This study presents an approach to solve multi-response simulation optimization problems. This approach integrates a simulation model with a genetic algorithm heuristic and a goal programming model. This method was modified to perform the search considering the mean and the variance of the responses. This way, the selection process of the genetic algorithm is performed stochastically, and not deterministically like most of the approaches reported in the literature. The methodology was tested using a simulation model of a cancer treatment facility created by the authors. The multi-objective optimization heuristic was successfully used to improve the performance of the model relative to four different system objectives. Empirical results show that the methodology is capable of generating an important part of the Pareto optimal frontier, mostly concentrated in the center portion, where practical solutions are generally located. Significance: Even though real life problems present more than one objective, most simulation optimization studies have been faced with a single objective. This article presents an approach for solving this type of situations and also applies the methodology to a case in the healthcare industry, a field that lacks of applications in simulation optimization.© INTERNATIONAL JOURNAL OF INDUSTRIAL ENGINEERING.