Developing a decision-theoretic network for a congenital heart disease

  • Niels Peek
  • Jaap Ottenkamp
Decision-Support Theories
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1211)


To support paediatric cardiologists in prognostic assessment and treatment planning, a decision-theoretic network for congenital heart disease is being constructed. The network is built in collaboration with a domain expert, using modelling methods commonly advocated in the literature. Although these methods prove to be useful in many cases, it was found that in some situations their applicability falls short. These situations and their associated problems are described. Techniques that have been developed to effectively deal with the problems are presented.


Congenital Heart Disease Pulmonary Vascular Resistance Ventricular Septum Defect Domain Expert Ventricular Septal Defect 
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.
    Andreassen, S., Hovorka, R. Benn, J., Olesen, K. and Carson, E.: A model-based approach to insulin adjustment, In: M. Stefanelli et al., Proc 3rd Conf on Artificial Intelligence in Medicine, Berlin: Springer Verlag (1991) 239–248Google Scholar
  2. 2.
    Dagum, P. and Galper, A.: Forecasting sleep apnea with dynamic network models. Proc 9th Conf on Uncertainty in Artificial Intelligence (1993) 41–48Google Scholar
  3. 3.
    Druzdzel, M. and Van der Gaag, L.: Eliciation of probabilities for belief networks: combining qualitative and quantitative information. Proc 11th Conf on Uncertainty in Artificial Intelligence (1995) 141–148Google Scholar
  4. 4.
    Druzdzel, M., Van der Gaag, L., Henrion, M. and Jensen, F. (eds.): Building Proba-bilistic Networks: Where Do the Numbers Come From? IJCAI-95 Workshop, Montreal, Quebec, Canada (1995)Google Scholar
  5. 5.
    Egar, J., Puerta, A. and Musen, M.: Graph-grammar assistance for modeling of decisions, In: B.R. Gaines et al., Proc 7th AAAI Knowledge Acquisition for KB Systems WS, Banff: SRDG Publications (1992)Google Scholar
  6. 6.
    Goldman, R. and Charniak, E.: A language for the construction of belief networks. IEEE Trans on Pattern Analysis and Machine Intelligence, 15(3) (1993) 196–208Google Scholar
  7. 7.
    Graham, T., and Gutgesell, H.: Ventricular septal defekts. In: A.J. Moss, F.H. Adams et al., Heart Disease in Infants, Children, and Adolescents, Baltimore: Williams & Wilkins (1995) 724–746Google Scholar
  8. 8.
    Heckerman, D., Horvitz, E. and Nathwani, B.: Toward normative expert systems: part II — probability-based representations for efficient knowledge acquisition and inference, Methods of Information in Medicine 31 (1992) 106–116Google Scholar
  9. 9.
    Henrion, M.: Some practical issues in constructing belief networks. In: L.N. Kanal et al., Uncertainty in Artificial Intelligence 3, Amsterdam: Elsevier (1989) 161–173Google Scholar
  10. 10.
    Henrion, M. and Druzdzel, M.: Qualitative propagation and scenario-based approaches to explanation of probabilistic reasoning. In: L.N. Kanal and J.F. Lemmer, Uncertainty in Artificial Intelligence 6, Amsterdam: Elsevier (1991) 17–32Google Scholar
  11. 11.
    Kidd, L., Driscoll, D. and Gersony, W.: Second natural history study of congenital heart defects: results of treatment of patients with ventricular septal defects. Circulation 87 (1993) 138–151Google Scholar
  12. 12.
    Korver, M. and Lucas, P.: Converting a rule-based system into a belief network. Medical Informatics 18(3) (1993) 219–241Google Scholar
  13. 13.
    Lucas, P.: Knowledge acquisition for decision-theoretic expert systems. AISB Quarterly 94 (1996) 23–33Google Scholar
  14. 14.
    Macartney, F., Spiegelhalter, D. and Rigby, M.: Medical management, in: R.H. Anderson et al., Paediatric Cardiology, Vol. 1, Edinburgh: Churchill Livingstone (1987) 421–442Google Scholar
  15. 15.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference, Morgan Kaufmann Publishers, Palo Alto, 1998Google Scholar
  16. 16.
    Schreiber, A., Wielinga, B., De Hoog, R., Akkermans, H. and Van de Velde, W.: CommonKADS: a comprehensive methodology for KBS development. IEEE Expert, 9(6) (1994) 28–37Google Scholar
  17. 17.
    Shachter, R.: Evaluating influence diagrams. Operations Research 34 (1996) 79–90Google Scholar
  18. 18.
    Spirtes, P.: Directed cyclic graphical representations of feedback models. Proc 11th Conf on Uncertainty in Artificial Intelligence (1995) 491–498Google Scholar
  19. 19.
    Van der Gaag, L. and Meyer, J.-J.: Characterising normal forms for informational independence. Proc 6th Int Conf on Information Processing and Management of Uncertainty in Knowledge-Based Systems (1996) 973–978Google Scholar
  20. 20.
    Wellman, M.: Fundamental concepts of qualitative probabilistic networks. Artificial Intelligence 44(3) (1990) 257–303Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Niels Peek
    • 1
  • Jaap Ottenkamp
    • 2
  1. 1.Dept. of Computer ScienceUtrecht UniversityTB Utrecht
  2. 2.Dept. of Paediatric Cardiology, Academic Medical CentreUniversity of AmsterdamAZ Amsterdam

Personalised recommendations