The scope of the proposed study is to develop and test new statistical procedures for cost-effectiveness analyses (CEA). Guided by an expanding literature on methods appropriate for CEA, introduction of guidelines for conducting and reporting economic analysis, and experience in CEA analyses, this research plan addresses the development of models that reflect accurately the experience of patients in sustained and changing states of health. The analyses will be based on continuous-time Markov models (both inhomogeneous and semi-Markov) that describe the evolution of patient histories following an intervention or treatment strategy. Measures widely used in cost-effectiveness analyses such as average cost- effectiveness ratio, or C/E ratio, and marginal or incremental cost- effectiveness ration (CER), are defined as parameters in a Markov model. Effectiveness measures include life expectancy, median survival time, and survival rates, discounted where appropriate at a constant rate. Costs are viewed as the value of resources utilized, and consists of two components, 1) cost due to sojourn in health states, and 2) costs due to transition from one health state to another. Covariates that may influence cost and effectiveness measures are incorporated through semi-parametric regression models into the transition intensities of the Markov models. New statistical methods for estimation of cost-effectiveness ratios, C/E and CER, are developed in this proposal. They exploit fully data arising from the longitudinal assessment of patients through different health states following an intervention, and permit quantitation of the variability in estimated CER's, and their dependence on covariate information on patients. The methodology allows for construction of confidence intervals for CER's and statistical tests of hypothesis for given critical values of CER's that governing bodies or affected communities may establish. The performance of the proposed methods will be evaluated with simulated and actual patient history data. The methodology will be applied in two externally funded, peer-reviewed investigations. 1)The Michigan Inter-Institutional Collaborative Heart Study on cost, outcomes, and treatment in acute myocardial infarction of 1,200 patients from three institutions, will investigate factors influencing type of treatment offered to patients, variations based on race and gender, and cost-effectiveness of treatments and procedures. 2) The Strategies for the Care of the Very Low Birthweight Infant Study will investigate competing treatment strategies for care of low birthweight infants with respect to comorbidity, patient benefits and costs, using outcome data from over 3,000 births from the US, Canada, and the Netherlands. The ultimate goal of the study is to assess the cost-effectiveness and cost- utility of different patterns of newborn care utilization. The methods proposed in this investigation have immediate application to these studies, and offer an array of promising techniques for use in cost-effectiveness analysis.
