Using patient data within hospital electronic medical records between January 2013 and June 2015, researchers developed a statistical model for forecasting 3 days in advance the number of platelet units likely to be transfused, potentially allowing for optimal inventory management to ensure adequate supply for patient transfusion needs while minimizing waste; such an approach could potentially save 80 million dollars annually if adopted nationwide, according to the authors.
###
Article #17-14097: "Big data modeling to predict platelet usage and minimize wastage in a tertiary care system," by Leying Guan et al.
MEDIA CONTACT: Tho Pham, Stanford University, CA; tel: 650-723-2597; e-mail: < thopham@stanford.edu >
Proceedings of the National Academy of Sciences