Partially observable Markov decision model for the treatment of early Prostate Cancer

Abstract

Prostate cancer is second only to lung cancer as the leading cause of cancer deaths in the world Furthermore, policies are difficult to make because of the generally indolent nature of prostate cancer and because it tends to occur in older men who often have multiple, competing medical illnesses. In this paper we applied a Partially observable Markov decision processes (POMDP) formulation to the problem of treating patients with Early prostate Cancer (EPC). The purpose of this paper is to address the challenge of effectively managing Early Prostate cancer therapies. To solve this problem we used a procedure that take advantage of special problem structure, and we provide optimal policies to stochastic and dynamic decisions naturally arise in finding optimal disease treatment plans.