Abstract

Images depicting dark skin tones are significantly underrepresented in the 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. Previously, domain experts have manually assessed textbooks to estimate the diversity in skin images. Manual assessment does not scale to many educational materials and introduces human errors. To automate this process, we present the Skin Tone Analysis for Representation in EDucational materials (STAR-ED) framework, which assesses skin tone representation in medical education materials using machine learning. Given a document (e.g., a textbook in .pdf), STAR-ED applies content parsing to extract text, images, and table entities in a structured format. Next, it identifies images containing skin, segments the skin-containing portions of those images, and estimates the skin tone using machine learning. STAR-ED was developed using the Fitzpatrick17k dataset. We then externally tested STAR-ED on four commonly used medical textbooks. 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 (Fitzpatrick V-VI) images constitute only 10.5% of all skin images. We envision this technology as a tool for medical educators, publishers, and practitioners to assess skin tone diversity in their educational materials.

Details

Title
Skin Tone Analysis for Representation in Educational Materials (STAR-ED) using machine learning
Author
Tadesse, Girmaw Abebe 1 ; Cintas, Celia 1 ; Varshney, Kush R. 2 ; Staar, Peter 3 ; Agunwa, Chinyere 2 ; Speakman, Skyler 4 ; Jia, Justin 5 ; Bailey, Elizabeth E. 5 ; Adelekun, Ademide 6 ; Lipoff, Jules B. 7 ; Onyekaba, Ginikanwa 6 ; Lester, Jenna C. 8 ; Rotemberg, Veronica 9   VIAFID ORCID Logo  ; Zou, James 5   VIAFID ORCID Logo  ; Daneshjou, Roxana 5   VIAFID ORCID Logo 

 IBM Research – Africa, Nairobi, Kenya 
 IBM Research – T. J. Watson, New York, USA (GRID:grid.481554.9) (ISNI:0000 0001 2111 841X) 
 IBM Research – Europe, Zurich, Switzerland (GRID:grid.410387.9) 
 IBM Research – Africa, Nairobi, Kenya (GRID:grid.481554.9) 
 Stanford University, Stanford, USA (GRID:grid.168010.e) (ISNI:0000 0004 1936 8956) 
 University of Pennsylvania, Philadelphia, USA (GRID:grid.25879.31) (ISNI:0000 0004 1936 8972) 
 Temple Medical School, Department of Dermatology, Philadelphia, USA (GRID:grid.25879.31) 
 University of California San Francisco, San Franciscoa, USA (GRID:grid.266102.1) (ISNI:0000 0001 2297 6811) 
 Memorial Sloan-Kettering Cancer Center, New York, USA (GRID:grid.51462.34) (ISNI:0000 0001 2171 9952) 
Pages
151
Publication year
2023
Publication date
Dec 2023
Publisher
Nature Publishing Group
e-ISSN
23986352
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2852877840
Copyright
© The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.