Transfusion Cost Containment for Abdominal Surgery with Neural Networks

Abstract

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.