Chapter 5

Optimizing Cancer Screening Using Partially Observable Markov Decision Processes

Oguzhan Alagoz
University of Wisconsin, Madison, Madison, Wisconsin 53705, alagoz@engr.wisc.edu

Abstract
This tutorial describes the use of partially observable Markov decision processes (POMDPs) for optimizing cancer screening decisions. POMDP models can be used to address several controversial open research questions in cancer screening, such as when to start and stop screening and how often to screen. POMDP models provide a well-suited framework to optimize screening decisions because they allow the representation of the unobservable true health condition of a patient and screening tests that provide partial information about the true health condition. This tutorial uses a previously developed POMDP model for mammography screening to demonstrate the development and application of a POMDP model for cancer screening. In addition, challenges for applying POMDPs to model other cancer screening problems as well as possible future research directions are described.

Keywords: partially observable Markov decision processes; POMDPs; disease screening; personalized medicine; healthcare applications

Download Chapter 5 - Password-protected content.

The 2011 volume of the TutORials in Operations Research series will be available to people who have registered for the 2011 INFORMS Annual Meeting. All INFORMS members will be able to access TutORials after January 1, 2012. Printed TutORials books from this and previous years can also be ordered here, along with CDs from 2005 to 2009.

For login instructions click here.

________________________________________________

Citation information:

Alagoz, O.Optimizing Cancer Screening Using Partially Observable Markov Decision Processes. J. Geunes, ed. INFORMS TutORials in Operations Research, Vol. 8. INFORMS, Hanover, MD, pp. 75--89.