Post

New research · Ophthalmology
European journal of ophthalmology · 5d
Cross-sectionalEuropean journal of ophthalmology · 2026

Smartphone-based offline AI for multi-disease retinal screening: Real-world accuracy.

Aditya Kelkar, Jai Kelkar, Yash Garg … Sabyasachi Sengupta
Read paper
OphthalmologyCross-sectional

Smartphone AI detected any retinal disease with very high sensitivity in real-world screening.

Smartphone-based offline AI for multi-disease retinal screening: Real-world accuracy.

Aditya Kelkar … Sabyasachi Sengupta
European journal of ophthalmology · 2026
Purpose

To evaluate the diagnostic accuracy of a multi-disease offline artificial intelligence system (Medios-AI, MAI), integrated into a smartphone-based fundus camera, for simultaneous screening of diabetic retinopathy (diabetic retinopathy), glaucoma, and age-related macular degeneration (AMD) in a real-world setting.

Methods

In this prospective cross-sectional study, 193 adults (371 eyes) aged ≥18 years with diabetic retinopathy, glaucoma, AMD, or normal fundus were enrolled between May and December 2024.

n = 371 eyes
Results

correctly flagged nearly all eyes that truly had retinal disease

99.3%
Sensitivity
95.7%
Specificity
More results

For glaucoma (n = 109), sensitivity was 98.2% (95% CI: 94-100), specificity 99.0% (95% CI: 97-100), AUROC 0.99.

For AMD (n = 56), sensitivity was 88.9% (95% CI: 77-96), specificity 97.5% (95% CI: 95-99), AUROC 0.93.

For diabetic retinopathy (n = 78), sensitivity was 84.6% (95% CI: 75-92), specificity 99.0% (95% CI: 97-100), AUROC 0.92.

More results

Agreement on vertical cup-to-disc ratio between AI and graders ranged from -0.1 to +0.1, with intergrader ICC of 0.97 (P < 0.001 for all comparisons).

“
Conclusion

ConclusionsMAI demonstrated significant diagnostic accuracy for diabetic retinopathy, glaucoma, and AMD using an offline, smartphone-based platform, supporting scalable, point-of-care retinal screening in resource-limited settings.

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