Ingeniare. Revista chilena de ingeniería
versión On-line ISSN 0718-3305
ALBORNOZ, Víctor; HINRICHSEN, Mónica; MIRANDA, Patricia y PENA, Pedro. USE OF MARKOV CHAINS IN PREDICTION OF THE DYNAMICS OF PATIENT BEHAVIOR IN A CARDIOLOGIC INTENSIVE CARE UNIT. Ingeniare. Rev. chil. ing. [online]. 2006, vol.14, n.2, pp. 153-158. ISSN 0718-3305. http://dx.doi.org/10.4067/S0718-33052006000100009.
In this paper we present a probabilistic model that contributes to the study of dynamics in the behavior and permanence of patients in a cardiovascular intensive care unit. The model corresponds to a discrete Markov Chain, that allows to predict the time that a patient remains in the system through the time, by means of certain severity of illness states and the corresponding transition probabilities between those states. The different states are based on the construction of a new score created for this study. We summarize the details of the adopted methodology and the main results reached in the application of the model.
Palabras llave : Markov chains; probabilistic model; intensive care unit; length of hospital stay; score.