In literature, several organizational solutions are proposed to determine the probability of patients’ voluntary discharge from the emergency department. Here, the issue of self-discharge is analyzed by modeling through the Markov theory, an innovative approach recently applied to the healthcare field. The aim of the work is to propose a new method to calculate the rate of voluntary discharge by defining a generic model to describe the process of first aid using the “behavioral” Markov chain model, a new approach that takes into account the satisfaction of the patient. The proposed model is then applied on MatLab and validated to a real case study at the hospital “A. Cardarelli” of Naples. It was found that most of the risk of self-discharge is during the wait time before the patient is seen and for the final report; usually, once the analysis is requested, the patient, although not very satisfied, is willing to wait longer for the results. The model allows the description of the first aid process from the perspective of the patient. The presented model is generic and adaptable to each hospital facility by changing only the transition probabilities between states.Version of record at "doi: 10.3934/mbe.2021013":Carlo Ricciardi, Alfonso Maria Ponsiglione, Giuseppe Converso, Ida Santalucia, Maria Triassi, Giovanni Improta. Implementation and validation of a new method to model voluntary departures from emergency departments. Mathematical Biosciences and Engineering, 2021, 18(1): 253-273. doi: 10.3934/mbe.2021013
