Advertisement

GoldenEye++: A Closer Look into the Black Box

  • Andreas Henelius
  • Kai Puolamäki
  • Isak Karlsson
  • Jing Zhao
  • Lars Asker
  • Henrik Boström
  • Panagiotis Papapetrou
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9047)

Abstract

Models with high predictive performance are often opaque, i.e., they do not allow for direct interpretation, and are hence of limited value when the goal is to understand the reasoning behind predictions. A recently proposed algorithm, GoldenEye, allows detection of groups of interacting variables exploited by a model. We employed this technique in conjunction with random forests generated from data obtained from electronic patient records for the task of detecting adverse drug events (ADEs). We propose a refined version of the GoldenEye algorithm, called GoldenEye++, utilizing a more sensitive grouping metric. An empirical investigation comparing the two algorithms on 27 datasets related to detecting ADEs shows that the new version of the algorithm in several cases finds groups of medically relevant interacting attributes, corresponding to prescribed drugs, undetected by the previous version. This suggests that the GoldenEye++ algorithm can be a useful tool for finding novel (adverse) drug interactions.

Keywords

Classifiers Randomization Adverse drug events. 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Henelius, A., Puolamäki, K., Boström, H., Asker, L., Papapetrou, P.: A peek into the black box: exploring classifiers by randomization. Data Mining and Knowledge Discovery 28(5–6), 1503–1529 (2014)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Härmark, L., Van Grootheest, A.C.: Pharmacovigilance: methods, recent developments and future perspectives. European Journal of Clinical Pharmacology 64(8), 743–752 (2008)CrossRefGoogle Scholar
  3. 3.
    Stricker, B.H.Ch., Psaty, B.M.: Detection, verification, and quantification of adverse drug reactions. BMJ: British Medical Journal 329(7456), 44 (2004)Google Scholar
  4. 4.
    van Puijenbroek, E.P., Egberts, A.C.G., Heerdink, E.R., Leufkens, H.G.M.: Detecting drug-drug interactions using a database for spontaneous adverse drug reactions: an example with diuretics and non-steroidal anti-inflammatory drugs. European Journal of Clinical Pharmacology 56(9–10), 733–738 (2000)CrossRefGoogle Scholar
  5. 5.
    Milstien, J.B., Faich, G.A., Hsu, J.P., Knapp, D.E., Baum, C., Dreis, M.W.: Factors affecting physician reporting of adverse drug reactions. Drug Information Journal 20(2), 157–164 (1986)Google Scholar
  6. 6.
    Norén, G.N., Edwards, I.R.: Opportunities and challenges of adverse drug reaction surveillance in electronic patient records. Pharmacovigilance Review 4(1), 17–20 (2010)Google Scholar
  7. 7.
    Breiman, L.: Random forests. Machine Learning 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
  8. 8.
    Chawla, N.V.: Data mining for imbalanced datasets: an overview. In: Data mining and Knowledge Discovery Handbook, pp. 853–867. Springer (2005)Google Scholar
  9. 9.
    Wickham, H., Chang, W.: devtools: Tools to make developing R code easier, R package version 1.5 (2014)Google Scholar
  10. 10.
    Bache, K., Lichman, M.: UCI machine learning repository (2014)Google Scholar
  11. 11.
    Dalianis, H., Hassel, M., Henriksson, A., Skeppstedt, M.: Stockholm EPR corpus: a clinical database used to improve health care. In: Swedish Language Technology Conference, pp. 17–18 (2012)Google Scholar
  12. 12.
    Liaw, A., Wiener, M.: Classification and regression by randomforest. R News 2(3), 18–22 (2002)Google Scholar
  13. 13.
    R Core Team. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria (2014)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Andreas Henelius
    • 1
  • Kai Puolamäki
    • 1
  • Isak Karlsson
    • 2
  • Jing Zhao
    • 2
  • Lars Asker
    • 2
  • Henrik Boström
    • 2
  • Panagiotis Papapetrou
    • 2
  1. 1.Finnish Institute of Occupational HealthHelsinkiFinland
  2. 2.Department of Computer and Systems SciencesStockholm University, Forum 100KistaSweden

Personalised recommendations