Data Mining Models to Predict Patient’s Readmission in Intensive Care Units

Pedro Braga, Filipe Portela, Manuel Filipe Santos, Fernando Rua

2014

Abstract

Decision making is one of the most critical activities in Intensive Care Units (ICU). Moreover, it is extremely difficult for health professionals to interpret in real time all the available data. In order to improve the decision process, classification models have been developed to predict patient’s readmission in ICU. Knowing the probability of readmission in advance will allow for a more efficient planning of discharge. Consequently, the use of these models results in a lower rates of readmission and a cost reduction, usually associated with premature discharges and unplanned readmissions. In this work was followed a numerical index, called Stability and Workload Index for Transfer (SWIFT). The data used to induce the classification models are from ICU of Centro Hospitalar do Porto, Portugal. The results obtained so far, in terms of accuracy, were very satisfactory (98.91%). Those results were achieved through the use of Naïve Bayes technique. The models will allow health professionals to have a better perception on patient’s future condition in the moment of the hospital discharge. Therefore it will be possible to know the probability of a patient being readmitted into the ICU.

References

  1. ACSS, 2012. Administração Central do Sistema de Saúde, Circular Normativa nº 33/2012 Available at: http://www.acss.min-saude.pt.
  2. Barua, S., Islam, M. & Murase, K., 2013. ProWSyn: Proximity Weighted Synthetic Oversampling Technique for Imbalanced Data Set Learning. Advances in Knowledge Discovery and Data Mining. s.l.:Springer Berlin Heidelberg, pp. 317-328.
  3. Chapman, P. et al., 1999. CRISP-DM 1.0, s.l.: SPSS.
  4. Gajic, O. et al., 2008. The Stability and Workload Index for Transfer score predicts unplanned intensive care unit patient readmission: Initial development and validation. Crit Care Med. 676-682.
  5. Gortzis, L. G. et al., 2008. Predicting ICU survival: A meta-level approach, s.l.: BMC Health Services Research.
  6. Intelligence, S., 2013. Hospital Readmissions on the Increase, press release.
  7. Ministério da Saúde, 2003. Cuidados Intensivos: Recomendações para o seu desenvolvimento.
  8. Portela, F., Pinto, F. & Santos, M. F., 2012. Data Mining Predictive Models for Pervasive Intelligent Decision Support in Intensive Care. Advances in Information Systems and Technologies.
  9. Portela, et al., 2012. Intelligent and Real Time Data Acquisition and Evaluation to Determine Critical Events in Intensive Medicine. Procedia Technology.
  10. Prati, Batista & Monard, 2008. Curvas de ROC para avaliação de classificadores. pp. 215-222.
  11. Russell, S., 1999. Reducing readmissions to the intensive care unit.. Heart Lung.
  12. Santos, M. F., Mathew, W. & Portela, C. F., 2011. Grid data mining for outcome prediction in intensive care medicine, s.l.: Springer CCIS.
  13. Silva, A., 2007. Modelos de Inteligência Artificial na análise da monitorização de eventos clínicos adversos, Disfunção/Falência de órgãos e prognóstico do doente, Universidade do Porto, PHD Thesis;
  14. Taft, M. et al., 2003. Oracle Data Mining Concepts, 10g Release 1 (10.1), s.l.: Oracle Corporation.
Download


Paper Citation


in Harvard Style

Braga P., Portela F., Filipe Santos M. and Rua F. (2014). Data Mining Models to Predict Patient’s Readmission in Intensive Care Units . In Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-015-4, pages 604-610. DOI: 10.5220/0004907806040610


in Bibtex Style

@conference{icaart14,
author={Pedro Braga and Filipe Portela and Manuel Filipe Santos and Fernando Rua},
title={Data Mining Models to Predict Patient’s Readmission in Intensive Care Units},
booktitle={Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2014},
pages={604-610},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004907806040610},
isbn={978-989-758-015-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Data Mining Models to Predict Patient’s Readmission in Intensive Care Units
SN - 978-989-758-015-4
AU - Braga P.
AU - Portela F.
AU - Filipe Santos M.
AU - Rua F.
PY - 2014
SP - 604
EP - 610
DO - 10.5220/0004907806040610