LEME: open large language models for ophthalmology with advanced reasoning and clinical validation

Large language models (LLMs) offer potential to alleviate the growing public health burden of eye disease; however, few models have been tailored for ophthalmology or evaluated against clinically relevant benchmarks and real-world workflows. Here, we present LEME, a suite of open-weight LLMs for ophthalmology developed via a two-stage framework: instruction tuning on 211,149 examples curated from authoritative sources, and reinforcement learning with 29,747 preference-labeled examples to enhance clinical reasoning and informativeness. LEME was evaluated under zero-shot settings using five curated benchmarks, covering question answering and patient-physician consultation. LEME outperformed all seven baselines (all p < 0.004), notably exceeding GPT-4o by 3.32% in average ROUGE-L. Furthermore, LEME was assessed on three downstream tasks using deidentified patient data. In answering patient queries, LEME received the highest overall ratings from attending clinicians; its completeness rating even surpassed that of the expert-written answers ( p = 0.015). For visual acuity extraction from clinical notes, LEME achieved the highest F1 scores, outperforming LLaMA-3 70B by 14.1% and Eye-LLaMA by 59.0%. Finally, in assessment and treatment plan generation, LEME achieved ratings approaching those of attending clinicians, demonstrating promise for ophthalmic decision support. All models, datasets, and code are made open to support further development and validation.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2026-09-25
DOI
https://doi.org/10.1038/s41746-026-03104-4
Citations
1
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

LEME: open large language models for ophthalmology with advanced reasoning and clinical validation

Dianbo Liu, Jimin Huang, Aidan Gilson, Maxwell Singer et al.
1 citations
npj Digital Medicine
Artificial Intelligence in Healthcare and Education
article

LEME: open large language models for ophthalmology with advanced reasoning and clinical validation

Dianbo Liu, Jimin Huang, Aidan Gilson, Maxwell Singer, Ron Afshari Adelman, Krithi Pushpanathan, Sahana Srinivasan, Lucila Ohno‐Machado, Yih Chung Tham, Erping Long, Qingyu Chen, Qianqian Xie, Hua Dong Xu, X. C. Ai, Peixing Wan, Hyunjae Kim, Luciano V. Del Priore
article en
1 citations

Abstract

Large language models (LLMs) offer potential to alleviate the growing public health burden of eye disease; however, few models have been tailored for ophthalmology or evaluated against clinically relevant benchmarks and real-world workflows. Here, we present LEME, a suite of open-weight LLMs for ophthalmology developed via a two-stage framework: instruction tuning on 211,149 examples curated from authoritative sources, and reinforcement learning with 29,747 preference-labeled examples to enhance clinical reasoning and informativeness. LEME was evaluated under zero-shot settings using five curated benchmarks, covering question answering and patient-physician consultation. LEME outperformed all seven baselines (all p < 0.004), notably exceeding GPT-4o by 3.32% in average ROUGE-L. Furthermore, LEME was assessed on three downstream tasks using deidentified patient data. In answering patient queries, LEME received the highest overall ratings from attending clinicians; its completeness rating even surpassed that of the expert-written answers ( p = 0.015). For visual acuity extraction from clinical notes, LEME achieved the highest F1 scores, outperforming LLaMA-3 70B by 14.1% and Eye-LLaMA by 59.0%. Finally, in assessment and treatment plan generation, LEME achieved ratings approaching those of attending clinicians, demonstrating promise for ophthalmic decision support. All models, datasets, and code are made open to support further development and validation.

npj Digital Medicine
Massachusetts Eye and Ear Infirmary (US), National Institutes of Health (US), Harvard University (US), University of Liverpool (GB), National University of Singapore (SG), Korea University (KR), Singapore National Eye Center (SG), Yale University (US), Singapore Eye Research Institute (SG), National Cancer Institute (US), National University Hospital (SG), Center for Cancer Research (US), Moorfields Eye Hospital (GB), University College London (GB), The University of Texas Health Science Center at Houston (US), Stanford University (US)
Cancer Prevention and Research Institute of Texas, National Institute for Health and Care Excellence, National Institutes of Health
Openalex Percentile: Top 100%
Artificial Intelligence in Healthcare and Education
DOIOpen Access PDFOpenAlex
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.