Real-Time Data Mining Models for Predicting Length of Stay in Intensive Care Units

Rui Veloso, Filipe Portela, Manuel Filipe Santos, Álvaro Silva, Fernando Rua, António Abelha, José Machado

2014

Abstract

Nowadays the efficiency of costs and resources planning in hospitals embody a critical role in the management of these units. Length Of Stay (LOS) is a good metric when the goal is to decrease costs and to optimize resources. In Intensive Care Units (ICU) optimization assumes even a greater importance derived from the high costs associated to inpatients. This study presents two data mining approaches to predict LOS in an ICU. The first approach considered the admission variables and some other physiologic variables collected during the first 24 hours of inpatient. The second approach considered admission data and supplementary clinical data of the patient (vital signs and laboratory results) collected in real-time. The results achieved in the first approach are very poor (accuracy of 73 %). However, when the prediction is made using the data collected in real-time, the results are very interesting (sensitivity of 96.104%). The models induced in second experiment are sensitive to the patient clinical situation and can predict LOS according to the monitored variables. Models for predicting LOS at admission are not suited to the ICU particularities. Alternatively, they should be induced in real-time, using online-learning and considering the most recent patient condition when the model is induced.

References

  1. Azari, A., Janeja, V.P. & Mohseni, A., 2012. Predicting Hospital Length of Stay (PHLOS): A Multi-tiered Data Mining Approach. In 2012 IEEE 12th ICDB Workshops. IEEE, pp. 17-24.
  2. Breiman, L. et al., 1984. Classification and Regression Trees no, ed., Belmont, CA: Wadsworth International Group.
  3. Caetano, N. et al., 2014. A Data-Driven Approach to Predict Hospital Length of Stay: A Portuguese Case Study. In ICEIS 2014. (Accepted to be published)
  4. Cios, K. et al., 2007. Supervised Learning: Statistical Methods. In A Knowledge Discovery Approach. Springer US, pp. 307-386.
  5. Clarke, A., 1996. Why are we trying to reduce length of stay? Evaluation of the costs and benefits of reducing time in hospital must start from the objectives that govern change. Quality in health care: QHC, 5(3), pp.172-9.
  6. Dahan, H. et al., 2014. Proactive Data Mining with Decision Trees, New York, NY: Springer New York.
  7. Guy W., Rush J, e. a. (2000). Clinical Global Impressions (CGI) Scale. Psychiatric Measures, APA.
  8. Hachesu, P.R. et al., 2013. Use of data mining techniques to determine and predict length of stay of cardiac patients. Healthcare informatics research, 19(2), pp.121-129.
  9. Han, J., Kamber, M. & Pei, J., 2011. Data Mining: Concepts and Techniques 3rd ed., San Francisco, CA, USA: Morgan Kaufmann Publishers Inc.
  10. Hand, D.J., Smyth, P. & Mannila, H., 2001. Principles of data mining. Available at: http://dl.acm.org/citation. cfm?id=500820 [Accessed May 5, 2014].
  11. Isken, M.W. & Rajagopalan, B., 2002. Data Mining to Support Simulation Modeling of Patient Flow in Hospitals. Journal of Medical Systems, 26(2), pp.179- 197.
  12. Kantardzic, M., 2011. Data Mining: Concepts, Models, Methods, and Algorithms 2nd ed., Wiley-IEEE Press.
  13. Marshall, A., Vasilakis, C. & El-Darzi, E., 2005. Length of Stay-Based Patient Flow Models: Recent Developments and Future Directions. Health Care Management Science, 8(3), pp.213-220.
  14. Michie, D., Spiegelhalter, D.J., et al., 1994. Machine Learning, Neural and Statistical Classification. Ellis Horwood.
  15. Portela, F., Santos, M.F., Silva, Á., et al., 2013. Data Mining for Real-Time Intelligent Decision Support System in Intensive Care Medicine. In ICAART 2013 - International Conference on Agents and Artificial Intelligence. pp. 270-276.
  16. Portela, F., Santos, M.F., Machado, J., et al., 2013. Pervasive and Intelligent Decision Support in Critical Health Care Using Ensembles. In ITBAM. pp. 1-16.
  17. Portela, F., Pinto, F. & Santos, M.F., 2012. Data Mining Predictive Models for Pervasive Intelligent Decision Support in Intensive Care Medicine. In KMIS. pp. 81- 88.
  18. Quiland, J.R., 1986. Induction of Decision Tress. Machine Learning, 1(1), pp.81.106.
  19. Rokach, L. & Maimon, O., 2010. Supervised Learning. In O. Maimon & L. Rokach, eds. Data Mining and Knowledge Discovery Handbook. Springer US, pp. 133-147.
  20. Santos, M.F. & Azevedo, C., 2005. Data Mining Descoberta de conhecimento em base de dados, FCA - Editora de Informática, Lda.
  21. Santos, M.F., Portela, F. & Vilas-Boas, M., 2011. INTCARE?: multi-agent approach for real-time intelligent decision support in intensive medicine. Taylor, K., 2010. Oracle Data Mining Concepts.
  22. Vapnik, V.N., 1995. The Nature of Statistical Learning Theory 1st ed., Springer.
  23. Wagener, G. et al., 2011. The Surgical Procedure Assessment (SPA) score predicts intensive care unit length of stay after cardiac surgery. The Journal of thoracic and cardiovascular surgery, 142(2), pp.443- 50.
  24. Wirth, R., & Hipp, J. (2000). CRISP-DM: Towards a standard process model for data mining. Paper presented at the 4th ICPAKDD.
  25. Zhang, X.-C., Zhang, Z.-D. & Huang, D.-S., 2012. Prediction of length of ICU stay using data-mining techniques: an example of old critically Ill postoperative gastric cancer patients. Asian Pacific journal of cancer prevention: APJCP, 13(1), pp.97- 101.
Download


Paper Citation


in Harvard Style

Veloso R., Portela F., Filipe Santos M., Silva Á., Rua F., Abelha A. and Machado J. (2014). Real-Time Data Mining Models for Predicting Length of Stay in Intensive Care Units . In Proceedings of the International Conference on Knowledge Management and Information Sharing - Volume 1: KMIS, (IC3K 2014) ISBN 978-989-758-050-5, pages 245-254. DOI: 10.5220/0005083302450254


in Bibtex Style

@conference{kmis14,
author={Rui Veloso and Filipe Portela and Manuel Filipe Santos and Álvaro Silva and Fernando Rua and António Abelha and José Machado},
title={Real-Time Data Mining Models for Predicting Length of Stay in Intensive Care Units },
booktitle={Proceedings of the International Conference on Knowledge Management and Information Sharing - Volume 1: KMIS, (IC3K 2014)},
year={2014},
pages={245-254},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005083302450254},
isbn={978-989-758-050-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Knowledge Management and Information Sharing - Volume 1: KMIS, (IC3K 2014)
TI - Real-Time Data Mining Models for Predicting Length of Stay in Intensive Care Units
SN - 978-989-758-050-5
AU - Veloso R.
AU - Portela F.
AU - Filipe Santos M.
AU - Silva Á.
AU - Rua F.
AU - Abelha A.
AU - Machado J.
PY - 2014
SP - 245
EP - 254
DO - 10.5220/0005083302450254