Abstract
In order to provide more ethical and objective measures of the likelihood of Intensive Care Unit (ICU) recovery, hospitals have turned increasingly to decision support system software packages, such as APACHE. However, these packages derive estimates from parametric techniques, such as Binary Logit Regression (BLR) in the APACHE case, and require the developer to specify in advance the functional relationships among variables in the model. Recent rapid advancements in computer software and hardware technology have encouraged researchers to use more computationally intensive, non-parametric techniques such as Neural Networks (NNs), which are purported to be better than parametric models in terms of prediction capabilities. The present study applies both methodologies to a sample of ICU patients and shows that the NN technique predicts mortality rates more correctly than BLR, and offers a promising non-parametric alternative to the parametric methodologies in hospital settings.
Similar content being viewed by others
References
J.R. Kimberly and E.J. Zajac, Strategic adaptation in health care organizations: Implications for theory and research, Medical Care Review 42(2) (1985) 267-302.
M.D. Fottler, Health care organization performance: Present and future research, Yearly Review of Management: A Special Issue of the Journal of Management 13 (1987) 367-392.
S. Shortell, E. Morrison and B. Friedman, Strategic Choices for American Hospitals (Jossey-Bass, San Francisco, CA, 1990).
J. Goldman, The giant that keeps on growing, Institutional Investor 30(12) (1996) 2-3.
K.S. Abramowitz, Forecast for the health care industry, Institutional Investor (September 1998).
G.S. Bilchik, Organizational depression, Hospitals Health Networks 74(2) (2000) 34-38.
A.S. Relmann, Assessment and accountability: The third revolution in medical care, New England Journal of Medicine 319 (1988) 1220-1222.
D.S. O'Leary, The joint commission looks to future, Journal of the American Medical Association 258 (1987) 936-940.
P.M. Ellwood, Outcomes management: A technology of patient experience, New England Journal of Medicine (1988) 1549-1556.
M.S. Kraatz, Learning by association? Interorganizational networks and adaptation to environmental change, Academy of Management Journal 41(6) (1988) 621-643.
S. Walczak and J.E. Scharf, Reducing surgical patient costs through use of an artificial neural network to predict transfusion requirements, Decision Support Systems 30(2) (2000) 125-138.
B.C. Borlase, J.T. Baxter, P.N. Benotti, M. Stone, E.F. Wood, R.A. Forse, G.L. Blackburn and G. Steele, Surgical intensive care unit resource use in a specialty referral hospital: Predictors of early death and cost implications, Surgery 109(6) (1991) 687-693.
W.A. Knaus, E.A. Draper and D. Wagner, Evaluating medical surgical intensive care units, in: Major Issues in Critical Care Medicine, eds. J.E. Parrillo and S.M. Ayers (Williams & Wilkins, Baltimore, MD 1984) p. 35-46.
Software for hard issues: Who will live? Who will die? A computer votes, Business Week 27 (April 1992) 55.
Office of Medical Applications Research, National Institutes of Health Consensus Development Conference Summary, NIH, U.S. Department of Health and Human Service, Critical Care Medicine 4(6) (1983).
R.D. Abbott, Logistic regression in survival analysis, American Journal of Epidemiology 121 (1985) 465-471.
S.H. Moolgavkar, Assessing the adequacy of the logistic regression model for matched case control studies, Statistics in Medicine 4 (1985) 425-435.
S. Lemeshow, D. Teres, J. Avrunin and H. Pastides, Predicting the outcome of ICU patients, Journal of the American Statistical Association 83 (1988) 348-356.
K. Adams, R. Houchens, G. Wright and J. Robbins, Predicting hospital choice for rural medicare beneficiaries: The role of severity of illness, Health Care Services 26(5) (1991) 583-612.
L. Adair, B. Popkin and D. Guilkey, The duration of breast-feeding: How is it affected by industry factors? Demography 30(1) (1993) 63-80.
D.P. Papadakis, W.A. Knaus, E.A. Draper and J.E. Zimmerman, Identification of low-risk monitor admissions to medical-surgical ICUs, Chest 92(4) (September 1987) 423-428.
D.P. Wagner, W.A. Knaus, E.A. Draper and J.E. Zimmerman, Identification of low-risk monitor patients within a medical surgical intensive care unit, Medical Care 21(4) (1983) 425-434.
S. Radcliffe, Where have all the margins gone, Best's Review, Life/Health Ed. (April 1982) 10-15.
A.W. Lo, Logit versus discriminant analysis: A specification test and application to corporate bankruptcy, Journal of Econometrics 31 (1986) 151-178.
R. BarNiv and R.A. Hershbarger, Classifying financial distress in the life insurance industry, The Journal of Risk and Insurance 57 (Spring 1990) 110-136.
S.J. Press and S. Wilson, Choosing between logistic regression and discriminant analysis, Journal of American Statistical Association (December 1978) 699-705.
D. McFadden, A comment on discriminant analysis versus logit analysis, Annals of Economic and Social Measurement (1976) 511-523.
H. White, Neural network learning and statistics, AI Expert (December 1989) 48-52.
D. Fletcher and E. Goss, Forecasting with neural networks: An application using bankruptcy data, Information and Management 24 (1993) 159-167.
R. Hecht-Nielsen, Neurocomputing (Addison-Wesley, New York, 1989).
A.N. Kolmogorov, On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition, Dokl. Akad. Nauk USSR 114 (1957) 953-956.
M. Caudill, Neural network training tips and techniques, AI Expert (January 1990) 56-61.
R.P. Lippman, An introduction to computing with neural nets, IEEE ASSP 4 (1987) 4-22.
D.E. Rumelhart, G.E. Hinton and R.J. Williams, Learning internal representations by error propagation, in: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. I, eds. D.E. Rumelhart and J.L. McClelland (MIT Press, Cambridge, MA, 1986) pp. 318-362.
F. Soulie, P. Gallinari, Y. Cun and S. Thiria, Evaluation of network architectures on test learning tasks, in: Proceedings of the IEEE 1st International Conference on Neural Networks, Vol. II (1990) pp. 653-660.
M. Wann, T. Hediger and N. Greenbaum, The influence of training sets on generalization in feed-forward neural networks, in: Proceedings of the IEEE 1st International Conference on Neural Networks, Vol. III (1990) pp. 137-142.
D.W. Hosmer and S. Lemeshow, Applied Logistic Regression (Wiley, New York, NY, 1989).
P. Lachenbruch, An almost unbiased method of obtaining confidence intervals for the probability of misclassification in discriminant analysis, Biometrics 23(4) (December 1967) 639-645.
Y.H. Pao, Adaptive Pattern Recognition and Neural Networks (Addison-Wesley, Reading, MA, 1989).
A.J. Maren, D. Jones and S. Franklin, Handbook of Neural Computing Applications (Academic Press, San Diego, CA, 1990).
Y. Yoon, G. Swales and T.M. Margavio, A comparison of discriminant analysis versus artificial neural networks, Journal of Operational Research Society 44(1) (1993) 51-60.
M. Caudill, Using neural nets, AI Expert (December 1989) 34-61.
B. Efron, Regression and ANOVA with zero-one data: Measures of residual variation, Journal of the American Statistical Association (March 1978) 113-121.
J.A. Hanley and B.J. McNeil, The meaning and use of the area under a receiver operating characteristic (ROC) curve, Radiology 143 (April 1982) 29-36.
J.A. Hanley and B.J. McNeil, A method of comparing the areas under receiver operating characteristic curves derived from the same cases, Radiology 148 (September 1983) 839-843.
S. Bhattacharyya and P.C. Pendharkar, Inductive, evolutionary, and neural computing techniques for discrimination: A comparative study, Decision Sciences 29(4) (Fall 1998) 871-899.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Goss, E.P., Vozikis, G.S. Improving Health Care Organizational Management Through Neural Network Learning. Health Care Management Science 5, 221–227 (2002). https://doi.org/10.1023/A:1019760901191
Issue Date:
DOI: https://doi.org/10.1023/A:1019760901191