no code implementations • 13 Jul 2022 • Grant Duffy, Shoa L. Clarke, Matthew Christensen, Bryan He, Neal Yuan, Susan Cheng, David Ouyang
When predicting race, we show that tuning the proportion of a confounding variable (sex) in the training data significantly impacts model AUC (ranging from 0. 57 to 0. 84), while in training a sex prediction model, tuning a confounder (race) did not substantially change AUC (0. 81 - 0. 83).