Premium
Adaptive Risk Group Refinement
Author(s) -
LeBlanc Michael,
Moon James,
Crowley John
Publication year - 2005
Publication title -
biometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.298
H-Index - 130
eISSN - 1541-0420
pISSN - 0006-341X
DOI - 10.1111/j.1541-0420.2005.020738.x
Subject(s) - group (periodic table) , computer science , mathematics , chemistry , organic chemistry
Summary We construct interpretable prognostic rules based on a sequence of “box‐shaped” regions in the predictor space indexed by the fraction of patients in the prognostic group. In addition, the method can be used as a building block to construct more general prognostic rules based on unions of boxes, or even as a tool to find multiple prognostic groups. Simulations are used to study the properties of the new method and compare it to constructing prognostic groups based on regression trees and linear proportional hazards (PH) models. We consider an example based on data from several completed clinical trials for patients with multiple myeloma.