Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations

Artificial intelligence (AI) systems have increasingly achieved expert-level performance in medical imaging applications. However, there is growing concern that such AI systems may reflect and amplify human bias, and reduce the quality of their performance in historically under-served populations su...

Descripción completa

Detalles Bibliográficos
Autores principales: Seyyed-Kalantari, Laleh, Zhang, Haoran, McDermott, Matthew B. A., Chen, Irene Y., Ghassemi, Marzyeh
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group US 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8674135/
https://www.ncbi.nlm.nih.gov/pubmed/34893776
http://dx.doi.org/10.1038/s41591-021-01595-0

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8674135/
https://www.ncbi.nlm.nih.gov/pubmed/34893776
http://dx.doi.org/10.1038/s41591-021-01595-0

Ejemplares similares