Artificial Intelligence-Assisted Lesion-Based Urgent Referral Triage of Ultra-Widefield Retinal Images: A Multi-Reader Multi-Case Randomized Reader Study

Overview

his study evaluates the clinical utility of an artificial intelligence (AI)-assisted lesion-based urgent referral triage system for ultra-widefield (UWF) retinal images. Unlike disease-classification systems, the AI system identifies predefined vision-threatening retinal findings and generates lesion-level urgent referral recommendations. Participating ophthalmologists will evaluate UWF retinal images under randomized AI-assisted and unassisted conditions. The primary objective is to determine whether lesion-based AI assistance improves urgent referral triage performance compared with unaided image interpretation.

Ultra-widefield retinal imaging is increasingly used for retinal disease screening and referral triage. Many vision-threatening retinal abnormalities require timely identification and referral to retinal specialists. The AI system evaluated in this study is designed as a lesion-based triage tool rather than a disease-diagnosis system. The model identifies predefined urgent referral retinal findings and generates referral recommendations based on lesion-level evidence. Urgent referral findings include: * Retinal detachment * Untreated retinal tear or retinal hole * Vitreous hemorrhage * Pre-retinal hemorrhage * Subretinal hemorrhage * Retinal neovascularization * Optic disc neovascularization * Tractional fibrovascular membrane Treated retinal tears associated with laser barricade scars are classified as non-urgent referral findings. A total of 600 UWF retinal images acquired using Zeiss and Optos imaging systems will be included. Participating ophthalmologists will independently evaluate images in randomized AI-assisted and unassisted settings. The primary objective is to determine whether AI assistance improves lesion-based urgent referral triage accuracy.