Guideline-grounded retrieval-augmented generation for ophthalmic clinical decision support

TL;DR

This paper introduces Oph-Guid-RAG, a multimodal retrieval-augmented generation system for ophthalmic clinical decision support that improves accuracy and robustness by integrating visual evidence retrieval with controllable reasoning.

Contribution

The work presents a novel multimodal RAG system that directly retrieves guideline page images and employs a controllable retrieval framework for ophthalmology decision support.

Findings

Improves accuracy from 0.5956 to 0.6576 on challenging cases.

Achieves 30% improvement over GPT-5.2 in overall score.

Reranking, routing, and retrieval design are critical for performance.

Abstract

In this work, we propose Oph-Guid-RAG, a multimodal visual RAG system for ophthalmology clinical question answering and decision support. We treat each guideline page as an independent evidence unit and directly retrieve page images, preserving tables, flowcharts, and layout information. We further design a controllable retrieval framework with routing and filtering, which selectively introduces external evidence and reduces noise. The system integrates query decomposition, query rewriting, retrieval, reranking, and multimodal reasoning, and provides traceable outputs with guideline page references. We evaluate our method on HealthBench using a doctor-based scoring protocol. On the hard subset, our approach improves the overall score from 0.2969 to 0.3861 (+0.0892, +30.0%) compared to GPT-5.2, and achieves higher accuracy, improving from 0.5956 to 0.6576 (+0.0620, +10.4%). Compared to GPT-5.4, our method achieves a larger accuracy gain of +0.1289 (+24.4%). These results show that our method is more effective on challenging cases that require precise, evidence-based reasoning. Ablation studies further show that reranking, routing, and retrieval design are critical for stable performance, especially under difficult settings. Overall, we show how combining visionbased retrieval with controllable reasoning can improve evidence grounding and robustness in clinical AI applications,while pointing out that further work is needed to be more complete.