Exportar Publicação

Caetano, Nuno, Cortez, Paulo & Laureano, Raul M. S. (2015). Using Data Mining for Prediction of Hospital Length of Stay: An Application of the CRISP-DM Methodology. In José Cordeiro, Slimane Hammoudi, Leszek Maciaszek, Olivier Camp, Joaquim Filipe (Ed.), Enterprise Information Systems. (pp. 149-166). Alemanha: Springer International Publishing.

N. Caetano et al.,  "Using Data Mining for Prediction of Hospital Length of Stay: An Application of the CRISP-DM Methodology", in Enterprise Information Systems, José Cordeiro, Slimane Hammoudi, Leszek Maciaszek, Olivier Camp, Joaquim Filipe, Ed., Alemanha, Springer International Publishing, 2015, vol. 227, pp. 149-166

@incollection{caetano2015_1732235607516,
	author = "Caetano, Nuno and Cortez, Paulo and Laureano, Raul M. S.",
	title = "Using Data Mining for Prediction of Hospital Length of Stay: An Application of the CRISP-DM Methodology",
	booktitle = "Enterprise Information Systems",
	year = "2015",
	volume = "227",
	series = "Lecture Notes in Business Information Processing",
	edition = "1",
	pages = "149-149",
	publisher = "Springer International Publishing",
	address = "Alemanha",
	url = "http://link.springer.com/chapter/10.1007/978-3-319-22348-3_9"
}

TY  - CHAP
TI  - Using Data Mining for Prediction of Hospital Length of Stay: An Application of the CRISP-DM Methodology
T2  - Enterprise Information Systems
VL  - 227
AU  - Caetano, Nuno
AU  - Cortez, Paulo
AU  - Laureano, Raul M. S.
PY  - 2015
SP  - 149-166
DO  - 10.1007/978-3-319-22348-3_9
CY  - Alemanha
UR  - http://link.springer.com/chapter/10.1007/978-3-319-22348-3_9
AB  - Hospitals are nowadays collecting vast amounts of data related with patient records. All this data hold valuable knowledge that can be used to improve hospital decision making. Data mining techniques aim precisely at the extraction of useful knowledge from raw data. This work describes an implementation of a medical data mining project approach based on the CRISP-DM methodology. Recent real-world data, from 2000 to 2013, were collected from a Portuguese hospital and related with inpatient hospitalization. The goal was to predict generic hospital Length Of Stay based on indicators that are commonly available at the hospitalization process (e.g., gender, age, episode type, medical specialty). At the data preparation stage, the data were cleaned and variables were selected and transformed, leading to 14 inputs. Next, at the modeling stage, a regression approach was adopted, where six learning methods were compared: Average Prediction, Multiple Regression, Decision Tree, Artificial Neural Network ensemble, Support Vector Machine and Random Forest. The best learning model was obtained by the Random Forest method, which presents a high quality coefficient of determination value (0.81). This model was then opened by using a sensitivity analysis procedure that revealed three influential input attributes: the hospital episode type, the physical service where the patient is hospitalized and the associated medical specialty. Such extracted knowledge confirmed that the obtained predictive model is credible and with potential value for supporting decisions of hospital managers.
ER  -