Table 4. Model performance when trained on Whites and tested on non-Whites.
| Model | AUROC on generalizability experiment | Previous AUROC results |
|---|---|---|
| Logistic Regression with L1 regularization | 75.86% | 75.44% |
| XGBoost | 76.26% | 75.73% |
Official websites use .gov
A
.gov website belongs to an official
government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you've safely
connected to the .gov website. Share sensitive
information only on official, secure websites.