Quantification and valuation of uncertainty of calibrated parameters in decision models

Abstract: We evaluated the implications of different approaches to characterize the uncertainty of calibrated parameters of stochastic decision models (DMs) in the quantified value of such uncertainty in decision making. We used a microsimulation DM of colorectal cancer (CRC) screening to conduct a cost-effectiveness analysis (CEA) of a 10-year colonoscopy screening. We calibrated the natural history model of CRC to epidemiological data with different degrees of uncertainty and obtained the joint posterior distribution of the parameters using a Bayesian approach. We conducted a probabilistic sensitivity analysis (PSA) on all the model parameters with different characterizations of the uncertainty of the calibrated parameters. We estimated the value of uncertainty of the different characterizations with a value of information analysis. All analyses were conducted using high-performance computing resources running the Extreme-scale Model Exploration with Swift (EMEWS) framework. The posterior distribution had a high correlation among some parameters. The parameters of the Weibull hazard function for the age of onset of adenomas had the highest posterior correlation of -0.958. Considering full posterior distributions and the maximum-a-posteriori estimate of the calibrated parameters, there is little difference in the spread of the distribution of the CEA outcomes with a similar expected value of perfect information (EVPI) of $653 and $685, respectively, at a WTP of $66,000/QALY. Ignoring correlation on the posterior distribution of the calibrated parameters produced the widest distribution of CEA outcomes and the highest EVPI of $809 at the same WTP. Different characterizations of the uncertainty of calibrated parameters affect the expected value of reducing uncertainty on the CEA. Ignoring inherent correlation among calibrated parameters on a PSA overestimates the value of uncertainty.