Abstract:This chapter presents the main lines of agent based modeling in the field of medical research. The general diagram consists of a cohort of patients (virtual or real) whose evolution is observed by means of so-called evolution models. Scenarios can then be explored by varying the parameters of the different models. This chapter presents techniques for virtual patient generation and examples of execution models. The advantages and disadvantages of these models are discussed as well as the pitfalls to be avoided. Finally, an application to the medico-economic study of the impact of the penetration rate of generic versions of treatments on the costs associated with HIV treatment is presented.