A Temporal Data Mining Approach for Discovering Knowledge on the Changes of the Patient’s Physiology

  • Corrado Loglisci
  • Donato Malerba
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5651)


Physiological data represent the health conditions of a patient over time. They can be analyzed to gain knowledge on the course of a disease or, more generally, on the physiology of a patient. Typical approaches rely on background medical knowledge to track or recognize single stages of the disease. However, when no one domain knowledge is available these approaches become inapplicable. In this paper we describe a Temporal Data Mining approach to acquire knowledge about the possible causes which can trigger particular stages of the disease or, more generally, which can determine changes in the patient’s physiology. The analysis is performed in two steps: first, identification of the states of the disease (namely, the stages through which the physiology evolves), then detection of the events which may determine the change from a state to the next one. Computational solutions to both issues are presented. The application to the scenario of the sleep disorders allows to discover events, in the form of breathing and cardiovascular disorders, which may trigger particular sleep stages. Results are evaluated and discussed.


Temporal Data Mining Physiological Data States Events 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Adlassnig, K.P.: Fuzzy Systems in Medicine. In: Proc. of the International Conference in Fuzzy Logic and Technology, pp. 2–5 (2001)Google Scholar
  2. 2.
    Fawcett, T., Provost, F.: Activity Monitoring: Noticing Interesting Changes in Behavior. In: KDD 1999, pp. 53–62 (1999)Google Scholar
  3. 3.
    Goldberger, A.L., Amaral, L.A.N., Glass, L., Hausdorff, J.M., Ivanov, P.C., Mark, R.G., Mietus, J.E., Moody, G.B., Peng, C.K., Stanley, H.E.: PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation 101(23), e215–e220 (2000)CrossRefGoogle Scholar
  4. 4.
    Guimares, G., Peter, J.H., Penzel, T., Ultsch, A.: A method for automated temporal knowledge acquisition applied to sleep-related breathing disorders. Artificial Intelligence in Medicine 23(2), 211–237 (2001)CrossRefGoogle Scholar
  5. 5.
    Guyet, T., Garbay, C., Dojat, M.: Human/Computer Interaction to Learn Scenarios from ICU Multivariate Time Series. In: AIME, pp. 424–428 (2005)Google Scholar
  6. 6.
    Haimowitz, I.J., Le, P.P., Kohane, I.S.: Clinical monitoring using regression-based trend templates. Artificial Intelligence in Medicine 7(6), 473–496 (1995)CrossRefPubMedGoogle Scholar
  7. 7.
    Kahn, M.G.: Modeling Time in Medical Decision-support Programs. Medical Decision Making 11(4), 249–264 (1991)CrossRefPubMedGoogle Scholar
  8. 8.
    Lavrac, N., Zupan, B.: Data Mining in Medicine. In: The Data Mining and Knowledge Discovery Handbook, pp. 1107–1138 (2005)Google Scholar
  9. 9.
    Loglisci, C., Berardi, M.: Segmentation of Evolving Complex Data and Generation of Models. In: ICDM Workshops, pp. 269–273 (2006)Google Scholar
  10. 10.
    Malerba, D.: Learning Recursive Theories in the Normal ILP Setting. Fundam. Inf. 57(1), 39–77 (2003)Google Scholar
  11. 11.
    Shahar, Y.: A Framework for Knowledge-Based Temporal Abstraction. Artif. Intell. 90(1-2), 79–133 (1997)CrossRefGoogle Scholar
  12. 12.
    Uckun, S.: Intelligent systems in patient monitoring and therapy management. A survey of research projects. Int. J. Clin. Monit. Comput. 11(4), 241–253 (1994)CrossRefPubMedGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Corrado Loglisci
    • 1
  • Donato Malerba
    • 1
  1. 1.Dipartimento di InformaticaUniversita’ degli Studi di BariBariItaly

Personalised recommendations