AI-assisted nurse-led skin cancer screening in a teledermoscopy framework: a multi-site evaluation with one million lesions
- 1The University of Melbourne
Abstract
Nurse-led skin cancer screening extends specialist reach but depends on the nurse selecting which lesions to forward for diagnosis, and performance varies with experience. We evaluated whether real-time decision support using artificial intelligence (AI) improves malignancy detection in routine nurse-led teledermoscopy screening across MoleMap clinics in New Zealand and Australia (January 2024-July 2025). In this real-world study, clinics using AI decision support were compared with standard clinics. Nurses examined patients, captured dermoscopic images, and forwarded selected lesions to teledermatologists, who provided the reference diagnosis. The analytic cohort comprised 1,102,382 lesions from 98,422 patients across 577 sites. AI-assisted screening was associated with a higher malignancy detection rate than standard screening (25.5 vs 15.7 malignancies per 1,000 lesions; odds ratio adjusted for nurse experience 1.73, 95% CI 1.68-1.77), a finding consistent across all nurse-experience tiers and the three major malignant subtypes. AI assistance was also associated with a shift in recommended management: 21 additional intervention recommendations and 13 additional safety-netting recommendations (self-monitoring, short-term follow-up, or specialist referral) per 1,000 lesions, approximately balanced by 34 fewer no-action recommendations. The reference standard was teledermatologist diagnosis and allocation was not randomised; findings are therefore associational and require prospective, outcome-based confirmation.
Related
- Screening and evaluation of medicine food homology herbal combinations for ameliorating chemotherapy induced ovarian aging under an integrated multi-strategy framework
- Retrospective Review of Suspected Melanoma Diagnoses Made by a Single-Centre Teledermoscopy Service in New Zealand.
- Sex-related refractive disparities in school-aged children: a population-based cross-sectional study of 4.47 million screening records
- Evaluation of linkage between health, education and social care administrative data for 21 million children in England
- Initial screening positivity for suspected scoliosis and machine learning-assisted risk prioritization: a school-based cross-sectional study in Wuhai, Inner Mongolia, China
BibTeX
@misc{shaik2026aiassisted,
title = {{AI-assisted nurse-led skin cancer screening in a teledermoscopy framework: a multi-site evaluation with one million lesions}},
author = {N. E. K. Shaik and N. Desai and K. Wang and L. Wild and A. G. Dunn and A. Oakley and M. Palaniswami and J. Vendrig},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.01.26364543},
url = {https://www.medrxiv.org/content/10.64898/2026.10.01.26364543v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - AI-assisted nurse-led skin cancer screening in a teledermoscopy framework: a multi-site evaluation with one million lesions
AU - N. E. K. Shaik
AU - N. Desai
AU - K. Wang
AU - L. Wild
AU - A. G. Dunn
AU - A. Oakley
AU - M. Palaniswami
AU - J. Vendrig
PY - 2026
DA - 2026/10/01
PB - medRxiv
DO - 10.64898/2026.10.01.26364543
UR - https://www.medrxiv.org/content/10.64898/2026.10.01.26364543v1
AB - Nurse-led skin cancer screening extends specialist reach but depends on the nurse selecting which lesions to forward for diagnosis, and performance varies with experience. We evaluated whether real-time decision support using artificial intelligence (AI) improves malignancy detection in routine nurse-led teledermoscopy screening across MoleMap clinics in New Zealand and Australia (January 2024-July 2025). In this real-world study, clinics using AI decision support were compared with standard clinics. Nurses examined patients, captured dermoscopic images, and forwarded selected lesions to teledermatologists, who provided the reference diagnosis. The analytic cohort comprised 1,102,382 lesions from 98,422 patients across 577 sites. AI-assisted screening was associated with a higher malignancy detection rate than standard screening (25.5 vs 15.7 malignancies per 1,000 lesions; odds ratio adjusted for nurse experience 1.73, 95% CI 1.68-1.77), a finding consistent across all nurse-experience tiers and the three major malignant subtypes. AI assistance was also associated with a shift in recommended management: 21 additional intervention recommendations and 13 additional safety-netting recommendations (self-monitoring, short-term follow-up, or specialist referral) per 1,000 lesions, approximately balanced by 34 fewer no-action recommendations. The reference standard was teledermatologist diagnosis and allocation was not randomised; findings are therefore associational and require prospective, outcome-based confirmation.
ER -