Application of artificial intelligence in predicting the criticality of blood drug stocks: A study with real operational data
DOI:
https://doi.org/10.33448/rsd-v15i4.50932Keywords:
Artificial Intelligence, Blood Transfusion, Predictive Learning Models, Stock, Transfusion Safety.Abstract
The adequate availability of blood components is a critical challenge for healthcare systems, especially given the variability in healthcare demand and the operational limitations of blood transfusion services. The objective of this study was to apply artificial intelligence techniques to predict the criticality of blood transfusion stocks, based on the analysis of operational data from a Brazilian public blood center, from January to March 2026. This is an observational, retrospective, and analytical study with a quantitative approach, using descriptive statistics and supervised machine learning models, including Random Forest and XGBoost. The results showed structured patterns of criticality, with greater stability in red blood cell concentrates and greater variability in platelet concentrates, which presented a more frequent recurrence of critical and emergency states. The models demonstrated satisfactory performance in predicting criticality levels, with high agreement between observed and predicted values. It is concluded that the application of artificial intelligence represents a promising tool for anticipating critical scenarios, optimizing the management of blood stocks, and supporting decision-making, contributing to transfusion safety and the efficiency of health services.
References
Abolghasemi, H., et al. (2010). Blood donor incentives: A step forward or backward. Asian Journal of Transfusion Science, 4(1), 9–13.
Agresti, A. (2010). Analysis of ordinal categorical data (2nd ed.). Wiley.
Brasil. Ministério da Saúde. (2011). Guia nacional de gerenciamento de estoque de sangue em situações de emergência. Ministério da Saúde.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Chandler, T., et al. (2020). Blood inventory management: Hospital best practices. Transfusion Medicine Reviews, 34(3), 181–188.
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). ACM.
Estcourt, L. J., et al. (2017). Platelet transfusions for preventing bleeding in people with haematological disorders after chemotherapy and stem cell transplantation. Cochrane Database of Systematic Reviews, (7).
Field, A. (2013). Discovering statistics using IBM SPSS statistics (4th ed.). Sage.
Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and practice (2nd ed.). OTexts.
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2021). An introduction to statistical learning: With applications in R (2nd ed.). Springer.
Karakatsanis, A., et al. (2021). Forecasting blood demand: A systematic review. Vox Sanguinis, 116(2), 109–121.
Klein, H. G., et al. (2019). Biomedical excellence for safer transfusion. The New England Journal of Medicine, 381(6), 509–511.
Kuhn, M., & Johnson, K. (2013). Applied predictive modeling. Springer.
McKinney, W. (2010). Data structures for statistical computing in Python. In Proceedings of the 9th Python in Science Conference (pp. 56–61). SciPy.
Pedregosa, F., et al. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
Pereira et al. (2018). Metodologia da pesquisa científica. [Free ebook]. Editora da UFSM.
Pierskalla, W. P. (2005). Supply chain management of blood banks. Operations Research, 53(5), 769–784.
Rajkomar, A., Dean, J., & Kohane, I. (2019). Machine learning in medicine. The New England Journal of Medicine, 380(14), 1347–1358.
Risemberg, R. I. C., Wakin, M., & Shitsuka, R. (2026). A importância da metodologia científica no desenvolvimento de artigos científicos. E-Acadêmica, 7(1), e0171675. https://doi.org/10.52076/eacad-v7i1.675.
Sibinga, C. T. S. (2020). Artificial intelligence in transfusion medicine and its impact on the quality concept. Transfusion and Apheresis Science, 59(6), e103021.
Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427–437.
Wasserstein, R. L., & Lazar, N. A. (2016). The ASA statement on p-values: Context, process, and purpose. The American Statistician, 70(2), 129–133.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Weber de Santana Teles, Max Cruz da Silva, Elaine Cristina Posener Araújo, Ádamo Newton Marinho Andrade, Lana Elise de Santana Santos, Cauã Marx Nascimento de Carvalho, Raphael Davisson Lopes Santos, Sales de Oliveira Farias, Abraão Soares Silva
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.
