Skin Tone Analysis for Representation in Educational Materials (STAR-ED) using machine learning
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, do...
| Główni autorzy: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Artykuł |
| Język: | English |
| Wydane: |
Nature Portfolio
2023-08-01
|
| Seria: | npj Digital Medicine |
| Dostęp online: | https://doi.org/10.1038/s41746-023-00881-0 |
| _version_ | 1827708142158348288 |
|---|---|
| author | 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 |
| author_facet | 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 |
| author_sort | Girmaw Abebe Tadesse |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T16:59:33Z |
| format | Article |
| id | doaj.art-0b3cc841ae2c48ca92f068d15d2a5ec8 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-10T16:59:33Z |
| publishDate | 2023-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-0b3cc841ae2c48ca92f068d15d2a5ec82023-11-20T11:01:01ZengNature Portfolionpj Digital Medicine2398-63522023-08-016111010.1038/s41746-023-00881-0Skin Tone Analysis for Representation in Educational Materials (STAR-ED) using machine learningGirmaw Abebe Tadesse0Celia Cintas1Kush R. Varshney2Peter Staar3Chinyere Agunwa4Skyler Speakman5Justin Jia6Elizabeth E. Bailey7Ademide Adelekun8Jules B. Lipoff9Ginikanwa Onyekaba10Jenna C. Lester11Veronica Rotemberg12James Zou13Roxana Daneshjou14IBM Research – AfricaIBM Research – AfricaIBM Research – T. J. WatsonIBM Research – EuropeIBM Research – T. J. WatsonIBM Research – AfricaStanford UniversityStanford UniversityUniversity of PennsylvaniaDepartment of Dermatology, Temple Medical SchoolUniversity of PennsylvaniaUniversity of California San FranciscoMemorial Sloan-Kettering Cancer CenterStanford UniversityStanford UniversityAbstract 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.https://doi.org/10.1038/s41746-023-00881-0 |
| spellingShingle | 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 Skin Tone Analysis for Representation in Educational Materials (STAR-ED) using machine learning npj Digital Medicine |
| title | Skin Tone Analysis for Representation in Educational Materials (STAR-ED) using machine learning |
| title_full | Skin Tone Analysis for Representation in Educational Materials (STAR-ED) using machine learning |
| title_fullStr | Skin Tone Analysis for Representation in Educational Materials (STAR-ED) using machine learning |
| title_full_unstemmed | Skin Tone Analysis for Representation in Educational Materials (STAR-ED) using machine learning |
| title_short | Skin Tone Analysis for Representation in Educational Materials (STAR-ED) using machine learning |
| title_sort | skin tone analysis for representation in educational materials star ed using machine learning |
| url | https://doi.org/10.1038/s41746-023-00881-0 |
| work_keys_str_mv | AT girmawabebetadesse skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT celiacintas skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT kushrvarshney skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT peterstaar skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT chinyereagunwa skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT skylerspeakman skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT justinjia skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT elizabethebailey skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT ademideadelekun skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT julesblipoff skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT ginikanwaonyekaba skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT jennaclester skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT veronicarotemberg skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT jameszou skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning AT roxanadaneshjou skintoneanalysisforrepresentationineducationalmaterialsstaredusingmachinelearning |