A Note on Healthcare Support using Markov Decision Processes

Abstract

In previous research Markov decision processes are used in order to represent a healthcare support. A treatment or a healthcare advice is selected and the total cost is minimized in the previous research. In this research an additional examination is selected before the selection of treatment or healthcare advice. Active learning for a patient's unknown health status is done by the selection of additional examination. After the examination a treatment or a healthcare advice is selected depending on the result of the examination. We propose a new healthcare support method which minimizes total cost with reference to a Bayes criterion. In the proposed method dynamic programming is used.