Advertisement

An Investigation of Differential Skin Colonization of Neonates by Staphylococci, Using an Artificial Neural Network-based System

  • Diana R. Cundell
  • Les M. Sztandera
  • Alan Arbeter
  • Jean M. Morrone
Conference paper
Part of the Advances in Soft Computing book series (AINSC, volume 19)

Abstract

In this study, we designed an intelligent system to examine the influence of the demographic variables of gender, blood type, and race on the distribution of skin staphylococci bacteria on neonates up to 48 hours old. Bacterial samples were obtained from the axilla and groin of 200 babies, born over an 18-month period, and the staphylococci therein identified using standard microbiological techniques. The intelligent system created for the analysis of this real database was a supervised neural network program made up of a Multi-Layer Perceptron. Six skin staphylococcal species could be reproducibly classified, namely S. aureus (95.2%), S. saprophyticus (88.9%), S. hominis (84.2%), Micrococcus sp. (83.3%), S. haemolyticus (77.9%) and S. epidermidis (77.7%). The remaining three species, which constituted less than 3% of all isolates, were insufficient in number to assign to a class. Of the variables investigated, site of isolation had no effect on determining the staphylococcal distribution and the demographic variables, in order of importance, were found to be gender, blood type and race. These studies suggest that demographic variables are major factors influencing staphylococcal distribution. Such a system may, therefore, hold promise as a diagnostic tool.

Keywords

Hide Layer Blood Type Output Class Fuzzy Entropy Skin Flora 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cundell D.R., Silibovsky R.S., Sanders R. and Sztandera L.M. (2000) Analyzing putative correlates between age, blood type, gender and/or race with bacterial infection. Artificial Intelligence in Medicine 586: 1–5Google Scholar
  2. 2.
    Cundell D.R., Silibovsky R.S., Sanders R. and Sztandera L.M. (2001) An Intelligent Medical System to diagnose bacterial infection in hospitalized patients. International Journal of Medical Informatics 63: 31–40CrossRefGoogle Scholar
  3. 3.
    Sztandera L. M. and Cios K. J. (1997), Ontogenic Neuro-Fuzzy Algorithm: F-CID3, Neurocomputing, 14: 383–402.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Diana R. Cundell
    • 1
  • Les M. Sztandera
    • 2
  • Alan Arbeter
    • 3
  • Jean M. Morrone
    • 1
  1. 1.Biology DepartmentPhiladelphia UniversityPhiladelphiaUSA
  2. 2.Computer Science DepartmentPhiladelphia UniversityPhiladelphiaUSA
  3. 3.Department of PediatricsAlbert Einstein Medical CenterPhiladelphiaUSA

Personalised recommendations