Post

New research · AI in Medicine
Nature medicine · 6d
AI / informaticsNature medicine · 2026

AI-based clinician decision support system for diagnosis of inherited retinal diseases: a multicenter, randomized trial.

Huixun Jia, Bo Qian, Yanlin Qu … Xiaodong Sun
Read paper
AI in MedicineAI / informatics

Retina4IRD assistance improved top-5 genetic diagnostic accuracy for suspected inherited retinal diseases.

AI-based clinician decision support system for diagnosis of inherited retinal diseases: a multicenter, randomized trial.

Huixun Jia … Xiaodong Sun
Nature medicine · 2026
Background

The accurate and timely diagnosis of inherited retinal diseases (inherited retinal diseases) represents an unmet clinical need in ophthalmology, as the current pathways rely on resource-intensive phenotyping, multidisciplinary expertise and genetic testing.

Methods

We conducted a randomized controlled trial with 300 participants with suspected inherited retinal diseases randomized 1:1 to either Retina4IRD-assisted specialist arm or specialist-only arm.

n = 3,376 eyes
Results

Top-5 genetic diagnoses were more accurate with Retina4IRD-assisted specialists.

88.5%
Retina4IRD-assisted sp
67.3%
specialist-only arm
More results

Retina4IRD uses a Vision Transformer model pretrained with RETFound.

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.

More results

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.

“
Conclusion

Our study shows that Retina4IRD is a clinician decision support system tool prior to genetic testing and aligns with clinical workflow for patients with suspected inherited retinal diseases.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
AI / Informatics
0·962 for OCT
MerMED-FM was very accurate at diagnosing diseases using eye scans
AI / Informatics
0.98
Artificial intelligence's eyelid-height measurements matched doctors' manual measurements almost perfectly
AI / Informatics
92.1%
combining eye scans and photos correctly told benign from cancerous lesions apart nearly every time
Cohort Study
28.6%
recurred locally in more than 1 in 4 patients over years of follow-up
Cohort Study
-0.395
excision group's post-op eyelid fullness score was lower - greater improvement
Cohort Study
86.7%
of infants probed after 12 months still had unresolved tear duct blockage
Observational
16%
eyelid tissue in rosacea patients showed less of this key repair-signaling protein inside cell nuclei
Cohort Study
25%
about 1 in 4 treated cases had symptoms return after improving