A Classification-Tree Hybrid Method for Studying Prognostic Models in Intensive Care

  • Ameen Abu-Hanna
  • Nicolette de Keizer
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2101)


Health care effectiveness and efficiency are under constant scrutiny especially when treatment is quite costly as in Intensive Care (IC). At the heart of quality of care programs lie prognostic models whose predictions for a particular patient population may be used as a norm to which actual outcomes of that population can be compared. This paper motivates and suggests a method based on Machine Learning and Statistical ideas to study the behavior of current IC prognostic models for predicting in-hospital mortality. An application of this method to an exemplary logistic regression model developed on the IC data from the National Intensive Care Evaluation registry reveals the model’s weaknesses and suggests ways for developing improved prognostic models.


Prognostic Model Brier Score Admission Type National Intensive Care Evaluation Probabilistic Logistic Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Abu-Hanna A, Lucas PJF. Prognostic Models in Medicine AI and Statistical Approaches, (Abu-Hanna A. and Lucas PJF, eds.). Special issue of Methods of Information in Medicine 2001, 40:1–5.Google Scholar
  2. 2.
    Bennett D, Bion J. ABC of Intensive Care. Organisation of Intensive Care. BMJ 1999; 318:1468–1470.Google Scholar
  3. 3.
    Cleveland, W. S. (1979) Robust Locally Weighted Regression and Smoothing Scatterplots. J. Amer. Statist. Assoc. 74, 829–836.zbMATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Hand DJ. Construction and Assessment of Classification Rules. Chichester: John Wiley and Sons, 1997.zbMATHGoogle Scholar
  5. 5.
    Hosmer D.W., Lemeshow S. Applied Logistic Regression, Wiley, New-York, 1989.Google Scholar
  6. 6.
    Hosmer D.W., Hosmer T., Le Cessie S., Lemeshow S. A Comparison of Goodness-of-fit Tests for the Logistic Regression Model. Statistics in Medicine 1997; 16:965–980.CrossRefGoogle Scholar
  7. 7.
    de Keizer N. An Infrastructure for Quality Assessment in Intensive Care; Prognostic Models and Terminological Systems. PhD Thesis, 2000, University of Amsterdam.Google Scholar
  8. 8.
    Knaus W, Draper E, Wagner D, Zimmerman J. APACHE II: a Severity of Disease Classification System. Crit Care Med 1985; 13:818–829.CrossRefGoogle Scholar
  9. 9.
    Kohavi R. Scaling Up the Accuracy of Naive-Bayes Classifiers: a Decision-Tree Hybrid. Proc. of the Second Int. Conference on Knowledge Discovery and Data Mining. 1996; 202–207.Google Scholar
  10. 10.
    Le Gall J, Lemeshow S, Saulnier F. A New Simplified Acute Physiology Score (SAPS-II) Based on a European/North American Multicenter Study. JAMA 1993; 270:2957–2963.CrossRefGoogle Scholar
  11. 11.
    Long WJ. A Comparison of Logistic Regression to Decision-Tree Induction in a Medical Domain. Compt Bio Res 1993:74–97.Google Scholar
  12. 12.
    Lucas PJF, Abu-Hanna A. Prognostic Methods in Medicine (Lucas PJF and Abu-Hanna A. eds.). Special issue of Artificial Intelligence in Medicine. 1999; 15(2):105–119.Google Scholar
  13. 13.
    Miller M.E., Hui S.L. Validation Techniques for Logistic Regression Models. Statistics in Medicine, 1991, Vol 10, pp. 1213–1226.CrossRefGoogle Scholar
  14. 14.
    Rowan K, Kerr J, Major E, McPherson K, Short A, Vessey M. Intensive Care Society’s APACHE II study in Britain and Ireland-II. BMJ 1993; 307:977–981.CrossRefGoogle Scholar
  15. 15.
    Schwarzer G, Vach W, Schumacher M. On Misuses of Artificial Neural Networks for Prognostic and Diagnostic Classification in Oncology. Statistics in Medicine 2000; 19: 541–561.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Ameen Abu-Hanna
    • 1
  • Nicolette de Keizer
    • 1
  1. 1.Department of Medical InformaticsAMC-University of AmsterdamAmsterdamThe Netherlands

Personalised recommendations