A stochastic framework for estimation of summary measures in cost–effectiveness analyses

Abstract

Stochastic modeling of patient health and cost outcomes is a useful tool in identifying and assessing the important individual characteristics that influence these outcomes. It is a critical step in cost–effectiveness analysis that aims to structure comparisons between competing healthcare interventions on both health outcomes and costs. The authors use a continuous-time finite-state nonhomogeneous Markov process to describe the occurrence of patient events as they unfold over time. States of the process represent health conditions or health states (e.g., well, ill or dead). Commonly used measures of health outcome, such as life expectancy and quality-adjusted survival, are defined in terms of expected values of functions of the process. Costs are incurred through medical resource use while sojourning in health states, and in transitions between health states. By combining these expenditure streams, the authors define net present values for expected total cost over a specified time period. Metrics used in cost–effectiveness analyses, such as net health benefit, net health cost and the cost–effectiveness ratio are defined as functions of expected values. In this longitudinal framework the authors describe regression models for estimation of these summary statistics and quantifying the impact thereupon of explanatory variables. With increasing attention being given to longitudinal studies for gathering economic data alongside clinical investigations, these models can be applied to analyze jointly both costs and patient outcomes and more fully exploit the dynamic mechanisms that engender cost and health outcome data.

Keywords::

• Cox regression
• nonhomogeneous Markov process
• regression model
• simulation
• sojourn time
• survival function
• transition probabilities
• quality of life