Currently submitted to: JMIR Dermatology
Date Submitted: Oct 8, 2026
Open Peer Review Period: Oct 16, 2026 - Dec 11, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Artificial Intelligence in Skin Cancer Detection by Primary Care Physicians: A Scoping Review
ABSTRACT
Background:
The prevalence of skin cancer is rising globally. Primary care physicians (PCPs) play a crucial role in diagnosing these cancers, but their accuracy varies. Artificial intelligence (AI) tools may assist PCPs, but it is unclear how effective modern AI tools can be. Previous reviews are out-of-date given the rapid AI advancements.
Objective:
This study aims to characterize the evidence regarding the diagnostic performance of current AI technologies for skin cancer detection for PCPs.
Methods:
A scoping review was conducted using the electronic databases MEDLINE, Embase, Scopus, and Web of Science. Included articles were published in English after year 2000 capturing data on study features (i.e., skin cancer types examined, types of PCPs, AI techniques used), AI use paradigm (collaborative with PCPs or comparative against humans), diagnostic performance (i.e., accuracy, sensitivity, specificity, negative predictive value, and positive predictive value), and secondary concerns (i.e., validation approach, cost effectiveness, and environmental impact).
Results:
Of the 18 studies selected, most involved general practitioners, applied a comparative paradigm, and used convolutional neural networks. AI tools generally showed good accuracy in detecting skin cancer (6.7% to 59.9% above PCPs), performed at least as well as PCPs independently, and raised PCPs’ diagnostic performance. However, AI tools’ specificity was variable, at times lower than PCPs and even decreasing PCPs’ performance. 11 studies validated their AI tools with external clinical data, and none discussed cost effectiveness or environmental concerns.
Conclusions:
AI may potentially support PCPs in screening skin cancer, whether independently or to support PCPs. However, their worrisome association with lower specificity requires technical improvement and potential expert review. The low validation rate and non-existent discussion on economic or environmental challenges should caution against broad implementation.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.