Identificação de Fenótipos Clínicos e Desfechos da Transfusão de Hemácias em UTI Baseada em Trajetórias Fisiológicas
Resumo
Decisões de transfusão de hemácias em UTIs baseiam-se em limiares universais que negligenciam a heterogeneidade dos pacientes. Este estudo propõe um framework de IA utilizando MiniRocket e K-means em dados do MIMIC-IV para identificar fenótipos clínicos com respostas distintas à transfusão. A população foi segmentada em macrofenótipos de benefício e risco conforme trajetórias temporais. Enquanto um grupo teve redução de 6,5% na mortalidade, outro não obteve ganhos e exigiu ventilação mecânica prolongada. Os achados demonstram que a eficácia transfusional depende de trajetórias fisiológicas individuais, apoiando a transição de protocolos fixos para uma medicina personalizada e baseada em dados.
Referências
Bhavani, S. V. et al. (2022). Development and validation of novel sepsis subphenotypes using trajectories of vital signs. Intensive Care Medicine.
Bolcato, M. et al. (2020). Patient blood management: The best approach to transfusion medicine risk management. Transfusion and apheresis science : official journal of the World Apheresis Association : official journal of the European Society for Haemapheresis.
Carson, J. L. et al. (2012). Red Blood Cell Transfusion: A Clinical Practice Guideline From the AABB*. Annals of Internal Medicine.
Carson, J. L. et al. (2023). Transfusion thresholds and other strategies for guiding allogeneic red blood cell transfusion. Cochrane Database of Systematic Reviews.
Christiansson, S. (2023). Straight to the heart: Classification of multi-channel ecg-signals using minirocket. Master’s thesis.
Cochrane (2019). Cochrane handbook for systematic reviews of interventions, version 6.0 (updated july 2019), chapter 15.4.4.
Dempster, A. et al. (2021). Minirocket: A very fast (almost) deterministic transform for time series classification. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.
Hébert, P. C. et al. (1999). A multicenter, randomized, controlled clinical trial of transfusion requirements in critical care. New England Journal of Medicine.
Holst, L. B. et al. (2014). Lower versus higher hemoglobin threshold for transfusion in septic shock. New England Journal of Medicine.
Hyland, S. L. et al. (2020). Early prediction of circulatory failure in the intensive care unit using machine learning. Nature medicine, 26(3):364–373.
Iwashyna, T. J. et al. (2015). Implications of heterogeneity of treatment effect for reporting and analysis of randomized trials in critical care. American Journal of Respiratory and Critical Care Medicine.
Kramer, A. H. and Zygun, D. A. (2009). Anemia and red blood cell transfusion in neuro-critical care. Critical Care. [link]
Latona, A. et al. (2025). Coagulation and transfusion informatics in chronic liver disease: a data linkage study of emergency department presentations. EJHaem.
Liu, P. et al. (2023). Subphenotyping heterogeneous patients with chronic critical illness to guide individualised fluid balance treatment using machine learning: A retrospective cohort study. eClinicalMedicine.
Liu, S. et al. (2024). Association between alkaline phosphatase to albumin ratio and mortality among patients with sepsis. Scientific reports.
Mihaylova, M. et al. (2025). Anemia in newly diagnosed cases with liver cirrhosis. Acta Medica Bulgarica.
Ngufor, C. et al. (2018). Identification of clinically meaningful plasma transfusion subgroups using unsupervised random forest clustering. AMIA Annual Symposium Proceedings.
Pearl, J. (2013). Causality: Models, Reasoning, and Inference. Cambridge University Press, 2 edition.
Robins, J. M. et al. (2000). Marginal structural models and causal inference in epidemiology. Epidemiology.
Rodrigues, D. S. et al. (2022). Predicting the outcome for covid-19 patients by applying time series classification to electronic health records. BMC Medical Informatics and Decision Making.
Rosenbaum, P. R. and Rubin, D. B. (1983). The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1):41–55.
Santos, F. L. S. and Santis, G. C. D. (2017). Transfusao na emergencia: concentrado de hemacias. Revista QualidadeHC.
Seymour, C. W. et al. (2019). Derivation, validation, and potential treatment implications of novel clinical phenotypes for sepsis. JAMA.
Sharwardy, S. N. et al. (2019). Time series parameter prediction for ICU patient. In 22nd International Conf. on Computer and Information Technology (ICCIT).
Shashikumar, S. P. et al. (2017). Early sepsis detection in critical care patients using multiscale blood pressure and heart rate dynamics. Journal of electrocardiology, 50(6):739–743.
Smit, J. M. et al. (2023). Causal inference using observational intensive care unit data: A scoping review and recommendations for future practice. npj Digital Medicine.
Vincent, J.-L. et al. (2018). Worldwide audit of blood transfusion practice in critically ill patients. Critical Care.
Wang, D. et al. (2025). Prognostic indicators and outcome in patients with acute liver failure, sepsis and with and without shock: a retrospective cohort study. Annals of Medicine.
Xu, C. et al. (2026). Temperature trajectory in septic patients with hypothermia: When the ice begins to melt—a retrospective cohort study. Science Progress.
Yadav, S. K. et al. (2024). A contemporary review of blood transfusion in critically ill patients. Medicina.
Bolcato, M. et al. (2020). Patient blood management: The best approach to transfusion medicine risk management. Transfusion and apheresis science : official journal of the World Apheresis Association : official journal of the European Society for Haemapheresis.
Carson, J. L. et al. (2012). Red Blood Cell Transfusion: A Clinical Practice Guideline From the AABB*. Annals of Internal Medicine.
Carson, J. L. et al. (2023). Transfusion thresholds and other strategies for guiding allogeneic red blood cell transfusion. Cochrane Database of Systematic Reviews.
Christiansson, S. (2023). Straight to the heart: Classification of multi-channel ecg-signals using minirocket. Master’s thesis.
Cochrane (2019). Cochrane handbook for systematic reviews of interventions, version 6.0 (updated july 2019), chapter 15.4.4.
Dempster, A. et al. (2021). Minirocket: A very fast (almost) deterministic transform for time series classification. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.
Hébert, P. C. et al. (1999). A multicenter, randomized, controlled clinical trial of transfusion requirements in critical care. New England Journal of Medicine.
Holst, L. B. et al. (2014). Lower versus higher hemoglobin threshold for transfusion in septic shock. New England Journal of Medicine.
Hyland, S. L. et al. (2020). Early prediction of circulatory failure in the intensive care unit using machine learning. Nature medicine, 26(3):364–373.
Iwashyna, T. J. et al. (2015). Implications of heterogeneity of treatment effect for reporting and analysis of randomized trials in critical care. American Journal of Respiratory and Critical Care Medicine.
Kramer, A. H. and Zygun, D. A. (2009). Anemia and red blood cell transfusion in neuro-critical care. Critical Care. [link]
Latona, A. et al. (2025). Coagulation and transfusion informatics in chronic liver disease: a data linkage study of emergency department presentations. EJHaem.
Liu, P. et al. (2023). Subphenotyping heterogeneous patients with chronic critical illness to guide individualised fluid balance treatment using machine learning: A retrospective cohort study. eClinicalMedicine.
Liu, S. et al. (2024). Association between alkaline phosphatase to albumin ratio and mortality among patients with sepsis. Scientific reports.
Mihaylova, M. et al. (2025). Anemia in newly diagnosed cases with liver cirrhosis. Acta Medica Bulgarica.
Ngufor, C. et al. (2018). Identification of clinically meaningful plasma transfusion subgroups using unsupervised random forest clustering. AMIA Annual Symposium Proceedings.
Pearl, J. (2013). Causality: Models, Reasoning, and Inference. Cambridge University Press, 2 edition.
Robins, J. M. et al. (2000). Marginal structural models and causal inference in epidemiology. Epidemiology.
Rodrigues, D. S. et al. (2022). Predicting the outcome for covid-19 patients by applying time series classification to electronic health records. BMC Medical Informatics and Decision Making.
Rosenbaum, P. R. and Rubin, D. B. (1983). The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1):41–55.
Santos, F. L. S. and Santis, G. C. D. (2017). Transfusao na emergencia: concentrado de hemacias. Revista QualidadeHC.
Seymour, C. W. et al. (2019). Derivation, validation, and potential treatment implications of novel clinical phenotypes for sepsis. JAMA.
Sharwardy, S. N. et al. (2019). Time series parameter prediction for ICU patient. In 22nd International Conf. on Computer and Information Technology (ICCIT).
Shashikumar, S. P. et al. (2017). Early sepsis detection in critical care patients using multiscale blood pressure and heart rate dynamics. Journal of electrocardiology, 50(6):739–743.
Smit, J. M. et al. (2023). Causal inference using observational intensive care unit data: A scoping review and recommendations for future practice. npj Digital Medicine.
Vincent, J.-L. et al. (2018). Worldwide audit of blood transfusion practice in critically ill patients. Critical Care.
Wang, D. et al. (2025). Prognostic indicators and outcome in patients with acute liver failure, sepsis and with and without shock: a retrospective cohort study. Annals of Medicine.
Xu, C. et al. (2026). Temperature trajectory in septic patients with hypothermia: When the ice begins to melt—a retrospective cohort study. Science Progress.
Yadav, S. K. et al. (2024). A contemporary review of blood transfusion in critically ill patients. Medicina.
Publicado
01/06/2026
Como Citar
BRAGA, Lucas Pimenta et al.
Identificação de Fenótipos Clínicos e Desfechos da Transfusão de Hemácias em UTI Baseada em Trajetórias Fisiológicas. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 26. , 2026, Ouro Preto/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 489-500.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2026.21312.
