Artificial intelligence-based smartphone application for skin cancer detection: a prospective diagnostic accuracy study
- 17 February 2026
- journal article
- Published by Oxford University Press (OUP) in British Journal of Dermatology
- Vol. 194 (6) , 1077-1086
Abstract
Background: Smartphone applications (‘apps’) that use artificial intelligence (AI) for skin cancer diagnosis may help with early detection. However, prospective studies assessing real-world performance are scarce. Objectives: To evaluate in an independent prospective study the diagnostic accuracy of a widely used skin cancer detection app and the effect of photographic conditions in a user-representative cohort of patients consulting for lesions of concern. Methods: Between 1 February 2021 and 30 June 2023, participants presenting at an early-access consultation with a lesion of concern were consecutively enrolled. Following dermatological assessment, each lesion was photographed using the app. The app’s convolutional neural network (CNN) generates a binary risk output and advice. A teledermatology review was performed in a subset of cases. The diagnostic accuracy of the CNN combined with teledermatology review was compared with final clinical or histopathological diagnosis. Performance was tested under different photographic conditions (angle, lighting, user) and with different smartphone models. The trial was registered with ClinicalTrials.gov (NCT05246163). Results: A total of 1458 participants with 1904 lesions of concern were included. Of these, 185 (9.7%) were skin cancers, with 32 melanomas. Image capture was unsuccessful in 16.6% of lesions (n = 317/1904), despite optimal conditions. For successfully captured lesions, the CNN achieved a sensitivity of 82.5% and specificity of 76.8% for skin cancer detection. In-app teledermatology review was available for 65.7% (n = 1042/1587) of images. Combined CNN and teledermatology review resulted in increased specificity (86.8%; P < 0.001), with a sensitivity of 75.3%. Overall sensitivity in melanocytic lesions was lower than in nonmelanocytic lesions (71.0% vs. 76.3%; P < 0.001), whereas specificity was higher (90.0% vs. 84.9%; P < 0.001). A substudy demonstrated low image-capture success in user hands (28.9%) and variation in diagnostic performance between smartphone models. Conclusions: This independent, prospective study evaluated diagnostic performance of a widely used skin cancer detection app in a user-representative cohort. The findings highlight the importance of independent clinical validation of AI-based healthcare tools in real-world settings.Keywords
Funding Information
- Fund for Scientific Research Flanders
- Stand Up To Cancer (FWO–KOTK G0B1122N)
This publication has 30 references indexed in Scilit:
- Mobile Health Apps: Guidance for Evaluation and Implementation by Healthcare WorkersJournal of Technology in Behavioral Science, 2024
- Artificial Intelligence in Skin Cancer Diagnosis: A Reality CheckJournal of Investigative Dermatology, 2023
- Diagnosis of suspicious pigmented lesions in specialist settings with artificial intelligenceThe Lancet Digital Health, 2023
- The USPSTF I Statement on Skin Cancer Screening—Not a Disappointment but an OpportunityJAMA Dermatology, 2023
- Artificial intelligence in mobile health for skin cancer diagnostics at home (AIM HIGH): a pilot feasibility studyeClinicalMedicine, 2023
- Screening for Skin CancerJAMA, 2023
- The value of measuring uncertainty in neural networks in dermoscopyJournal of the American Academy of Dermatology, 2022
- A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysisThe Lancet Digital Health, 2019
- Cost-effectiveness and Budget Effect Analysis of a Population-Based Skin Cancer ScreeningJAMA Dermatology, 2017
- Total-Body Examination vs Lesion-Directed Skin Cancer ScreeningJAMA Dermatology, 2016