loss_one_minus_c_index function

Calculate the Concordance index loss

This function subtracts the C-index metric from one to obtain a loss function whose lower values indicate better model performance (useful for permutational feature importance)

loss_one_minus_c_index(y_true = NULL, risk = NULL, surv = NULL, times = NULL)

Arguments

• y_true: a survival::Surv object containing the times and statuses of observations for which the metric will be evaluated
• risk: a numeric vector of risk scores corresponding to each observation
• surv: ignored, left for compatibility with other metrics
• times: ignored, left for compatibility with other metrics

Returns

numeric from 0 to 1, lower values indicate better performance

References

• [1] Harrell, F.E., Jr., et al. "Regression modelling strategies for improved prognostic prediction." Statistics in Medicine 3.2 (1984): 143-152.

Examples

library(survival)
library(survex)

rotterdam <- survival::rotterdam
rotterdam$year <- NULL
cox_rotterdam_rec <- coxph(Surv(rtime, recur) ~ .,
    data = rotterdam,
    model = TRUE, x = TRUE, y = TRUE
)
coxph_explainer <- explain(cox_rotterdam_rec)

risk <- coxph_explainer$predict_function(coxph_explainer$model, coxph_explainer$data)
loss_one_minus_c_index(y_true = coxph_explainer$y, risk = risk)

See Also

c_index()