Bias in, bias out: Underreporting and underrepresentation of diverse skin types in machine learning research for skin cancer detection—A scoping review - 14/06/22
Doi : 10.1016/j.jaad.2021.06.884
Lisa N. Guo, MD a, b, Michelle S. Lee, BA a, b, Bina Kassamali, BA a, b, Carol Mita, MSLIS a, Vinod E. Nambudiri, MD, MBA a, b, ⁎ 
a Harvard Medical School, Boston, Massachusetts
b Department of Dermatology, Brigham and Women's Hospital, Boston, Massachusetts
∗Correspondence to: Vinod E. Nambudiri, MD, MBA, Department of Dermatology, Brigham and Women's Hospital, 221 Longwood Avenue, Boston, MA 02115Department of DermatologyBrigham and Women's Hospital221 Longwood AvenueBostonMA02115
Key words : artificial intelligence, machine learning, melanoma, racial diversity, skin cancer, skin of color
| Funding sources: None. |
|
| IRB approval status: No human subjects were involved in this study, thus institutional review board approval was not required. |
|
| Reprints not available from the authors. |
© 2021
American Academy of Dermatology, Inc.. Publié par Elsevier Masson SAS. Tous droits réservés.
Vol 87 - N° 1
P. 157-159 - juillet 2022 Retour au numéro
Article précédent
- National trends in hospitalizations of atopic dermatitis adult patients: A 21-year longitudinal United States population-based study
- Ehizogie Edigin, Asim Kichloo, Zain El-Amir, Farah Wani, Precious Obehi Eseaton, Hafeez Shaka
- Mohs micrographic surgery for vulvar malignancies: A systematic review
- Samantha Shwe, Ashley N. Elsensohn, Camila Ortiz, Christina N. Kraus
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?