SMABS 2004 Jena University
SMABS 2004 Home Organization About Jena Sponsors Links Imprint / Contact SMABS Home

European Association of Methodology

Department of methodology and evaluation research

Jena University

Contributions: Abstract

Decision theory in health care: Introduction to Markov modelling in medical decision making

Beate Jahn Karl Peter Pfeiffer
University of Innsbruck

As decision makers in health care are confronted with a continued increase in health care costs on the one hand, and limited budgets on the other, decision theory in the context of medical decision making has become highly significant. A major question to be considered is whether a new treatment, a medical device or a health care program offers good value for money. In this context, "good value" represents a trade-off of cost and benefit.

To estimate cost effectiveness of health care interventions, Markov models are particularly suitable. They should be applied when the decision problem involves a risk that is ongoing over time, the timing of events is important or major events occur more than once so that decision trees become unmanageable or may require unrealistic simplifications. The aim is to provide a comprehensive overview of Markov modelling for economic decisions in health care and to encourage the understanding of the strengths and weaknesses of these techniques. Therefore we will focus particularly on the evaluation of the model, i.e. matrix algebra, cohort simulation and Monte Carlo simulation. Additionally, the application of Markov-cycle trees, the memory-less quality of Markov models and fields of further research will be discussed.

The estimation of effects and costs in health care is particularly difficult because of the complexity of processes and the uncertainty which determines the outcomes. Markov models provide an intuitive approach to this task especially for time dependent, repetitive events, and can therefore also be applied to economic, educational and social models.