ChatMyopia : an AI agent for myopia-related consultation in primary eye care settings

Abstract

Large language models (LLMs) show promise for tailored healthcare communication but face challenges in interpretability and multi-task integration, particularly for domain-specific needs such as myopia, and their real-world effectiveness as patient education tools has yet to be demonstrated. Here, we introduce ChatMyopia, an LLM-based AI agent to address text- and image-based inquiries related to myopia. 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 accurate and safe responses with high scalability and interpretability. In a randomized controlled trial, it significantly improved patient satisfaction compared to traditional leaflets, enhancing patient education in accuracy, empathy, disease awareness, and communication with eye care practitioners. 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. Graphical abstract: [Figure not available: see fulltext.]