Advertisement

Discriminative Distance Functions and the Patient Neighborhood Graph for Clinical Decision Support

  • Alexey Tsymbal
  • Martin Huber
  • Shaohua Kevin Zhou
Conference paper
Part of the Advances in Experimental Medicine and Biology book series (AEMB, volume 680)

Abstract

There are two essential reasons for the slow progress in the acceptance of clinical similarity search-based decision support systems (DSSs); the especial complexity of biomedical data making it difficult to define a meaningful and effective distance function and the lack of transparency and explanation ability in many existing DSSs. In this chapter, we address these two problems by introducing a novel technique for visualizing patient similarity with neighborhood graphs and by considering two techniques for learning discriminative distance functions. We present an experimental study and discuss our implementation of similarity visualization within a clinical DSS.

Keywords

Clinical Decision Support System Similarity Search Distance Learning Neighborhood Graph Case Retrieval 

Notes

Acknowledgments

This work has been partially funded by the EU project Health-e-Child (IST 2004-027749).

References

  1. 1.
    Bar-Hillel A (2006) Learning from weak representations using distance functions and generative models. PhD Thesis, The Hebrew University of JerusalemGoogle Scholar
  2. 2.
    Berlin A, Sorani M, Sim I (2006) A taxonomic description of computer-based clinical decision support systems. Journal of Biomedical Informatics 39 (6): 656–667PubMedCrossRefGoogle Scholar
  3. 3.
    Blake CL, Keogh E, Merz CJ (1999) UCI repository of machine learning databases. Department of Information and Computer Science, University of California at IrvineGoogle Scholar
  4. 4.
    Breiman L (2001) Random forests. Machine Learning 45(1):5–32CrossRefGoogle Scholar
  5. 5.
    Hertz T (2006) Learning distance functions: algorithms and applications. PhD Thesis, The Hebrew University of JerusalemGoogle Scholar
  6. 6.
    Ionasec RI, Tsymbal A, Vitanovski D et al (2009) Shape-based diagnosis of the aortic valve. In: Proc Int Conf SPIE Medical Imaging SPIE Medical Imaging Google Scholar
  7. 7.
    Mahamud S, Hebert M (2003) The optimal distance measure for object detection. In: Proc Int Conf Computer Vision and Pattern Recognition CVPR’03Google Scholar
  8. 8.
    Nilsson M, Sollenborn M (2004) Advancements and trends in medical case-based reasoning: an overview of systems and system development. In: Proc Int FLAIRS Conf. on AIGoogle Scholar
  9. 9.
    Qi Y, Klein-Seetharaman J, Bar-Joseph Z (2005). Random Forest similarity for protein–protein interaction prediction from multiple sources. In: Proc Pacific Symposium on BiocomputingGoogle Scholar
  10. 10.
    Schmidt R, Vorobieva O (2005) Adaptation and medical case-based reasoning focusing on endocrine therapy support. In: Proc Int Conf AI in Medicine, LNCS 3581, SpringerGoogle Scholar
  11. 11.
    Shi T, Horvath S (2006) Unsupervised learning with Random Forest predictors. Computational and Graphical Statistics 15(1):118–138CrossRefGoogle Scholar
  12. 12.
    Toussaint GT (1980) The relative neighborhood graph of a finite planar set. Pattern Recognition 12(4):261–268CrossRefGoogle Scholar
  13. 13.
    Tsymbal A, Zhou SK, Huber M (2009) Neighborhood graph and learning discriminative distance functions for clinical decision support. In: Proc Annual Int Conf of IEEE Engineering in Medicine and Biology Society EMBC’09Google Scholar
  14. 14.
    Witten I, Frank E (2005) Data mining: practical machine learning tools with Java implementations. Morgan Kaufmann, San FranciscoGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Alexey Tsymbal
    • 1
  • Martin Huber
  • Shaohua Kevin Zhou
  1. 1.Corporate Technology Div. Siemens AGErlangenGermany

Personalised recommendations