ArticleBMJ open ophthalmology2025
Can off-the-shelf visual large language models detect and diagnose ocular diseases from retinal photographs?
Article in BMJ open ophthalmology, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 3 papers.
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.
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.
Who cites it
3 citing papers in PubMed.
- BEnchmarking Large Language Models for Ophthalmology (BELO): An Expert-Curated Data Set and Evaluation Framework for Knowledge and Reasoning.Ophthalmology science · 2026Article
- Assessing large language models as assistive tools in selecting first trial lens parameters for orthokeratology.Frontiers in medicine · 2026Article
- Accuracy and Reproducibility of Different Artificial Intelligence Chatbots' Responses to Patient-Based Vitreoretinal Questions: A Comparative Study.Clinical ophthalmology (Auckland, N.Z.) · 2026Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
13 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
backgroundThe advent of generative artificial intelligence has led to the emergence of multiple vision large language models (VLLMs). This study aimed to evaluate the capabilities of commonly available VLLMs, such as OpenAI's GPT-4V and Google's Gemini, in detecting and diagnosing ocular diseases from retinal images. METHODS AND ANALYSIS: From the Singapore Epidemiology of Eye Diseases (SEED) study, we selected 44 representative retinal photographs, including 10 healthy and 34 representing six eye diseases (age-related macular degeneration, diabetic retinopathy, glaucoma, visually significant cataract, myopic macular degeneration and retinal vein occlusion). OpenAI's GPT-4V (both default and data analyst modes) and Google Gemini were prompted with each image to determine if the retina was normal or abnormal and to provide diagnostic descriptions if deemed abnormal. The outputs from the VLLMs were evaluated for accuracy by three attending-level ophthalmologists using a three-point scale (poor, borderline, good).
resultsGPT-4V default mode demonstrated the highest detection rate, correctly identifying 33 out of 34 detected correctly (97.1%), outperforming its data analyst mode (61.8%) and Google Gemini (41.2%). Despite the relatively high detection rates, the quality of diagnostic descriptions was generally suboptimal-with only 21.2% of GPT-4V's (default) responses, 4.8% of GPT-4V's (data analyst) responses and 28.6% for Google Gemini's responses rated as good.
conclusionsAlthough GPT-4V default mode showed generally high sensitivity in abnormality detection, all evaluated VLLMs were inadequate in providing accurate diagnoses for ocular diseases. These findings emphasise the need for domain-customised VLLMs and suggest the continued need for human oversight in clinical ophthalmology.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
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.