Septic Shock Diagnosis by Neural Networks and Rule Based Systems

  • R. Brause
  • F. Hamker
  • J. Paetz
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 96)


In intensive care units physicians are aware of a high lethality rate of septic shock patients. In this contribution we present typical problems and results of a retrospective, data driven analysis based on two neural network methods applied on the data of two clinical studies.


Neural Network Septic Shock Early Warning System Septic Shock Patient Intensive Care Unit Physician 
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]
    Berthold, M. (1999), “Fuzzy logic,” Chapter 8 in Berthold, M. and Hand, D.J. (Eds.), Intelligent Data Analysis: an Introduction, Springer-Verlag, pp. 269–298.Google Scholar
  2. [2]
    Berthold, M. and Diamond, J. (1995), “Boosting the performance of RBF networks with dynamic decay adjustment,” Advances in Neural Information Processing Systems, vol. 7, pp. 521–528.Google Scholar
  3. [3]
    Berthold, M. and Diamond, J. (1998), “Constructive training of probabilistic neural networks,” Neurocomputing, vol. 19, pp. 167–183.CrossRefGoogle Scholar
  4. [4]
    Brause, R. and Hanisch, E. (2000), Medical Data Analysis ISMDA 2000, Springer Lecture Notes in Comp.Sc., LNCS 1933, Springer Verlag, Heidelberg.Google Scholar
  5. [5]
    Brause, R. (1999), “Revolutionieren neuronale Netze unsere Vorhersagefähigkeiten?” Zentralblatt für Chirurgie, vol. 124, pp. 692–698.Google Scholar
  6. [6]
    Brause, R. and Friedrich, F. (2000), “A neuro-fuzzy approach as medical diagnostic interface,” Proc. ESANN 2000, De Facto Publ., Brussels, pp. 201–206.Google Scholar
  7. [7]
    Bruske, J. (1998), “Dynamische Zellstrukturen. Theorie und Anwendung eines KNN-Modells,” Dissertation, Technische Fakultät der Christian-Albrechts-Universität, Kiel, Germany.Google Scholar
  8. [8]
    Bruske, J. and Sommer, G. (1995), “Dynamic cell structure learns perfectly topology preserving map,” Neural Computation, vol. 7, pp. 845–865.CrossRefGoogle Scholar
  9. [9]
    Bellman, R. (1961), Adaptive Control Processes: a Guided Tour, Princeton, NJ: Princeton University Press.Google Scholar
  10. [10]
    Dybowski, R. (1997), “Assigning confidence intervals to neural network predictions,” Technical Report, Division of Infection, UMDS (St Thomas’ Hospital), London, 2 March 1997, available at
  11. [11]
    Fein, A.M. et al. (Eds.) (1997), Sepsis and Multiorgan Failure, Williams and Wilkins, Baltimore.Google Scholar
  12. [12]
    Fritzke, B. (1994), “Fast learning with incremental RBF networks,” Neural Processing Letters, vol. 1, no. 1, pp. 2–5.CrossRefGoogle Scholar
  13. [13]
    Fritzke, B. (1995), “A growing neural gas network learns topologies,” in: Tesauro, G., Touretzky, D.S., and Leen, T.K. (Eds.), Proc. Advances in Neural Information Processing Systems (NIPS 7), MIT Press, Cambridge, MA, pp. 625–632.Google Scholar
  14. [14]
    Fritzke, B. (1997), “Incremental neuro-fuzzy systems,” in: Bosacchi, B., Bezdek, J.C., and Fogel, D.B. (Eds.), Proc. SPIE, vol. 3165, Applications of Soft Computing, pp. 86–97.Google Scholar
  15. [15]
    Geisser, S. (1975), “The predictive sample reuse method with applications,” Journal of The American Statistical Association, vol. 70, pp. 320–328.CrossRefGoogle Scholar
  16. [16]
    Hamker, F., Paetz, J., Thöne, S., Brause, R., and Hanisch, E. (2000), `Erkennung kritischer Zustände von Patienten mit der Diagnose `Septischer Schock’ mit einem RBF-Netz,“ Tech. Report, Interner Bericht 04/00, Fachbereich Informatik, J.W. Goethe-Uni-versität Frankfurt a. M., fbreport04–00.pdf.Google Scholar
  17. [17]
    Hartung, J. (1993), Statistik: Lehr-und Handbuch der Angewandten Statistik, Oldenbourg-Verlag, München.Google Scholar
  18. [18]
    Haykin, S. (1999), Neural Networks, a Comprehensive Foundation, Prentice Hall, 2nd edition, Upper Saddle River, NJ 07458.Google Scholar
  19. [19]
    Heinke, D. and Hamker, F. (1998), “Comparing neural networks, a benchmark on growing neural gas, growing cell structures, and fuzzy ARTMAP,” IEEE Transactions on Neural Networks, vol. 9, no. 6, pp. 1279–1291.PubMedCrossRefGoogle Scholar
  20. [20]
    Huber, K.-P. and Berthold, M.R. (1995), “Building precise classifiers with automatic rule extraction,” IEEE International Conference on Neural Networks, vol. 3, pp. 1263–1268.Google Scholar
  21. [21]
    Inza I., Merino M., Larranaga P., Quiroga J., Sierra B., and Girala M. (2000), “Feature subset selection using probabilistic tree structures. a case study in the survival of cirrhotic patients treated with TIPS,” in [4], pp. 97–110.Google Scholar
  22. [22]
    Kindermann, L., Lewandowski, A., Tagscherer, M., and Protzel, P. (1999), “Computing confidence measures and marking unreliable predictions by estimating input data densities with MLPs,” Proceedings of the Sixth International Conference on Neural Information Processing (ICONIP ‘89), Perth, Australia, pp. 91–94.Google Scholar
  23. [23]
    Lavrac, N. (1999), “Machine learning for data mining in medicine,” in: Horn, W. et al (Eds.), Proc. AIMDM’99. LNAI 1620, Springer-Verlag, Berlin Heidelberg, pp. 47–62.Google Scholar
  24. [24]
    Martinetz, T.M. and Schulten, K.J. (1994), “Topology representing networks,” Neural Networks, vol. 7, pp. 507–522.CrossRefGoogle Scholar
  25. [25]
    Members of the American College of Chest Physicians/Society of Critical Care Medicine Consensus Conference Committee (1992), “Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis,” Crit. Care Med., vol. 20, pp. 864–874.CrossRefGoogle Scholar
  26. [26]
    Mosteller, F. and Tukey, J.W. (1968), “Data analysis, including statistics,” in: Lindzey, G. and Aronson, E. (Eds.), Handbook of Social Psychology 2, Addison-Wesley.Google Scholar
  27. [27]
    Nauck, D. (1999), “Obtaining interpretable fuzzy classification rules from medical data,” Artificial Intelligence in Medicine, vol. 16, no. 2, pp. 149–169.PubMedCrossRefGoogle Scholar
  28. [28]
    Neugebauer, E. and Lefering, R. (1996), “Scoresysteme und Datenbanken in der Intensivmedizin — Notwendigkeit und Grenzen,” Intensivmedizin, vol. 33, pp. 445–447.Google Scholar
  29. [29]
    Paetz, J., Hamker, F., and Thöne, S. (2000), “About the analysis of septic shock patient data,” in [4], pp. 130–137. Also available at paetz/PaetzISMDA2000.pdf.Google Scholar
  30. [30]
    Pietruschka, U. and Brause, R. (1999), “Using growing RBF nets in rubber industry process control,” Neural Computing and Applications, Springer Verlag, vol. 8, no. 2, pp. 95–105.Google Scholar
  31. [31]
    Schumacher, M., Rößner, R., and Vach, W. (1996), “Neural networks and logistic regression, part I,” Computational Statistics and Data Analysis, vol. 21, pp. 661–682.CrossRefGoogle Scholar
  32. [32]
    Seely, A. and Christou, N. (2000), “Multiple organ dysfunction syndrome, exploring the paradigm of complex nonlinear systems,” Crit. Care Med., vol. 28, no. 7, pp. 2193–2200.PubMedCrossRefGoogle Scholar
  33. [33]
    Tagscherer, M., Kindermann, L., Lewandowski, A., and Protzel, P. (1999), “Overcome neural limitations for real world applications by providing confidence values for network predictions,” Proceedings of the Sixth International Conference on Neural Information Processing (ICONIP ‘89), Perth, Australia, pp. 520–525.Google Scholar
  34. [34]
    Toweill, D., Sonnenthal, K., Kimberly, B., Lai, S., and Goldstein, B. (2000), “Linear and nonlinear analysis of hemodynamic signals during sepsis and septic shock,” Crit. Care Med., vol. 28, no. 6, pp. 2051–2057.PubMedCrossRefGoogle Scholar
  35. [35]
    Vach, W., Roner, R., and Schumacher, M. (1996), “Neural networks and logistic regression: part II,” Computational Statistics and Data Analysis, vol. 21, 683–701.CrossRefGoogle Scholar
  36. [36]
    Wade, S., Büssow, M, and Hanisch, E. (1998), “Epidemiology of systemic inflammatory response syndrome, sepsis and septic shock in surgical intensive care patients,” Chirurg, vol. 69, pp. 648–655.PubMedCrossRefGoogle Scholar
  37. [37]
    Wahba, G. and Wold, S. (1975), “A completely automatic French curve: fitting spline functions by cross-validation,” Communications in Statistics, vol. 4, pp. 1–17.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • R. Brause
  • F. Hamker
  • J. Paetz

There are no affiliations available

Personalised recommendations