Neural Processing Letters

, Volume 11, Issue 3, pp 229–238 | Cite as

Transfusion Cost Containment for Abdominal Surgery with Neural Networks

  • Steven Walczak
  • John E. Scharf


Typing and crossmatching blood is a significant cost for most hospitals, regardless of whether the blood is actually transfused. Many hospitals have implemented a Maximum Surgical Blood Order Schedule, MSBOS, to control over-ordering of blood units for surgery. The research presented in this article examines the use of neural networks for predicting the quantity of blood required by individual patients undergoing abdominal surgery (e.g. splenectomy). A comparison is made between the neural network predictions at a particular hospital versus the current MSBOS methodology for ordering surgical blood, by using the crossmatch to transfusion ratio. Results from the neural network transfusion predictions for the abdominal aortic aneurysm (AAA) surgery imply that neural networks can significantly improve the transfusion efficiency of hospitals. However, further examination of neural network capabilities for predicting the transfusion needs of patients undergoing other types of abdominal surgeries indicates that for operations other than the AAA, neural networks tend to under-predict the transfusion requirements of ten percent of the patients. Even if not used to limit over-ordering of blood for surgical transfusions, neural networks may be used as an intelligent decision support system to evaluate the current efficiency of hospital transfusion practices and to indicate beneficial changes to current MSBOS values.

neural networks abdominal surgery AAA transfusion cost MSBOS 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Barnard, E. and Wessels, L.: Extrapolation and interpolation in neural network classifiers, IEEE Control Systems 12 (1992), 50–53.Google Scholar
  2. 2.
    Baxt, W. G. and Skora, J.: Prospective validation of artificial neural network trained to identify acute myocardial infarction, The Lancet 347 (January 6, 1996), 12–15.Google Scholar
  3. 3.
    Bounds, D. G., Lloyd, P. J. and Mathew, B. G.: A comparison of neural network and other pattern recognition approaches to the diagnosis of low back disorders, Neural Networks 3 (1990), 583–591.Google Scholar
  4. 4.
    Clark, J. A. and Ayoub, M. M.: Blood and component wastage report: A quality assurance function of the hospital transfusion committee, Transfusion 29 (2), (1989), 139–142.Google Scholar
  5. 5.
    Dorffner, G. and Porenta, G.: On using feedforward neural networks for clinical diagnostic tasks, Artificial Intelligence in Medicine 6 (1994), 417–435.Google Scholar
  6. 6.
    Dorman, B. H., Spinale, F.G., Bailey, M. K., Kratz, J. M. and Roy, R. C.: Identification of patients at risk for excessive blood loss during coronary artery bypass surgery: Thromboelastograph versus coagulation screen, Anesthesia Analgesia 76 (4), (1993), 694–700.Google Scholar
  7. 7.
    Dybowski, R. and Gant, V.: Artificial neural networks in pathology and medical laboratories, The Lancet 346 (November 4, 1995), 1203–1207.Google Scholar
  8. 8.
    Fisher, R. E., Scott, J. A. and Palmer, E. L.: Neural networks in ventilation-perfusion imaging, Radiology 198 (March 1996), 699–706.Google Scholar
  9. 9.
    Goodnough, L. W., Soegiarso, R. W., Birkmeyer, J. D. and Welch, H. G.: Economic impact of inappropriate blood transfusions in coronary artery bypass graft surgery, The American Journal of Medicine 94 (1993), 509–514.Google Scholar
  10. 10.
    Hasley, P. B., Lave, J. R., Hanusa, B. H., Arena, V. C., Ramsey, G., Kapoor, W. N. and Fine, M. J.: Variation in the use of red blood cell transfusions, Medical Care 33 (11) (1995), 1145–1160.Google Scholar
  11. 11.
    Hassoun, M. H., Wang, C. and Spitzer, A. R.: NNERVE: Neural Network Extractions of Repetitive Vectors for Electromyography-Part II: Performance analysis, IEEE Transactions on Biomedical Engineering 41 (1994), 1053–1061.Google Scholar
  12. 12.
    Jain, A. J., Mao, J. and Mohiuddin, K. M.: Artificial neural networks: A tutorial, Computer 29 (1996), 31–44.Google Scholar
  13. 13.
    Lowery, T. A. and Clark, J. A.: Successful implementation of maximum surgical blood order schedule, Journal of the Medical Association of Georgia 78 (1989), 155–158.Google Scholar
  14. 14.
    Montague, G. and Morris, J.: Neural-network contributions in biotechnology, Trends in Biotechnology 12 (1994), 312–324.Google Scholar
  15. 15.
    Murphy, W. G., Phillips, P., Gray, A., Heatley, L., Palmer, J., Hopkins, D. and Crawford, R. J.: Blood use for surgical patients: a study of Scottish hospital transfusion practices, Journal of the Royal College of Surgeons of Edinburgh 40 (1995), 10–13.Google Scholar
  16. 16.
    Palmer, R. H., Kane, J. G., Churchill, W. H., Goldman, L. and Komaroff, A. L.: Cost and quality in the use of blood bank services for normal deliveries, cesarean sections, and hysterectomies, JAMA 256 (July 11, 1986), 219–223.Google Scholar
  17. 17.
    Spiess, B. D., Counts, R. B. and Gould, S. A.: Perioperative Transfusion Medicine, Williams and Wilkins, Baltimore, MD, USA, 1998.Google Scholar
  18. 18.
    Wilkins, M. F., Morris, C. W. and Boddy, L.: A comparison of Radial Basis Function and backpropagation neural networks for identification of marine phytoplankton from multivariate flow cytometry data, Computer Applications in the Biosciences 10 (1994), 285–294.Google Scholar

Copyright information

© Kluwer Academic Publishers 2000

Authors and Affiliations

  • Steven Walczak
    • 1
  • John E. Scharf
    • 2
  1. 1.College of Business and AdministrationUniversity of Colorado at DenverDenverUSA
  2. 2.Dept. of AnesthesiologyUniversity of South Florida College of MedicineTampaUSA

Personalised recommendations