Table 2.

Discrimination of the models for predicting 10-year risk of developing HF in the derivation cohort among Black and White adults.

	Race Specific							Not Race Specific
	oRSF	oRSF (Top-20)	Forward Cox	Lasso Cox	Ridge Cox	Boosted Cox	GBT	oRSF
Black adults	0.88 (0.86–0.91)	0.88 (0.85–0.90)	0.76 (0.71–0.80)	0.80 (0.75–0.84)	0.81 (0.50–0.85)	0.81 (0.74–0.87)	0.86 (0.84–0.89)	0.81 (0.78–0.83)
White adults	0.89 (0.86–0.91)	0.88 (0.85–0.90)	0.77 (0.73–0.80)	0.78 (0.55–0.84)	0.78 (0.50–0.82)	0.82 (0.71–0.87)	0.87 (0.85–0.90)	0.80 (0.76–0.85)

Data presented are C-index (95% confidence interval).

The following models were analyzed: race specific oblique random survival forests specific (oRSF), oRSF with the top 20 most important variables (oRSF top-20), forward stepwise Cox regression (forward Cox), Lasso Cox regression (Lasso Cox), Ridge cox regression (ridge Cox), boosted Cox regression (boosted Cox), gradient boosted trees (GBT), and oRSF with race as a covariate (oRSF not race specific). Confidence intervals are the 95% ranges among 1000 bootstrapped replicates.