Large language models (LLMs) show promise for tailored healthcare communication but face challenges in interpretability and multi-task integration particularly for domain-specific needs like myopia, and their real-world effectiveness as patient education tools has yet to be demonstrated. Here, we introduce ChatMyopia, an LLM-based AI agent designed to address text and image-based inquiries related to myopia. To achieve this, ChatMyopia integrates an image classification tool and a retrieval-augmented knowledge base built from literature, expert consensus, and clinical guidelines. Myopic maculopathy grading task, single question examination and human evaluations validated its ability to deliver personalized, accurate, and safe responses to myopia-related inquiries with high scalability and interpretability. In a randomized controlled trial (n=70, NCT06607822), ChatMyopia significantly improved patient satisfaction compared to traditional leaflets, enhancing patient education in accuracy, empathy, disease awareness, and patient-eyecare practitioner communication. These findings highlight ChatMyopia's potential as a valuable supplement to enhance patient education and improve satisfaction with medical services in primary eye care settings.
@article{arxiv.2507.19498,
title = {ChatMyopia: An AI Agent for Pre-consultation Education in Primary Eye Care Settings},
author = {Yue Wu and Xiaolan Chen and Weiyi Zhang and Shunming Liu and Wing Man Rita Sum and Xinyuan Wu and Xianwen Shang and Chea-su Kee and Mingguang He and Danli Shi},
journal= {arXiv preprint arXiv:2507.19498},
year = {2025}
}