The purpose of this paper has been to present a hybrid model for decision making under combined uncertainties. The motivation for this study is the fact that consideration of only one kind of uncertainty can lead to a serious underestimation of the risk. Dempster Shafer theory is created to model and manage ignorance in observation. There have been attempts to extend this theory to provide a framework for combining uncertainties due to ignorance with possibilities and probabilistic uncertainties. All these sources of uncertainties are usually present in medical decision making applications. In this paper we present an extension of statistical decision making, which manages combined uncertainties, drawing upon "Generalized Dempster Shafer Theory"(2) Caro lucas is with Center