Images depicting dark skin tones are significantly underrepresented in educational materials used to teach primary care physicians and dermatologists to recognize skin diseases. This could contribute to disparities in skin disease diagnosis across different racial groups. The Skin Tone Analysis for Representation in EDucational materials (STAR-ED) framework assesses skin tone representation in medical education materials using machine learning. STAR-ED extracts text, images, and tables; identifies images containing skin; segments skin regions; and estimates skin tone using machine learning. Results show strong performance in detecting skin images (0.96 ± 0.02 AUROC and 0.90 ± 0.06 F1 score) and classifying skin tones (0.87 ± 0.01 AUROC and 0.91 ± 0.00 F1 score). STAR-ED quantifies the imbalanced representation of skin tones in four medical textbooks: brown and black skin tones constitute only 10.5% of all skin images.

Girmaw Abebe Tadesse, Celia Cintas, Kush R. Varshney, Peter Staar, Chinyere Agunwa, Skyler Speakman, Justin Jia, Elizabeth E. Bailey, Ademide Adelekun, Jules B. Lipoff, Ginikanwa Onyekaba, Jenna C. Lester, Veronica Rotemberg, James Zou, Roxana Daneshjou