A Case-Based Approach for the Classification of Medical Time Series

  • Alexander Schlaefer
  • Kay Schröter
  • Lutz Fritsche
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2199)


An early and reliable detection of rejections is most important for the successful treatment of renal transplantation patients. A good indicator for the renal function of transplanted patients is the course over time of the parameter creatinine. Existing systems for the analysis of time series usually require frequent and equidistant measurements or a well defined medical theory. These requirements are not fulfilled in our application domain. In this paper we present a case-based approach to classify a creatinine course as critical or non-critical. The distance measure used to find similar cases is based on linear regression. Our results show that while having a good specificity, our sensitivity is significantly higher than that of physicians.


Case Base Acute Rejection Electronic Patient Record Temporal Abstraction Intensive Care Unit Environment 
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.
    R. Bellazzi, C. Larizza, A. Riva: Interpreting Longitudinal Data through Temporal Abstractions: An Application to Diabetic Patients Monitoring. In Liu, Cohen, Berthold (Eds.) LNCS 1280, Springer, 1997.Google Scholar
  2. 2.
    L. Gierl, M. Bull, R. Schmidt: CBR in Medicine. In B. Bartsch-Spoerl, S. Wess, H.-D. Burkhard, M. Lenz (Eds.): Case-Based Reasoning Technology — from Foundation to Application, Springer, 1998.Google Scholar
  3. 3.
    I. J. Haimowitz, P. Phuc Le, I. S. Kohane: Clinical monitoring using regression-based trend templates. Artificial Intelligence in Medicine 7, 473–496, 1995.CrossRefGoogle Scholar
  4. 4.
    G. Lindemann, L. Fritsche, K. Schröter, A. Schlaefer, K. Budde, H.-H. Neumayer: A Web-Based Patient Record for Hospitals-The Design of TBase2. In Bruch, Köckerling, Bouchard, Schug-Paß (Eds.): New Aspects of High Technology in Medicine, 2000.Google Scholar
  5. 5.
    S. Miksch, W. Horn, C. Popow, F. Paky: Intensive Care Monitoring and Therapy Planning for Newborns. In AAAI 1994 Spring Symposium: Artificial Intelligence in Medicine Europe: Interpreting Clinical Data, AAAI Press, 1994.Google Scholar
  6. 6.
    M. M. Richter: Introduction. In B. Bartsch-Spoerl, S. Wess, H.-D. Burkhard, M. Lenz (Eds.): Case-Based Reasoning Technology-from Foundation to Application, Springer, 1998.Google Scholar
  7. 7.
    R. Schmidt, B. Pollwein, L. Gierl: Experiences with Case-Based Reasoning Methods and Prototypes for Medical Knowledge-Based Systems. In W. Horn et al. (Eds.): AIMDM 99, LNAI 1620, Springer, 1999.Google Scholar
  8. 8.
    R. Schmidt, B. Heindl, B. Pollwein, L. Gierl: Multiparametric time course prognoses by means of case-based reasoning and abstractions of data and time. Medical Informatics, Vol. 22, No. 3, 237–250, 1997.CrossRefGoogle Scholar
  9. 9.
    K. Schröter, G. Lindemann, L. Fritsche: TBase2-A Web-Based Electronic Patient Record. Fundamenta Informaticae 43, pages 343–353, IOS Press, Amsterdam, 2000.Google Scholar
  10. 10.
    Y. Shahar: Timing Is Everything: Temporal Reasoning and Temporal Data Maintenance in Medicine. In LNAI 1620, Springer, 1999.Google Scholar
  11. 11.
    Y. Shahar, M. A. Musen: Knowledge-Based Temporal Abstraction in Clinical Domains. Technical Report SMI-95-561, Stanford University 1995.Google Scholar
  12. 12.
    E. H. Shortliffe: Clinical Decision-Support Systems. In E. H. Shortliffe, L. E. Perreault (Eds.): Medical Informatics-Computer Applications in Health Care, Addison-Wesley, 1990.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Alexander Schlaefer
    • 1
  • Kay Schröter
    • 1
  • Lutz Fritsche
    • 2
  1. 1.Department of Computer Science, Artificial Intelligence GroupHumboldt University BerlinBerlinGermany
  2. 2.Department of NephrologyUniversity Hospital CharitéBerlinGermany

Personalised recommendations