ADAGES), were included. Vision components of LLaVA and PaliGemma, as well as RETFound and ResNet-50 models, were fine-tuned for glaucoma classification and VF MD prediction. Models were trained using OCT circle scans centered on the optic nerve head. Three training configurations were compared. Performance was evaluated using area under the receiver operating characteristic curve (AUC), mean absolute error (MAE), and related metrics. Results: The LLaVA model, when both vision encoder and multi-layer projector were fine-tuned, achieved the best performance with an AUC of 0.92 (95% confidence interval [CI], 0.86-0.95) for glaucoma classification and an MAE of 1.79 dB (95% CI, 1.55-2.00) for VF MD prediction. RETFound and PaliGemma also performed well, with AUCs of 0.91 and 0.90 and MAEs of 1.87 dB and 1.84 dB, respectively. Models with frozen vision encoders showed reduced accuracy. Stratified analysis showed better glaucoma classification in older individuals and moderate-to-advanced cases. VF MD prediction was more accurate in younger individuals, with higher errors in advanced glaucoma. Conclusions: Fine-tuned VLMs demonstrated high performance in glaucoma detection and VF MD prediction, matching or exceeding specialized foundation models and traditional convolutional neural network (CNN)-based methods. Translational Relevance: This study highlights the potential of general-purpose AI models to be adapted for glaucoma care, enabling scalable decision support from OCT imaging.

Indexed as

GlaucomaOphthalmologyVisual FieldsAgedFemaleHumansMaleMiddle AgedOptic DiskROC CurveTomography, Optical Coherence

Identifiers

PMID41258693
PMCPMC12641456

What OpenQuestion holds

Textmetadata
LicenceCC BY-NC-ND
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.