Brazilian Journal of Anesthesiology
https://bjan-sba.org/article/doi/10.1016/j.bjane.2026.844782
Brazilian Journal of Anesthesiology
Review Article

Artificial intelligence in the prediction of intraoperative red blood cell transfusion in cardiac surgery: a systematic review and diagnostic test accuracy meta-analysis

Inteligência artificial na predição de transfusão de hemácias intraoperatória em cirurgia cardíaca: uma revisão sistemática e metanálise de acurácia de teste diagnóstico

Filipe Giordano Valério, Amanda Carneiro Rodrigues, Davi Ricardo Soares Gama de Amorim, Roberta Esterque Cantarino, Glauco Martins de Araujo, Jimmy Yusuf, Lecticia Vianna Leal Soares Bessa, Millena Mendonça Andrade Paes Leme, Marcella Freire de Campos Euzebio, Flávio Luiz Seixas, Alexandra Rezende Assad, Luis Antonio dos Santos Diego

http://dx.doi.org/10.1016/j.bjane.2026.844782 Braz J Anesthesiol, vol.76, n4, 844782, 2026
PDF
Downloads: 0
Views: 1

Abstract

Background

Red Blood Cell (RBC) transfusion in cardiac surgery is associated with risks. Conventional prediction scores lack accuracy, conflicting with Patient Blood Management (PBM) principles. Artificial Intelligence (AI) offers a potential avenue for developing precise, data-driven predictive models to enhance clinical decision-making and optimize patient outcomes.

Methods

A systematic review and meta-analysis of diagnostic test accuracy studies was conducted following PRISMA guidelines, searching PubMed, Embase, and Cochrane Library databases until April 2025. Studies developing AI models to predict intraoperative Red Blood Cell (RBC) transfusions in adult cardiac surgery were included. Pooled sensitivity, specificity, and Area Under the receiver operating Characteristic Curve (AUC) were calculated using a bivariate random-effects model. To summarize overall diagnostic performance, Summary Receiver Operating Characteristic curves were generated.

Results

Five studies encompassing 3,063 patients were analyzed in the meta-analysis. AI models demonstrated high pooled specificity, ranging from 86.3% (95% CI 82.8%‒89.1%) to 93.6% (95% CI 84.3%‒97.6%), whereas pooled sensitivity ranged from 50.3% (95% CI 20.9%‒79.6%) to 55.7% (95% CI 33.8%‒75.6%). AUC values ranged between 0.793 (95% CI 0.634‒0.899) and 0.892 (95% CI 0.740‒0.943). Preoperative hemoglobin levels and patient age were consistently identified as clinical predictors for intraoperative RBC transfusion.

Conclusion

This systematic review and meta-analysis suggests that AI models may have potential for predicting intraoperative RBC transfusion in cardiac surgery, with consistently high specificity but only moderate sensitivity. However, given the low certainty of evidence, substantial heterogeneity, and reliance on non-standardized transfusion practices, these findings should be interpreted cautiously.

Keywords

Algorithms; Artificial intelligence; Blood transfusion; Cardiac surgical procedures; Erythrocyte transfusion; Prediction algorithms

Resumo

Introdução

A transfusão de hemácias em cirurgia cardíaca está associada a riscos. Os escores de predição convencionais carecem de acurácia, entrando em conflito com os princípios do Patient Blood Management (PBM). A Inteligência Artificial (IA) oferece um caminho potencial para o desenvolvimento de modelos preditivos precisos e baseados em dados para aprimorar a tomada de decisão clínica e otimizar os desfechos dos pacientes.

Métodos

Uma revisão sistemática e metanálise de estudos de acurácia de teste diagnóstico foi conduzida seguindo as diretrizes PRISMA, com buscas nas bases de dados PubMed, Embase e Cochrane Library até abril de 2025. Foram incluídos estudos que desenvolveram modelos de IA para predizer transfusões intraoperatórias de hemácias em cirurgia cardíaca de adultos. A sensibilidade, especificidade e a área sob a curva característica de operação do receptor (AUC) combinadas foram calculadas usando um modelo bivariado de efeitos aleatórios. Para resumir o desempenho diagnóstico geral, curvas características de operação do receptor resumidas (SROC) foram geradas.

Resultados

Cinco estudos abrangendo 3.063 pacientes foram analisados na metanálise. Os modelos de IA demonstraram alta especificidade combinada, variando de 86,3% (IC 95% 82,8%–89,1%) a 93,6% (IC 95% 84,3%–97,6%), enquanto a sensibilidade combinada variou de 50,3% (IC 95% 20,9%–79,6%) a 55,7% (IC 95% 33,8%–75,6%). Os valores de AUC variaram entre 0,793 (IC 95% 0,634–0,899) e 0,892 (IC 95% 0,740–0,943). Os níveis de hemoglobina pré-operatória e a idade do paciente foram consistentemente identificados como preditores clínicos para transfusão de hemácias intraoperatória.

Conclusão

Esta revisão sistemática e metanálise sugere que os modelos de IA podem ter potencial para predizer a transfusão de hemácias intraoperatória em cirurgia cardíaca, com especificidade consistentemente alta, mas sensibilidade apenas moderada. No entanto, dada a baixa certeza da evidência, a heterogeneidade substancial e a dependência de práticas de transfusão não padronizadas, esses achados devem ser interpretados com cautela.

Palavras-chave

Algoritmos; Inteligência artificial; Transfusão de sangue; Procedimentos cirúrgicos cardíacos; Transfusão de eritrócitos; Algoritmos de predição

References

1. Zhou R, Li Z, Liu J, et al. Prediction of intraoperative red blood cell transfusion in valve replacement surgery: machine learning algorithm development based on non-anemic cohort. Front Cardiovasc Med. 2024;11:1344170.

2. Cunha CBC, Lima TA, Ferraz DLM, et al. Predicting the Need for Blood Transfusions in Cardiac Surgery: A Comparison between Machine Learning Algorithms and Established Risk Scores in the Brazilian Population. Braz J Cardiovasc Surg. 2024. https://doi.org/10.21470/1678-9741-2023-0212.

3. Chen C, Wang Y, Yang X, et al. Machine Learning-Based Prediction of Intraoperative Red Blood Cell Transfusion in Aortic Valve Replacement Surgery. Clin Lab. 2024;70:709−17.

4. Liu S, Zhou R, Xia X-Q, et al. Machine learning models to predict red blood cell transfusion in patients undergoing mitral valve surgery. Ann Transl Med. 2021;9. 530-530.

5. Hung M, Besser M, Sharples LD, Nair SK, Klein AA. The prevalence and association with transfusion, intensive care unit stay and mortality of pre-operative anaemia in a cohort of cardiac surgery patients*. Anaesthesia. 2011;66:812−8.

6. Sun Z, Cui Z, Xie Y, et al. Evaluation of the Factors Influencing Blood Transfusion during Minimally Invasive Direct Coronary Artery Bypass Surgery. Cardiology. 2025;150:98−109.

7. Cespedes IC, Figueiredo MS, Hossne Junior NA, et al. Patient Blood Management Program Implementation: Comprehensive Recommendations and Practical Strategies. Braz J Cardiovasc Surg. 2024;39:e20240205.

8. Shander A, Hardy JF, Ozawa S, et al. A Global Definition of Patient Blood Management. Anesth Analg. 2022;135:476−88.

9. Boer C, Meesters MI, Milojevic M, et al. 2017 EACTS/EACTA Guidelines on patient blood management for adult cardiac surgery. J Cardiothorac Vasc Anesth. 2018;32:88−120.

10. Hassan J, Abbas M, Shaukat M, et al. Assessing operative mortality risk in cardiothoracic surgery: analysis of STS scores − a retrospective study. Cardiothorac Surg. 2025;33:18.

11. Nashef SAM, Roques F, Sharples LD, Nilsson J, Smith C, Goldstone AR, et al. EuroSCORE II. Eur J Cardiothorac Surg. 2012;41 (4):734−44. discussion 744-745.

12. Alghamdi AA, Davis A, Brister S, Corey P, Logan A. Development and validation of Transfusion Risk Understanding Scoring Tool (TRUST) to stratify cardiac surgery patients according to their blood transfusion needs. Transfusion (Paris). 2006;46:1120−9.

13. Chen S, Liu LP, Wang YJ, et al. Advancing Prediction of Risk of Intraoperative Massive Blood Transfusion in Liver Transplantation With Machine Learning Models. A Multicenter Retrospective Study. Front Neuroinformatics. 2022;16:893452. -893452.

14. Deeks JJ, Bossuyt PM, Leeflang MM, Takwoingi Y. Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy. 1st edition Chichester (UK): John Wiley & Sons; 2023.

15. Higgins JPT, Thomas J, Chandler J, et al. Cochrane Handbook for Systematic Reviews of Interventions editor(s). 2nd Edition Chichester (UK): John Wiley & Sons; 2019.

16. Salameh JP, Bossuyt PM, McGrath TA, et al. Preferred reporting items for systematic review and meta-analysis of diagnostic test accuracy studies (PRISMA-DTA): explanation, elaboration, and checklist. BMJ. 2020;370:m2632.

17. Ouzzani M, Hammady H, Fedorowicz Z, Elmagarmid A. Rayyan-a web and mobile app for systematic reviews. Syst Rev. 2016;5:210.

18. Wolff RF, Moons KGM, Riley RD, et al. PROBAST: A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies. Ann Intern Med. 2019;170:51−8.

19. Schunemann HJ, Higgins JPT, Vist GE, et al. GRADE handbook for grading quality of evidence and strength of recommendations. Cochrane handbook for systematic reviews of interventions. p 375, 2nd ed. Chichester (UK): John Wiley & Sons; 2019. p. 375 −402.

20. Luo D, Wan X, Liu J, Tong T. Optimally estimating the sample mean from the sample size, median, mid-range, and/or mid-quartile range. Stat Methods Med Res. 2018;27: 1785−805.

21. Wan X, Wang W, Liu J, Tong T. Estimating the sample mean and standard deviation from the sample size, median, range and/or interquartile range. BMC Med Res Methodol. 2014;14:135.

22. Posit team. RStudio: Integrated Development Environment for R. Posit Software. Boston, MA: PBC; 2025. Retrieved from http://www.posit.co/.

23. Philipp Doebler. mada: Meta-Analysis of Diagnostic Accuracy Retrieved from https://cran.r-project.org/package=mada;2025.

24. Balduzzi S, Rucker G, Schwarzer G. How to perform a meta- analysis with R: a practical tutorial. Evid Based Ment Health. 2019;22:153−60.

25. Reitsma JB, Glas AS, Rutjes AWS, Scholten RJPM, Bossuyt PM, Zwinderman AH. Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. J Clin Epidemiol. 2005;58:982−90.

26. Rutter CM, Gatsonis CA. A hierarchical regression approach to meta-analysis of diagnostic test accuracy evaluations. Stat Med. 2001;20:2865−84.

27. Harbord RM, Deeks JJ, Egger M, Whiting P, Sterne JAC. A unification of models for meta-analysis of diagnostic accuracy studies. Biostatistics. 2007;8:239−51.

28. Zhou Y, Dendukuri N. Statistics for quantifying heterogeneity in univariate and bivariate meta-analyses of binary data: the case of meta-analyses of diagnostic accuracy. Stat Med. 2014;33: 2701−17.

29. Ponce-Bobadilla AV, Schmitt V, Maier CS, Mensing S, Stodtmann S. Practical guide to SHAP analysis: Explaining supervised machine learning model predictions in drug development. Clin Transl Sci. 2024;17:e70056.

30. Kaneko H. Cross-validated permutation feature importance considering correlation between features. Anal Sci Adv. 2022;3:278−87.

31. McKenna SLB, Dohoo IR. Using and interpreting diagnostic tests. Vet Clin North Am Food Anim Pract. 2006;22:195−205.

32. Mirza FG, Abdul-Kadir R, Breymann C, Fraser IS, Taher A. Impact and management of iron deficiency and iron deficiency anemia in women’s health. Expert Rev Hematol. 2018;11:727−36.

33. Leff J, Romano CA, Gilbert S, Nair S. Validation Study of the Transfusion Risk and Clinical Knowledge (TRACK) Tool in Cardiac Surgery Patients: A Retrospective Analysis. J Cardiothorac Vasc Anesth. 2019;33:2669−75.

34. Ranucci M, Aronson S, Dietrich W, et al. Patient blood management during cardiac surgery: Do we have enough evidence for clinical practice? J Thorac Cardiovasc Surg. 2011;142:249.e1 −249.e32.

35. Clevenger B, Mallett SV, Klein AA, Richards T. Patient blood management to reduce surgical risk. Br J Surg. 2015;102: 1325−37.

36. Butcher A, Richards T. Cornerstones of patient blood management in surgery. Transfus Med. 2018;28:150−7.

37. Collins GS, Reitsma JB, Altman DG, Moons KGM. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD Statement. BMC Med. 2015;13:1−10.

Submitted date:
10/10/2025

Accepted date:
06/14/2026

6a635a44a9539566255f6f43 rba Articles
Links & Downloads
2352-2291 (Electronic) 0104-0014 (Printed)
Braz J Anesthesiol ©2026 All rights reserved for this website content. Articles follow their own licenses.

Braz J Anesthesiol

Share this page
Page Sections