JOURNAL ARTICLE

P28 Understanding ethnic inequality and barriers to participation in artificial intelligence (AI) image analysis research in dermatology.

  • Published In: British Journal of Dermatology, 2023, v. 189, n. 1. P. e25 1 of 3

  • Database: Academic Search Ultimate 2 of 3

  • Authored By: Paolino, Alexandra; Tan, Wei Ren; Choy, Shern-Ping; Kim, Byung Jin; Lim, Sarah Man Lin; Seo, Jiwon; Tan, Sze Ping; Duckworth, Michael; Coker, Bolaji; Quadry, Koyinsola; Mulcahy, Gary; Barker, Jonathan N W N; Lynch, Magnus; Corbett, Mark Stephen; Smith, Catherine H; Mahil, Satveer K 3 of 3

Abstract

The article focuses on the representation of ethnic groups in artificial intelligence (AI) research for dermatology, specifically in image-based assessment of psoriasis severity. A prospective observational cohort study conducted in a specialized psoriasis service in South London found that ethnic minorities were underrepresented among participants, with higher decline rates among non-white groups due to factors such as reluctance to have photos taken, psoriasis affecting intimate areas, time constraints, medical issues, and data security concerns. Of those recruited, 82% were white, and only 17% had darker Fitzpatrick skin types V/VI. The findings underscore the need to address barriers to participation to create more diverse and representative datasets, which are essential for developing accurate and equitable AI tools in dermatology.

Additional Information

  • Source:British Journal of Dermatology. 2023/07, Vol. 189, Issue 1, pe25
  • Document Type:Article
  • Subject Area:Ethnic and Cultural Studies
  • Publication Date:2023
  • ISSN:0007-0963
  • DOI:10.1093/bjd/ljad174.049
  • Accession Number:169875829
  • Copyright Statement:Copyright of British Journal of Dermatology is the property of Oxford University Press / USA and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Looking to go deeper into this topic? Look for more articles on EBSCOhost.