AI-Augmented Fundus Disease Screening by Non-Ophthalmologist Physicians: A Paired Before-After Study

Screening for retinal disease is increasingly performed by general practitioners and other non-ophthalmologist clinicians in primary care, especially where access to ophthalmology is limited and diagnostic accuracy may be suboptimal. To investigate the role of an automated fundus-interpretation support solution in improving general physicians' screening accuracy and referral decisions, we conducted a paired before-after study evaluating an AI-based decision support tool. Four non-ophthalmologists who have been involved in screen fundus images in clinical practice reviewed 500 de-identified color fundus photographs twice-first unaided and, after a washout period, with AI assistance. With AI support, diagnostic accuracy improved significantly from 82.8% to 91.1% (p < 0.0001), with the greatest benefit observed in glaucoma-suspect and multi-pathology cases. Clinicians retained final diagnostic authority, and a favorable safety profile was observed. These results demonstrate that AI-assisted diagnosis aid can meaningfully augment non-ophthalmologist screening and referral decision-making in real-world primary care, while underscoring the need for broader validation and implementation studies.