Show simple item record

dc.creatorChacón P,Max
dc.creatorRocco M,Víctor
dc.creatorMorgado A,Enrique
dc.creatorSáez H,Enzo
dc.creatorPliscoff M,Sergio
dc.date2002-01-01
dc.date.accessioned2019-09-10T12:40:57Z
dc.date.available2019-09-10T12:40:57Z
dc.identifierhttps://scielo.conicyt.cl/scielo.php?script=sci_arttext&pid=S0034-98872002000100010
dc.identifier.urihttps://revistaschilenas.uchile.cl/handle/2250/106157
dc.descriptionThe prediction of the length of stay at the moment of hospital admission is of outmost importance. Many studies have used lineal models to predict this variable, but there are inherent limitations to these models. The use of non lineal models has been scarce. Aim: To develop a non lineal model to predict length of stay in intensive care units. Material and methods: Retrospective analysis of 294 patients admitted to two intensive care units in Santiago, Chile. The severity of the disease motivating the admission was nominally quantified. This and other physiological variables were included in the model. The length of stay was modeled using Artificial Neural Networks. Results: The model yielded an error of 8.7% (3.6 ± 0.4 days, CI 95%) and a correlation coefficient of 0.9 (p <0.001) for the prediction of length of stay. Using net sensitivity analysis, the model determined that gastrointestinal diseases, infections and respiratory problems were the main causes of prolongation of intensive care unit stay. Conclusions: Intensive care units should have, in the future, computer systems that gather vital information to predict length of stay (Rev Méd Chile 2002; 130: 71-78)
dc.formattext/html
dc.languagees
dc.publisherSociedad Médica de Santiago
dc.relation10.4067/S0034-98872002000100010
dc.rightsinfo:eu-repo/semantics/openAccess
dc.sourceRevista médica de Chile v.130 n.1 2002
dc.subjectIntensive care units
dc.subjectModels, theoretical, Neural networks (computer)
dc.titleIdentificación de los determinantes de la estadía en Unidades de Cuidados Intensivos usando redes neuronales artificiales


This item appears in the following Collection(s)

Show simple item record