Helping specialists see urgency.
Researchers demonstrated deep-learning diagnosis and referral recommendations from retinal scans.
- Maturity
- Demonstrated, stage 3 of 4
- Support
- 1 source · paper
- Scale
- ● ≈ 24 mm · an eye
- Evidence detail
- How we know ↓
Specialists must identify which eye conditions need urgent attention.
Clinicians interpret detailed optical coherence tomography scans.
A two-stage model mapped scan features to diagnoses and referral suggestions.
What was shown, and what wasn’t
Shown
The system demonstrated strong retrospective referral performance.
Not shown · limits
- Retrospective performance does not establish routine clinical safety or benefit.
Bright editorial interpretation
It suggested a possible tool for supporting specialist triage.
Still open
Evaluate clinical workflows and outcomes prospectively.
How we know1 source · checked 2026-09-05 · no corrections
Original sources
Institutions: Moorfields Eye Hospital & DeepMind
- Maturity
- Demonstrated
- Source published
- 2018-08-13
- Last source review
- 2026-09-05
- Editorial method
- Original source check
- Place / relevance
- London, United Kingdom · institution-location
Bright compared this account with the linked original and supporting sources and kept reported, budgeted, projected, and observed claims distinct. Bright did not independently audit the underlying records.
Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.
Revision & correction history
No corrections recorded.
Keep exploring
Explore the shared question in another setting. These connections do not imply replication.