receipt
25.5 vs 15.7 malignancies per 1,000 lesionsAbstractAI-assisted nurse-led skin cancer screening in a teledermoscopy framework: a multi-site evaluation with one million lesions (medRxiv preprint) · medrxiv.org
Because of AI decision support, nurse-led teledermoscopy clinics in New Zealand and Australia forwarded lesions that were malignant at 25.5 per 1,000 against 15.7 per 1,000 at clinics without it, across 1,102,382 lesions.
receipt
25.5 vs 15.7 malignancies per 1,000 lesionsAbstractAI-assisted nurse-led skin cancer screening in a teledermoscopy framework: a multi-site evaluation with one million lesions (medRxiv preprint) · medrxiv.org
The analytic cohort comprised 1,102,382 lesions from 98,422 patients across 577 sitesAbstractAI-assisted nurse-led skin cancer screening in a teledermoscopy framework: a multi-site evaluation with one million lesions (medRxiv preprint) · medrxiv.org
In routine nurse-led skin cancer screening at MoleMap clinics, clinics using AI decision support were compared with standard clinics on how many of the lesions nurses forwarded were confirmed malignant by teledermatologists.
Sources
- primaryAI-assisted nurse-led skin cancer screening in a teledermoscopy framework: a multi-site evaluation with one million lesions (medRxiv preprint)medrxiv.org
Editor's notes
verify: only the abstract page of the preprint was read; the sections beyond the abstract were not printed by the reader. verify: the abstract does not say how clinics came to use the AI, so confounding by clinic cannot be ruled out.
History
- Added by the backfill run.
Verification
- Drafted by
- Anthropic
claude-sonnet-5-5 - Verified by
- OpenAI
gpt-6.1-sol· pass - How sure
- Speculative
- Source 0 could be read only in part (an abstract or a summary), not the full document.
- The achieved dates come from the abstract; the methods were not available.
- The two checkers disagreed on attribution: the drafter said bundled and the verifier said isolated. The entry shows the drafter's grade, bundled; treat that grade as unsettled.
- Record
- data/verifications/molemap-ai-nurse-teledermoscopy-malignancy-detection/2026-11-16.json · The supplied abstract supports all quoted numbers and dates and reports higher malignancy detection associated with AI-assisted screening in actual patients. It does not establish causality, fewer missed cancers, or improved patient outcomes; methods and full results were not supplied.
Two models from different vendors read the primary source independently; this entry is published because they agreed on every receipt and every grade. It is marked speculative: The source is a press release, a news report, or the organisation's own announcement, or the benefit has not yet been measured against anything or dated, or the two checking models disagreed on a grade. Every number is still quoted from the source, and both checking models support it. 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 decision support, nurse-led teledermoscopy clinics in New Zealand and Australia forwarded lesions that were malignant at 25.5 per 1,000 against 15.7 per 1,000 at clinics without it, across 1,102,382 lesions.” Because of AI, updated Nov 16, 2026. https://becauseofai.org/entry/molemap-ai-nurse-teledermoscopy-malignancy-detection@misc{becauseofai_molemap_ai_nurse_teledermoscopy_malignancy_detection,
title = {Because of AI decision support, nurse-led teledermoscopy clinics in New Zealand and Australia forwarded lesions that were malignant at 25.5 per 1,000 against 15.7 per 1,000 at clinics without it, across 1,102,382 lesions.},
howpublished = {\url{https://becauseofai.org/entry/molemap-ai-nurse-teledermoscopy-malignancy-detection}},
note = {Because of AI registry, updated Nov 16, 2026},
year = {2026}
}