Advertisement

Pervasive Ensemble Data Mining Models to Predict Organ Failure and Patient Outcome in Intensive Medicine

  • Filipe Portela
  • Manuel Filipe Santos
  • Álvaro Silva
  • António Abelha
  • José Machado
Part of the Communications in Computer and Information Science book series (CCIS, volume 415)

Abstract

The number of patients admitted to Intensive Care Units with organ failure is significant. This type of situation is very common in Intensive Medicine. Intensive medicine is a specific area of medicine whose purpose is to avoid organ failure and recover patients in weak conditions. This type of problems can culminate in the death of patient. In order to help the intensive medicine professionals at the exact moment of decision making, a Pervasive Intelligent Decision Support System called INTCare was developed. INTCare uses ensemble data mining to predict the probability of occurring an organ failure or patient death for the next hour. To assure the better results, a measure was implemented to assess the models quality. The transforming process and model induction are both performed automatically and in real-time. The ensemble uses online-learning to improve the models. This paper explores the ensemble approach to improve the decision process in intensive Medicine.

Keywords

Data Mining Intensive Care Organ Failure Patient Outcome INTCare Ensemble Real-time Pervasive Health Care 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Silva, Á., Cortez, P., Santos, M.F., Gomes, L., Neves, J.: Rating organ failure via adverse events using data mining in the intensive care unit. Artificial Intelligence in Medicine 43, 179–193 (2008)CrossRefGoogle Scholar
  2. 2.
    Silva, A., Cortez, P., Santos, M.F., Gornesc, L., Neves, J.: Mortality assessment in intensive care units via adverse events using artificial neural networks. Artificial Intelligence in Medicine 36, 223–234 (2006)CrossRefGoogle Scholar
  3. 3.
    Boas, M.V., Santos, M.F., Portela, F., Silva, A., Rua, F.: Hourly prediction of organ failure and outcome in real time in Intensive Care Medicine (2010)Google Scholar
  4. 4.
    Portela, F., Santos, M.F., Vilas-Boas, M.: A Pervasive Approach to a Real-Time Intelligent Decision Support System in Intensive Medicine. In: Fred, A., Dietz, J.L.G., Liu, K., Filipe, J. (eds.) IC3K 2010. CCIS, vol. 272, pp. 368–381. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  5. 5.
    Portela, F., Santos, M.F., Silva, Á., Machado, J., Abelha, A.: Enabling a Pervasive approach for Intelligent Decision Support in Critical Health Care. In: HCist 2011 – International Workshop on Health and Social Care Information Systems and Technologies, Algarve, Portugal, p. 10. S.-A.T. Publication (2011)Google Scholar
  6. 6.
    Portela, F., Santos, M.F., Gago, P., Silva, Á., Rua, F., Abelha, A., Machado, J., Neves, J.: Enabling real-time intelligent decision support in intensive care. In: 25th European Simulation and Modelling Conference- ESM 2011, 446 pages (2011)Google Scholar
  7. 7.
    Fayyad, U.M., Piatetsky-Shapiro, G., Smyth, P.: From data mining to knowledge discovery: an overview (1996)Google Scholar
  8. 8.
    Portela, F., Pinto, F.: Data Mining Predictive Models For Pervasive Intelligent Decision Support In Intensive Care Medicine. In: KMIS 2012 - nternational Conference on Knowledge Management and Information Sharing, Barcelona, INSTICC (2012)Google Scholar
  9. 9.
    Vincent, J., Mendonça, A., Cantraine, F., Moreno, R., Takala, J., Suter, P., Sprung, C., Colardyn, F., Blecher, S.: Use of the SOFA score to assess the incidence of organ dysfunction/failure in intensive care units: Results of a multicenter, prospective study. Critical Care Medicine 26, 1793–1800 (1998)CrossRefGoogle Scholar
  10. 10.
    Vincent, J.L., Moreno, R., Takala, J., Willatts, S., De Mendonca, A., Bruining, H., Reinhart, C.K., Suter, P.M., Thijs, L.G.: The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure. Intensive Care Medicine 22, 707–710 (1996)CrossRefGoogle Scholar
  11. 11.
    Portela, F., Santos, M., Vilas-Boas, M., Rua, F., Silva, Á., Neves, J.: Real-time Intelligent decision support in intensive medicine. In: KMIS 2010- International Conference on Knowledge Management and Information Sharing, Valência, Espanha, p. 7 (2010)Google Scholar
  12. 12.
    Santos, M.F., Portela, F., Vilas-Boas, M., Machado, J., Abelha, A., Neves, J.: INTCARE - Multi-agent approach for real-time Intelligent Decision Support in Intensive Medicine. In: 3rd International Conference on Agents and Artificial Intelligence (ICAART). Springer (2011)Google Scholar
  13. 13.
    Bellazzi, R., Zupan, B.: Predictive data mining in clinical medicine: current issues and guidelines. International Journal of Medical Informatics 77, 81–97 (2008)CrossRefGoogle Scholar
  14. 14.
    Han, J., Kamber, M.: Data mining: concepts and techniques. Morgan Kaufmann (2006)Google Scholar
  15. 15.
    Dietterich, T.: Ensemble methods in machine learning. Multiple Classifier Systems, 1–15 (2000)Google Scholar
  16. 16.
    Kantardzic, M.: Data mining: concepts, models, methods, and algorithms. Wiley-IEEE Press (2011)Google Scholar
  17. 17.
    Ting, K.M., Witten, I.H.: Issues in stacked generalization. Arxiv preprint arXiv:1105.5466 (2011)Google Scholar
  18. 18.
    Wolpert, D.H.: Stacked generalization*. Neural networks 5, 241–259 (1992)Google Scholar
  19. 19.
    Concepts, O.D.M.: 11g Release 1 (11.1). Oracle Corp. 2007 (2005)Google Scholar
  20. 20.
    Tamayo, P., Berger, C., Campos, M., Yarmus, J., Milenova, B., Mozes, A., Taft, M., Hornick, M., Krishnan, R., Thomas, S.: Oracle Data Mining. In: Data Mining and Knowledge Discovery Handbook, pp. 1315–1329 (2005)Google Scholar
  21. 21.
    Wu, X., Kumar, V., Ross Quinlan, J., Ghosh, J., Yang, Q., Motoda, H., McLachlan, G.J., Ng, A., Liu, B., Yu, P.S.: Top 10 algorithms in data mining. Knowledge and Information Systems 14, 1–37 (2008)CrossRefGoogle Scholar
  22. 22.
    Varshney, U.: Pervasive healthcare and wireless health monitoring. Mobile Networks and Applications 12, 113–127 (2007)CrossRefGoogle Scholar
  23. 23.
    Orwat, C., Graefe, A., Faulwasser, T.: Towards pervasive computing in health care - A literature review. BMC Medical Informatics and Decision Making 8, 26 (2008)CrossRefGoogle Scholar
  24. 24.
    Varshney, U.: Pervasive Healthcare Computing: EMR/EHR, Wireless and Health Monitoring. Springer-Verlag New York Inc. (2009)Google Scholar
  25. 25.
    Mikkonen, M., Väyrynen, S., Ikonen, V., Heikkila, M.O.: User and concept studies as tools in developing mobile communication services for the elderly. Personal and Ubiquitous Computing 6, 113–124 (2002)CrossRefGoogle Scholar
  26. 26.
    Satyanarayanan, M.: Pervasive computing: vision and challenges. IEEE Personal Communications 8, 10–17 (2002)CrossRefGoogle Scholar
  27. 27.
    Portela, F., Santos, M.F., Silva, A.: Towards Pervasive and Intelligent Decision Support in Intensive Medicine – A Data Stream Mining Approach. In: AIM - Artificial Intelligence in Medicine (2013)Google Scholar
  28. 28.
    Guy, W.: ECDEU assessment manual for psychopharmacology. Rockville, Md (1976)Google Scholar
  29. 29.
    Guy, W., Rush, J., et al.: Clinical Global Impressions (CGI) Scale. Psychiatric Measures, APA (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Filipe Portela
    • 1
  • Manuel Filipe Santos
    • 1
  • Álvaro Silva
    • 2
  • António Abelha
    • 3
  • José Machado
    • 3
  1. 1.Centro AlgoritmiUniversity of MinhoPortugal
  2. 2.Serviço de Cuidados IntensivosCentro Hospitalar do PortoPortugal
  3. 3.CCTCUniversity of MinhoPortugal

Personalised recommendations