Skip to main content

Diagnosis of MRSA with neural networks and logistic regression approach

Health Care Management Science volume 3, Article number: 287 (2000) Cite this article

Abstract

Antibiotic-resistant pathogens are increasingly prevalent in the hospitals and community. A timely and accurate diagnosis of the infection would greatly help physicians effectively treat patients. In this research we investigate the potential of using neural networks (NN) and logistic regression (LR) approach in diagnosing methicillin-resistant Staphylococcus aureus (MRSA). Receiver-Operating Characteristic (ROC) curve and the cross-validation method are used to compare the performances of both systems. We found that NN is better than the logistic regression approach, in terms of both the discriminatory power and the robustness. With modeling flexibility inherent in its techniques, NN is effective in dealing with MRSA and other classification problems involving large numbers of variables and interaction complexity. On the other hand, logistic regression in our case is slightly inferior, offers more clarity and less perplexity. It could be a method of choice when fewer variables are involved and/or justification of the results is desired.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

43,34 €

Price includes VAT (Finland)
Tax calculation will be finalised during checkout.

References

  1. D. Bamber, The area above the ordinal dominance graph and the area below the receiver operating graph, Journal of Mathematical Psychology 12 (1975) 387–415.

    Article  Google Scholar 

  2. J.M. Boyce, G. Potter-Bynoe, C. Chenevert and T. King, Environmental contamination due to methicillin-resistant staphylococcus aureus, Infection Control and Hospital Epidemiology 18(9) (1997) 622–627.

    Article  Google Scholar 

  3. BrainMaker (California Scientific Software Press, Nevada City, CA, 1998).

  4. W.K. Chow, A look at various estimators in logistic models in the presence of missing values. A Rand Note prepared for the US Department of Health, Education and Welfare, N-1324-HEW (1979).

  5. K. Gilhuijs, ROC analysis: software, Department of Radiology, University of Chicago (2000). http://www-radiology.uchicago.edu/krl/ toppage11.htm.

  6. A. Goetz et al., Methicillin-resistant Staphylococcus aureus (MRSA) in the community: a prospective hospital-based study of 504 patients, 37th Interscience Conference on Antimicrobial Agents and Chemotherapy, American Society of Microbiology, Toronto, abstract no. K163 (1997).

    Google Scholar 

  7. J.H. Hanley and B.J. McNeil, The meaning and use of the area under a receiver operating characteristic (ROC) curve, Radiology 143(1) (1982) 29–36.

    Google Scholar 

  8. B. Herold, Methicillin-resistant S. aureus rising in children, Journal of American Medical Association 279 (1998) 593–598.

    Article  Google Scholar 

  9. M.S. Hung, M.Y. Hu, B.E. Patuwo and M. Shanker, Estimation posterior probabilities in classification problems with neural networks, International Journal of Computational Intelligence and Organization 1 (1996) 49–60.

    Google Scholar 

  10. R.D. Hurrion, An example of simulation optimization using a neural network metamodel: finding the optimal number of Kabans in manufacturing system, Journal of Operational Research Society 48(11) (1992) 1105–1112.

    Article  Google Scholar 

  11. D.R. Kardatzke, ROC curves for comparing test statistics, Unpublished Dissertation, Graduate School of Public Health, University of Pittsburgh (1992).

  12. J. Lawrence, Introduction to Neural Networks: Design, Theory, and Applications (California Scientific Software Press, Nevada City, CA, 1994).

    Google Scholar 

  13. T. Master, Practical Neural Network Recipes in C++ (Academic Press, 1993).

  14. S. Menard, Applied Logistic Regression Analysis, Series: Quantitative Applications in the Social Sciences (Sage, Thousand Oaks, CA, 1993).

    Google Scholar 

  15. J. Neter, W. Wasserman and M.H. Kutner, Applied Linear Statistical Models: Regression, Analysis of Variance, and Experimental Designs (Irwin, Homewood, IL, 1994).

    Google Scholar 

  16. H. Sacho and B. Schoub, Community-acquired Methicillin-Resistant Staphylococcus Aureus (MRSA) infection, Lessons in infectious diseases (1995).

  17. SAS Institute Inc., The SAS System (SAS, Cary, NC, 1999).

    Google Scholar 

  18. M. Schumacher, R. Robner and W. Vach, Neural networks and logistic regression: Part I, Computational Statistics and Data Analysis 21 (1999) 661–682.

    Article  Google Scholar 

  19. H. Selker et al., A comparison of performance of mathematical predictive methods for medical diagnosis: identifying acute cardiac ischemia among emergency department patients, Journal of Investigative Medicine 43(5) (1995) 468–476.

    Google Scholar 

  20. M. Smith, Neural Networks for Statistical Modeling (Van Nostrand Reinhold, New York, NY, 1993).

    Google Scholar 

  21. J.A. Swets, Measuring the accuracy of diagnostic systems, Science 240 (1999) 1285–1293.

    Google Scholar 

  22. J.G. Taylor, Neural Networks and Their Applications (Wiley, 1999).

  23. H. White, Artificial Neural Networks: Approximation and Learning Theory (Basil Blackwell, Oxford, 1992).

    Google Scholar 

  24. G. Zhang and V. Berardi, An investigation of neural networks in thyroid function diagnosis, Health Care Management Science 1 (1999) 29–37.

    Article  Google Scholar 

Download references

Author information

Affiliations

  1. Katz Graduate School of Business, University of Pittsburgh, Pittsburgh, PA, 15260, USA

    Jen S. Shang

  2. VA Pittsburgh Healthcare System, Pittsburgh, PA, 15240, USA

    Yu-sen E. Lin & Angella M. Goetz

Authors
  1. Jen S. Shang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yu-sen E. Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Angella M. Goetz
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Shang, J.S., Lin, Ys.E. & Goetz, A.M. Diagnosis of MRSA with neural networks and logistic regression approach. Health Care Management Science 3, 287 (2000). https://doi.org/10.1023/A:1019018129822

Download citation

  • DOI: https://doi.org/10.1023/A:1019018129822

Keywords

  • Vancomycin
  • False Alarm
  • Neural Network Model
  • Logistic Regression Approach
  • Nosocomial Spread