Reducing Surgical Patient Costs Through Use of an Artificial Neural Network to Predict Transfusion Requirements

Document Type


Publication Date



neural networks, radial basis function, transfusion, cost reduction

Digital Object Identifier (DOI)



Transfusion and blood bank services have long been identified as a source of potential cost savings. The implementation and use of maximum surgical blood ordering schedules (MSBOS) and type and screen practices have already succeeded in reducing overall waste and costs associated with transfusion services, but further reductions in waste and cost are still realizable. An artificial neural network (ANN) is trained to predict the quantity of transfusion units that are required by surgical patients for a specific operation. The ANNs produce a significant reduction in the quantity of blood ordered and a subsequent reduction in costs to the hospital and patients. ANNs offer a means to reduce patient costs while maintaining a high level of patient care.


This article was written before Steven Walczak was affiliated with the University of South Florida.

Was this content written or created while at USF?


Citation / Publisher Attribution

Decision Support Systems, v. 30, issue 2, p. 125-138