The prolonged length of stay is an important aspect to be considered for the healthcare management since this affect both the health-related expenditure of the hospital and the quality of the offered service. In the light of these consideration is important for hospitals to be able to predict the LOS of patients and to work on the principal aspect affecting it in order to reduce LOS as much as possible. In this work we focus on patients undergoing mastectomy. The data were collected form 989 patients who underwent mastectomy surgery in the Surgery Department of the AORN “A. Cardarelli” of Naples. Different models have been tested and characterized and the one with the best performance was identified.