.png){kind=icon}
.png){kind=icon}
Return
An integrated language-vision foundation model for conversational diagnostics and triaging in primary eye care
.png){kind=icon}
OA
AI
DOI：10.1016/j.xcrm.2025.102476.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Meta-EyeFM router is 96.8% accurate in directing user queries for evaluation • Meta-EyeFM detects and differentiates ocular diseases with AUCs ≥91.2% and ≥82% • Meta-EyeFM outperforms Gemini-1.5 and GPT-4o in disease detection by 11%–43% • Meta-EyeFM generally outperforms clinician assessors, especially for glaucoma
Keywords:
ophthalmology
diagnostic decision support tool
foundation model
vision language model
large language model
artificial intelligence
deep learning
self-supervised learning model
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
10.6
Papers:
2.2K
Citations:
8.9K
Organization
No organization information available