Context: Building decision support tools in medicine requires identifying relevant variables to model the medical decision. Currently, machine learning techniques are used to select variables used for decision making from patient care data. Along with data-driven analysis, eliciting experts opinion can be useful to model decision making. Thus, combining expert data to observed data into a new variable selection method could identify the whole set of relevant variables for decision making. Objective: We propose a method that introduces experts’ information into a Bayesian variable selection model, the Stochastic Search Variable Selection (SSVS) model [1]. Experts’information would be introduced using simulated data incorporated via the power prior method that allows modulating the quantity of external information considered with observed data [2]. We consider the context of medical decisions regarding dose adjustment of Irinotecan for the treatment of metastatic colorectal cancer. Method: Expert information is first modeled through elicited weights, i.e. clinicians are asked to estimate, from 0 to 100, the weights that express their beliefs about the importance of each variable in their decision of dose adaptation. Then a sample of simulated data is generated from these weights. The relationship between repeated dose reductions, patient characteristics, and toxicities is modelled through a mixed effects logistic model for both simulated and observed data. Thereafter, the likelihood conditional on these simulated data is combined with observed data via the power prior method, which allows to incorporate a flexible amount of simulated data. Model parameters estimation incorporates a variable selection step using the SSVS model. The performance of this method is assessed for different amount of expert information. Results: The elicited weights deeply vary across clinicians. Performance does not depend on the amount of expert information. For the same amount of observed and expert information combined using the power method, we are able to select rare variables with high elicited weight. Conclusion: We present a Bayesian variable selection method incorporating elicited expert information and observed data. The method selects a set of relevant variables to model the medical decision process. References [1] George, E.I., McCulloch, R.E.: Variable Selection Via Gibbs Sampling. Journal of the American Statistical Association 88(423), 881–889 (1993). [2] Ibrahim, J.G., Chen, M.-H.: Power Prior Distributions for Regression Models. Statistical Science 15(1), 46–60 (2000).