Using relative utility curves for risk prediction

Risk prediction models that are based on medical history or the results of tests are becoming common in the cancer literature and are used to provide additional information to those who are involved in making treatment decisions on the basis of estimated risk.

In this commentary, Stuart G. Baker, ScD, of the National Cancer Institute in Bethesda, Md., elaborates on the relative utility curve as a method for evaluating risk prediction. He illustrates the application of relative utility curves in an analysis of previously published data involving the addition of breast density to a risk prediction model for invasive breast cancer.

"An important use of relative utility curves is to evaluate the addition of a risk factor to the risk prediction model," according to the author.

More information: http://jnci.oxfordjournals.org

Source: Journal of the National Cancer Institute (news : web)