Fig. 2.

Simulated Linear Experimental Log-Risk Surfaces. Predicted log-risk surfaces and errors for the simulated survival data with linear log-risk function with respect to a patient’s covariates x₀ and x₁. a The true log-risk h(x)=x₀+2x₁ for each patient. b The predicted log-risk surface of ${ĥ}_{\beta }\left(x\right)$ from the linear CPH model parameterized by β. c The output of DeepSurv ${ĥ}_{\theta }\left(x\right)$ predicts a patient’s log-risk. d The absolute error between true log-risk h(x) and CPH’s predicted log-risk ${ĥ}_{\beta }\left(x\right)$. e The absolute error between true log-risk h(x) and DeepSurv’s predicted log-risk ${ĥ}_{\theta }\left(x\right)$