A toolbox for surfacing health equity harms and biases in large language models
Stephen Pfohl(Boston College), K. K. Singhal(Google (United States)), Awa Dieng(Google (United States)), Katherine Heller(Google (United States)), Qazi Mamunur Rashid(Google (United States)), Ivor B. Horn(Google (United States)), Mike Schaekermann(Google (United States)), Darlene Neal(Google (United States)), Leo Anthony Celi(Beth Israel Deaconess Medical Center), Sushant Prakash(Google (United States)), Akeiylah Dewitt(Google (United States)), Chirag Nagpal(Google (United States)), Joëlle Barral(Google (United States)), Shekoofeh Azizi(Google (United States)), Nenad Tomašev(Google DeepMind (United Kingdom)), Rory Sayres(Google (United States)), Yossi Matias(Google (United States)), Greg S. Corrado(Google (United States)), Heather Cole-Lewis(Google (United States)), Mercy Asiedu(Google (United States)), Negar Rostamzadeh(Google (Canada)), Yun Liu(Google (United States)), Liam G. McCoy(University of Alberta), Alicia Parrish(Google (United States)), P. Mansfield(Google (United States)), Alan Karthikesalingam(Google (United States)), Alanna Walton(Google (United States)), Christopher Semturs(Google (United States)), Preeti Singh(Google (United States)), Jamila Smith-Loud(Google (United States))
Cited by 74
Related Papers
A guide to deep learning in healthcare
|Nature Medicine|2018|4.7k
Large language models encode clinical knowledge
|Nature|2023|3.1k
International evaluation of an AI system for breast cancer screening
|Nature|2020|3.1k
End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography
|Nature Medicine|2019|2.1k
Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning
|Nature Biomedical Engineering|2018|1.8k