New Generation Computing

, Volume 21, Issue 2, pp 123–133 | Cite as

Discovering validation rules from microbiological data

  • Evelina Lamma
  • Fabrizio Riguzzi
  • Sergio Storari
  • Paola Mello
  • Anna Nanetti
Special Feature

Abstract

A huge amount of data is daily collected from clinical microbiology laboratories. These data concern the resistance or susceptibility of bacteria to tested antibiotics. Almost all microbiology laboratories follow standard antibiotic testing guidelines which suggest antibiotic test execution methods and result interpretation and validation (among them, those annually published by NCCLS2,3). Guidelines basically specify, for each species, the antibiotics to be tested, how to interpret the results of tests and a list of exceptions regarding particular antibiotic test results. Even if these standards are quite assessed, they do not consider peculiar features of a given hospital laboratory, which possibly influence the antimicrobial test results, and the further validation process.

In order to improve and better tailor the validation process, we have applied knowledge discovery techniques, and data mining in particular, to microbiological data with the purpose of discovering new validation rules, not yet included in NCCLS guidelines, but considered plausible and correct by interviewed experts. In particular, we applied the knowledge discovery process in order to find (association) rules relating to each other the susceptibility or resistance of a bacterium to different antibiotics. This approach is not antithetic, but complementary to that based on NCCLS rules: it proved very effective in validating some of them, and also in extending that compendium. In this respect, the new discovered knowledge has lead microbiologists to be aware of new correlations among some antimicrobial test results, which were previously unnoticed. Last but not least, the new discovered rules, taking into account the history of the considered laboratory, are better tailored to the hospital situation, and this is very important since some resistances to antibiotics are specific to particular, local hospital environments.

Keywords

Knowledge Discovery and Data mining Microbiology Knowledge Based Systems Knowledge Elicitation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1).
    Dianoema S.p.A., see the web site: http://www.dianoema. it, 9 July 2001.Google Scholar
  2. 2).
    NCCLS, National Committee for Clinical Laboratory Standards, see the web site: http://www.nccls.org.Google Scholar
  3. 3).
    Ferraro, M. J. et. al., “Performance Standards for Antimicrobial Susceptibility Testing; Eleventh Informational Supplement,”NCCLS document M100-S11,21,1, 2001.Google Scholar
  4. 4).
    Lamma, E., Mello, P., Nanetti, A., Poli, G., Riguzzi, F. and Storari, S., “An Expert System for Microbiological Data Validation and Surveillance” to appear inProc. of ISMDA 2001, Lecture Notes in Computer Science, Springer-Verlag.Google Scholar
  5. 5).
    Lamma, E., Maestrami, L., Mello, P., Riguzzi, F. and Storari, S., “Rule-based Programming for Building Expert Systems: a Comparison in the Microbiological Data Validation and Surveillance Domain,” to appear inElectronic Notes in Theoretical Computer Science 59, 4, Elsevier Science Publishers, 2001.Google Scholar
  6. 6).
    Witten, I. H. and Frank, E.,Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations, Morgan Kaufmann, October 1999.Google Scholar
  7. 7).
    Rakesh, A. and Ramakrishnan, S., “Fast Algorithms for Mining Association Rules,” inProc. of the 20th International Conference on Very Large Databases, 1994.Google Scholar
  8. 8).
    World Health Organization Department of Communicable Disease Surveillance and Response,WHONET 5 — Microbiology Laboratory Database Software, WHO/CDS/CSR/DRS/99.1Google Scholar
  9. 9).
    Kahn, M. G., Steib, S. A., Fraser, V. J. and Dunghan, W. C.,An Expert System for Culture-Based Infection control Surveillance, Washington University, 1992.Google Scholar
  10. 10).
    Center for Disease Control National Nosocomial Infection Surveillance, CDC NNIS, see the web site:www.cdc.org, 9 July 2001.Google Scholar
  11. 11).
    Theratrac, Biomerieux, see the web site: http://www.theratrac.com, 9 July 2001.Google Scholar
  12. 12).
    Gamberger, D., Lavrac, N., Krstacic, G. and Smuc, T., “Inconsistency Tests for Patient Records in a Coronary Heart Disease Database”, inProc. of IDAMAP2000, 2000.Google Scholar
  13. 13).
    Stuhlinger, W., Hogl, O., Stoyan, H. and Muller, M., “Intelligent Data Mining for Medical Quality Management”, inProc. of IDAMAP2000, 2000.Google Scholar
  14. 14).
    Bohanec, M., Rems, M., Slavec, S. and Urh, B., “PTAH: A System for Supporting Nosocomial Infection Therapy”, in (Lavrac, N., Keravnou, E., Zupan, B. eds.)Intelligent Data Analysis in Medicine and Pharmacology, Kluwer Academic Publishers, 1997.Google Scholar
  15. 15).
    Lamma, E., Manservigi, M., Mello, P., Riguzzi, F., Serra, R. and Storari, S., “A System for Monitoring Nosocomial Infections,” inProc. of IDAMAP2000, 2000.Google Scholar
  16. 16).
    Intelligent Miner, see the web site: http://www.software.ibm.com/ data/iminer/fordata, 9 July 2001.Google Scholar
  17. 17).
    Hymel, P. A. and Brossette, S. E., “Data Mining-enhanced Infection Control Surveillance: Sensitivity and Specificity,”Poster at SHEA 2001, 2001.Google Scholar
  18. 18).
    DMSS, see the web site: http://www.medmined.com, 9 July 2001.Google Scholar

Copyright information

© Ohmsha, Ltd. and Springer 2003

Authors and Affiliations

  • Evelina Lamma
    • 1
  • Fabrizio Riguzzi
    • 1
  • Sergio Storari
    • 1
  • Paola Mello
    • 2
  • Anna Nanetti
    • 3
  1. 1.Department of EngineeringUniversity of FerraraFerraraItaly
  2. 2.DEISUniversity of BolognaBolognaItaly
  3. 3.Clinical, Specialist and Experimental Medicine Department, Microbiology sectionUniversity of BolognaBolognaItaly

Personalised recommendations