This prospective multicenter study assessed the diagnostic accuracy of the ADAE algorithm, an open-source ensemble algorithm, for melanoma detection. The study compared ADAE's performance to that of dermatologists on a heterogeneous test set from eight hospitals, using four different camera setups and including rare melanoma subtypes. ADAE demonstrated higher balanced accuracy and sensitivity than dermatologists, though with lower specificity. The results suggest AI could support dermatologists, particularly in diagnosing challenging cases.
Publisher
Nature Portfolio
Published On
Sep 11, 2024
Authors
Tags
ADAE algorithm
melanoma detection
diagnostic accuracy
AI support
dermatologists
sensitivity
specificity
Related Publications
Explore these studies to deepen your understanding of the subject.
