An estimated 3 billion people lack access to dermatological care globally. Artificial
intelligence (AI) may aid in triaging skin diseases and identifying malignancies. However …

Machine learning (ML) systems often exhibit unexpectedly poor behavior when they are
deployed in real-world domains. We identify underspecification in ML pipelines as a key …

Spitz tumors represent a distinct subtype of melanocytic lesions with characteristic
histopathologic features, some of which are overlapping with melanoma. More common in …

Machine learning has traditionally operated in a space where data and labels are assumed
to be anchored in objective truths. Unfortunately, much evidence suggests that the" …

How does the accuracy of deep neural network models trained to classify clinical images of
skin conditions vary across skin color? While recent studies demonstrate computer vision …

Although advances in deep learning systems for image-based medical diagnosis
demonstrate their potential to augment clinical decision-making, the effectiveness of …

While artificial intelligence (AI) holds promise for supporting healthcare providers and
improving the accuracy of medical diagnoses, a lack of transparency in the composition of …

Images depicting dark skin tones are significantly underrepresented in the educational
materials used to teach primary care physicians and dermatologists to recognize skin …

Clinical notes are becoming an increasingly important data source for machine learning
(ML) applications in healthcare. Prior research has shown that deploying ML models can …

Dermatologists of colour have long championed skin of colour representation in education
and workforce diversity. 1 For health equity, we must reconsider even fundamental and …