AI-based clinician decision support system for diagnosis of inherited retinal diseases: a multicenter, randomized trial
In brief
AI support boosts correct genetic diagnosis to 88.5% versus 67%
In a randomized trial of 295 patients with suspected inherited retinal disease, clinicians using the Retina4IRD AI tool achieved correct top-5 genotype identification in 88.5% of cases, compared with 67.3% without AI. The tool also improved top-1 accuracy (38% vs 22%) and downstream management scores, suggesting it can streamline diagnosis before genetic testing, though broader validation is needed.
- Journal
- Nature medicine (Q1)
- Published
- 24 July 2026
- Study design
- Randomized controlled trial
- Evidence level
- Level 1, High (CEBM 1b)
- Authors
- Huixun Jia, Bo Qian, Yanlin Qu, Jinyuan Wang, Jieqiong Chen, Tong Li, et al.
- PMID
- 42498742
- DOI
- 10.1038/s41591-026-04545-w
Why clinicians should know about it
- Picked for Ophthalmology (top studies of the week, 26 July 2026): Retina4IRD improves genetic diagnostic accuracy
Abstract
The accurate and timely diagnosis of inherited retinal diseases (IRDs) represents an unmet clinical need in ophthalmology, as the current pathways rely on resource-intensive phenotyping, multidisciplinary expertise and genetic testing. Here we developed Retina4IRD, an artificial intelligence (AI)-based clinician decision support system (CDSS) that predicts 17 genotype categories from retina images. Retina4IRD uses a Vision Transformer model pretrained with RETFound. We then trained and validated Retina4IRD using multimodal data with color fundus photographs and optical coherence tomography scans from 1,843 genetically confirmed patients (3,376 eyes) across China, South Korea and Poland. The top-5 prediction accuracy was 0.904 (95% confidence interval (CI): 0.896-0.912) and 0.856 (95% CI: 0.850-0.863) for internal and external validation, respectively. We conducted a randomized controlled trial with 300 participants with suspected IRD randomized 1:1 to either Retina4IRD-assisted specialist arm or specialist-only arm. Of these, 295 participants (median age 33 years, 114 (38.6%) females) with available next-generation sequencing reports were included in the final analysis. The primary outcome was met: top-5 genetic accuracy was significantly higher in the Retina4IRD-assisted specialist arm versus the specialist-only arm (88.5% versus 67.3%, P < 0.001). For secondary endpoints, top-1 to top-4 accuracies all favored the Retina4IRD-assisted specialist arm, with top-1 accuracy of 37.8% versus 22.4% and top-4 accuracy of 81.8% versus 53.1%, respectively. Post hoc analyses demonstrated that, with Retina4IRD assistance, clinicians made better management decisions, and the composite downstream management score indicated significantly higher scores relative to the control group (37.7 versus 28.5, P < 0.001). Our study shows that Retina4IRD is a CDSS tool prior to genetic testing and aligns with clinical workflow for patients with suspected IRDs. ClinicalTrials.gov identifier: NCT06839170 .
Abstract as published, via PubMed.
For healthcare professionals. The summary is generated by AI from the published abstract, and the evidence level is assigned automatically from the study design on the Oxford CEBM hierarchy. Neither is medical advice. Read the full paper before changing practice.