We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Machine learning in transfusion medicine: A scoping review.
- Authors
Maynard, Suzanne; Farrington, Joseph; Alimam, Samah; Evans, Hayley; Li, Kezhi; Wong, Wai Keong; Stanworth, Simon J.
- Abstract
This article provides a comprehensive review of the use of machine learning (ML) in transfusion medicine. It discusses the potential benefits of ML in improving patient outcomes and clinical practice in patient blood management. The review covers various studies that have developed prediction models for blood transfusion requirements in different surgical procedures, as well as studies on predicting transfusion needs in trauma patients, identifying risk factors for adverse outcomes, assessing transfusion appropriateness, and investigating transfusion safety. The studies utilize different ML models and report varying levels of accuracy in their predictions. The article highlights the potential of ML in improving transfusion practices and optimizing inventory management in hospital settings, but also emphasizes the need for further research, validation, and standardization in this field.
- Subjects
BLOOD platelet transfusion; CLINICAL prediction rules; BLOOD transfusion reaction; BLOOD transfusion; MACHINE learning; BRAIN natriuretic factor; CLINICAL decision support systems; ARTIFICIAL neural networks
- Publication
Transfusion, 2024, Vol 64, Issue 1, p162
- ISSN
0041-1132
- Publication type
Article
- DOI
10.1111/trf.17582