Cargando…
Confounders mediate AI prediction of demographics in medical imaging
Deep learning has been shown to accurately assess “hidden” phenotypes from medical imaging beyond traditional clinician interpretation. Using large echocardiography datasets from two healthcare systems, we test whether it is possible to predict age, race, and sex from cardiac ultrasound images using...
Autores principales: | Duffy, Grant, Clarke, Shoa L., Christensen, Matthew, He, Bryan, Yuan, Neal, Cheng, Susan, Ouyang, David |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9780355/ https://www.ncbi.nlm.nih.gov/pubmed/36550271 http://dx.doi.org/10.1038/s41746-022-00720-8 |
Ejemplares similares
-
Blinded, randomized trial of sonographer versus AI cardiac function assessment
por: He, Bryan, et al.
Publicado: (2023) -
Developing medical imaging AI for emerging infectious diseases
por: Huang, Shih-Cheng, et al.
Publicado: (2022) -
The Confounding Effect of Population Structure on Bayesian Skyline Plot Inferences of Demographic History
por: Heller, Rasmus, et al.
Publicado: (2013) -
Uncovering interpretable potential confounders in electronic medical records
por: Zeng, Jiaming, et al.
Publicado: (2022) -
AI vs. AI: Can AI Detect AI-Generated Images?
por: Baraheem, Samah S., et al.
Publicado: (2023)