TrialsgrambetaRCTs are beautiful

Zhang AI-OCT (DME)

2026

An AI-Based OCT System to Detect Diabetic Macular Edema: A Prospective Validation and Noninferiority Randomized Clinical Trial

In 276 patients referred with suspected diabetic macular oedema, an AI-based OCT report added to the referral decision reduced false-positive referrals compared with referral on the fundus-photograph screening report alone.

Result

False-positive DME referral rate (non-inferiority margin 20%)
Absolute difference
45.0 points
NNT
3
Effect estimate

absolute difference-45.095% CI -58.2 to -31.9 · P < 0.001

Absolute difference and NNT are derived from the event rates.

Also reported: For non-inferiority). Sensitivity for DME referral 100.0% in both groups; specificity 86.5% vs 0.0%. Silent-mode validation (603 patients): sensitivity 98.8%, specificity 90.7%.

Original publication
Subtopic
Prioritisation & triage
Design
Prospective silent-mode validation + multicentre non-inferiority RCT, Hong Kong
Relevance
Important: one of several pillars.
Source
Zhang S, et al. JAMA. 2026;336(3):215-223.doi 10.1001/jama.2026.7025

Discussion & critique

A model of stepwise evaluation: silent-mode validation first, then a randomised trial, showing that an AI-OCT second-stage screen can cut unnecessary specialist referrals for DME substantially without missing a case. The trial is small, drawn from a single screening programme, and because every participant was ultimately seen by a specialist it measures referral accuracy rather than downstream visual outcomes.