receipt
Because of AI, people in Tanzania with referable diabetic retinopathy were about twice as likely to reach the eye clinic within 8 weeks: 35.9% against 18.2% with standard screening.
receipt
In a randomised trial across 24 hospital clinics in the Kilimanjaro and Arusha regions of Tanzania, diabetes patients screened with an AI system that gave a result and face-to-face counselling on the spot attended the central eye clinic more often than patients who heard their result by phone weeks later.
Sources
- primaryCleland et al., Artificial intelligence-supported diabetic retinopathy screening in Tanzania: a randomised controlled trial. Lancet Global Health 2026doi.org
- secondaryISRCTN18317152 trial registrationisrctn.com
Editor's notes
verify: the publication date is taken from the press coverage of the paper (September 2026); the printed PDF text carries no day. verify: dates are the enrolment period; follow-up ran 8 weeks beyond it. The paper's decimal points are printed as middle dots, and receipts copy them.
History
- Corrected: stated the disclosures the gate found in the paper (SELENA+ supplied free for academic use; authors' commercial fees and one author's equity), which held the entry; no value changed.
- Added by the backfill run.
Verification
- Drafted by
- Anthropic
claude-opus-5-5 - Verified by
- OpenAI
gpt-6.1-sol· pass - How sure
- Strict
- Record
- data/verifications/tanzania-ai-dr-screening-rct/2026-11-15.json · The randomized trial supports increased clinic attendance with the bundled AI screening pathway: 35.9% versus 18.2% within 8 weeks. It does not isolate AI's independent contribution or establish reduced sight loss.
Two models from different vendors read the primary source independently; this entry is published because they agreed on every receipt and every grade. The models grading an AI registry have an interest in the answer. Cross-vendor checking and the receipts on this page are how the registry handles that, not a claim to have removed it. How the gate works · Dispute this entry
Cite this entry
“Because of AI, people in Tanzania with referable diabetic retinopathy were about twice as likely to reach the eye clinic within 8 weeks: 35.9% against 18.2% with standard screening.” Because of AI, updated Nov 15, 2026. https://becauseofai.org/entry/tanzania-ai-dr-screening-rct@misc{becauseofai_tanzania_ai_dr_screening_rct,
title = {Because of AI, people in Tanzania with referable diabetic retinopathy were about twice as likely to reach the eye clinic within 8 weeks: 35.9% against 18.2% with standard screening.},
howpublished = {\url{https://becauseofai.org/entry/tanzania-ai-dr-screening-rct}},
note = {Because of AI registry, updated Nov 15, 2026},
year = {2026}
}