Limits of Artificial Intelligence Models for Skin Cancer Diagnosis in Realistic Settings
JAMA Dermatology · 01.07.2026 · 162 (7) · 701
DOI: 10.1001/jamadermatol.2026.1492 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift JAMA Dermatology, erschienen am 01.07.2026. Verfasst von Julien Anriot und 10 weiteren Autor:innen. Beteiligte Einrichtung: Claude Bernard University Lyon 1, Lyon, France. Hauptthemen laut MEDLINE: Skin Neoplasms, Artificial Intelligence. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Importance Artificial intelligence (AI) systems for skin cancer detection perform well in controlled settings but frequently underperform in everyday clinical practice, raising critical questions about their readiness for deployment.
Objective
To compare the diagnostic accuracy of AI algorithms vs human evaluators across varying expertise levels for skin lesion diagnosis, including rare and atypical cases, in a realistic clinical context. Design, Setting, and Participants This multi-institutional diagnostic study compared diagnostic performance among AI models and physician readers with varying dermatological expertise, ranging from less than 1 year to more than 10 years of experience. A dataset of dermatological images representing everyday clinical scenarios was used and contained 1117 cases, including clinical and dermoscopic images with associated metadata. Study inclusion spanned from March 16, 2023, to August 1, 2025. Exposures Three AI algorithms: a first-generation convolutional neural network (CNN) and 2 foundation models (PanDerm unimodal and multimodal). Human readers evaluated 100 stratified, random cases drawn from the same dataset. Main Outcomes and Measures The primary outcome was reader-level multiclass diagnostic accuracy for skin lesion classification. Secondary outcomes were binary benign vs malignant sensitivity, specificity, and balanced accuracy. Performance was compared between AI algorithms and human readers stratified by experience level.
Results
A total of 652 physicians (median [IQR] age, 33 [29-37] years; 559 [85.7%] female) contributed to 1092 test iterations. All human readers outperformed the CNN (mean [SD] accuracy, 65.9% [10.5%] vs 56.7% [3.9%]; difference, 9.2 percentage points [pp]; 95% CI, −9.8 to 8.5 pp; P < .001). Unimodal accuracy exceeded readers with less than 3 years of experience (mean [SD] accuracy, 72.2% [3.5%] vs 68.2% [7.6%]; difference, 4.0 pp; 95% CI, 3.2-4.9 pp; P < .001). With a mean (SD) accuracy of 74.2% (5.7%), experts with more than 10 years of experience achieved the highest multiclass diagnostic accuracy, outperforming all AI models on this primary end point, which included 56.7% (3.9%) for CNN, 72.2% (3.5%) for the unimodal model, and 66.3% (3.8%) for the multimodal model. Conclusions and Relevance In this diagnostic study, a modern foundation model surpassed readers with less than 3 years of experience on accuracy of skin lesion diagnosis and matched those with 3 to 10 years of experience but remained inferior to experts with more than 10 years of experience, highlighting both the promise and current limitations of AI in dermatologic diagnosis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Claude Bernard University Lyon 1, Lyon, France.
- Centre Léon Berard, Lyon, France.
- AIM for Health Lab, Faculty of Information Technology, Monash University, Melbourne, Victoria, Australia.
- Faculty of Engineering, Monash University, Melbourne, Victoria, Australia.
- Department of Dermatology, Medical University of Vienna, Vienna, Austria.
- Cancer Research Center of Lyon, Lyon, France.
Zitieren
APA
Anriot, J., Yan, S., Coste, C., Tschandl, P., Verlingue, L., Andremasse, C., Amini-Adle, M., Perrot, J. L., Ge, Z., Kittler, H., & Thomas, L. (2026). Limits of Artificial Intelligence Models for Skin Cancer Diagnosis in Realistic Settings. JAMA Dermatology, 162(7), 701. https://doi.org/10.1001/jamadermatol.2026.1492
Vancouver
Anriot J, Yan S, Coste C, Tschandl P, Verlingue L, Andremasse C, et al. Limits of Artificial Intelligence Models for Skin Cancer Diagnosis in Realistic Settings. JAMA Dermatology. 2026;162(7):701. doi:10.1001/jamadermatol.2026.1492
BibTeX
@article{Anriot2026,
author = {Anriot, Julien and Yan, Siyuan and Coste, Clio and Tschandl, Philipp and Verlingue, Loic and Andremasse, Camille and Amini-Adle, Mona and Perrot, Jean Luc and Ge, Zongyuan and Kittler, Harald and Thomas, Luc},
title = {Limits of Artificial Intelligence Models for Skin Cancer Diagnosis in Realistic Settings},
journal = {JAMA Dermatology},
year = {2026},
volume = {162},
number = {7},
pages = {701},
doi = {10.1001/jamadermatol.2026.1492}
}
EUVIMED