Artificial intelligence in blood transfusion management: Global reduction of blood component waste and the emergence of predictive models that save millions of lives
DOI:
https://doi.org/10.33448/rsd-v14i12.50249Keywords:
Artificial Intelligence, Blood Transfusion Service, Predictive Learning Models, Machine Learning Algorithms, Transfusion Safety.Abstract
Blood transfusion management faces persistent challenges related to demand variability, the risk of shortages, and high levels of blood component waste, especially platelets. Artificial intelligence models have been highlighted for predicting transfusion patterns and optimizing stocks, offering more precise responses to healthcare systems. This study aims to investigate how artificial intelligence is being applied to blood component management, with an emphasis on two main axes: (1) the overall reduction of blood component waste and (2) the emergence of predictive models that effectively save lives by optimizing the availability, logistics, and use of these products. More specifically, it intends to review the literature from 2021 to 2025, identify practices, technologies, results, and gaps, and provide recommendations for the efficient and ethical adoption of these solutions in the transfusion healthcare sector. This is a hybrid systematic review, conducted according to PRISMA 2020, which analyzed 12 international studies applying AI, machine learning, deep learning, or optimization models to blood transfusion management. The results show that such models exhibit high accuracy in demand forecasting and contribute to more efficient inventory adjustments, loss reduction, and logistical streamlining. Multicenter evidence also points to increased availability of blood components and reduced operational costs. It is concluded that AI constitutes a strategic tool for improving transfusion efficiency and safety, although challenges such as interoperability, data governance, and large-scale validations still need to be overcome.
References
Abouee-Mehrizi, H., et al. (2022). Data-driven platelet inventory management under uncertainty. IISE Transactions on Healthcare Systems Engineering, 12(4), 233–247.
Agac, M. F., et al. (2025). Simulation of cloud-based blood supply chain: A system dynamics approach. Simulation.
Ansari, M., et al. (2024). AI-powered logistics in transfusion supply chains: A global analysis. Computers in Biology and Medicine, 168.
Ben Elmir, M., et al. (2023). Forecasting demand in blood supply chain using machine learning. Information, 14(1), 31.
Caicedo-Rolon, E., et al. (2022). Modeling platelet shelf-life and logistics: Challenges in transfusion medicine. Transfusion Medicine, 32, 54–63.
Cardona, P., et al. (2025). Artificial intelligence techniques in blood banks. Acta Haematologica Polonica, 56(4), 299–308.
Cognasse, F., et al. (2025). Emerging challenges in transfusion safety and inventory management. Transfusion Clinique et Biologique.
Douaioui, H., et al. (2024). Machine learning and deep learning models for demand forecasting in supply chain management: A critical review. Algorithms, 17(5), 93.
Farrington, C., et al. (2024). Many happy returns: Machine learning to support platelet issuing and waste reduction in hospital blood banks. arXiv preprint.
Feng, M.-X., et al. (2025). Platelet demand forecasting based on SARIMA model. Transfusion and Apheresis Science.
Ghouri, O., et al. (2023). Real-time donor engagement using AI-driven mobile systems. Healthcare Analytics, 3.
Ito, Y., et al. (2023). Evaluating inventory management policies of platelets at regional-block blood centers in Japan. Operations Research for Health Care, 40.
Kwon, H., et al. (2024). Forecasting blood demand using machine learning and national statistics: A Korean approach. Scientific Reports, 14.
Li, Z., et al. (2023). Forecasting demand in blood supply chain using data-driven models. Computers & Industrial Engineering, 183, 109281.
Maynard, S., et al. (2024). Machine learning in transfusion medicine: A scoping review. Transfusion Medicine Reviews, 38, 102–119.
Motamedi, A., et al. (2025). Enhancing platelet inventory management using predictive models: A multivariate forecast-based approach. BMC Health Services Research.
Pereira, A. S., Shitsuka, D. M., Parreira, F. J., & Shitsuka, R. (2018). Metodologia da pesquisa científica. Santa Maria: Editora da UFSM.
Sarvestani, S., et al. (2022). Hybrid ARIMA–ANN models for predicting RBC demand by blood group. Journal of Ambient Intelligence and Humanized Computing, 13, 567–579.
Schneider, D., et al. (2024). Artificial intelligence-based forecasting of blood product usage in hospitals: A systematic evaluation. Vox Sanguinis, 119(3), 345–356.
Snyder, H. (2019). Literature review as a research methodology: An overview and guidelines. Journal of Business Research, 104, 333–339.
Yang, H., et al. (2023). Deep learning models for predicting transfusion requirements in surgical patients. Journal of Medical Systems, 47(2), 112–121.
Wong, J., et al. (2024). Integrating AI-driven inventory optimization in national blood services: A multicenter evaluation. Transfusion, 64(1), 52–67.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Weber de Santana Teles, Max Cruz da Silva, Douglas Abilio, Ana Paula Barreto Prata Silva, Mariamália Newton Andrade, Orleane Souza Rezende, Ádamo Newton Marinho Andrade, Raphael Davisson Lopes Santos, Lorena Eugênia Rosa Coelho, Rute dos Santos Souza
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
1) Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2) Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3) Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
