Bayesian cost-effectiveness analysis - An example using the GUSTO trial

A desirable element of cost-effectiveness analysis (CEA) modeling is a syst ematic way to relate uncertainty about input parameters to uncertainty in t he computational results of the CEA model. Use of Bayesian statistical esti mation and Monte Carlo simulation provides a natural way to compute a poste rior probability distribution for each CEA result. We demonstrate this appr oach by reanalyzing a previously published CEA evaluating the incremental c ost-effectiveness of tissue plasminogen activator compared to streptokinase for thrombolysis in acute myocardial infarction patients using data from t he GUSTO trial and other auxiliary data sources. We illustrate Bayesian est imation for proportions, mean costs, and mean quality-oi-life weights. The computations are performed using the Bayesian analysis software WinBUGS, di stributed by the MRC Biostatistics Unit, Cambridge, England.