Skip to main content
Springer Nature Link
Log in

Predicting blood transfusions for coronary artery bypass graft patients using deep neural networks and synthetic data

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Coronary Artery Bypass Graft (CABG) is a common cardiac surgery, but it continues to have many associated risks, including the need for blood transfusions. Previous research has shown that blood transfusion during CABG surgery is associated with an increased risk for infection and mortality. The current study aims to use modern techniques, such as deep neural networks and data synthesis, to develop models that can best predict the need for blood transfusion among CABG patients. Results show that neural networks with synthetic data generated by DataSynthesizer have the best performance. Implications of results and future directions are discussed.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

The data utilized in this study are not publicly available. The Participant Use Data File (PUF) is a Health Insurance Portability and Accountability Act (HIPAA)-compliant data file containing cases submitted to the American College of Surgeons National Surgical Quality Improvement Program (ACS NSQIP). PUF access is reserved for participating staff and hospitals. Requests for participation can be made directly to ACS, where the individual requests will be reviewed, and data can be downloaded upon approval. Please refer to the ACS NSQIP website at: https://www.facs.org/quality-programs/dataand-registries/acs-nsqip/participant-use-data-file/.

References

  1. Horvath K, Acker M, Chang H, Bagiella E et al (2013) Blood transfusion and infection after cardiac surgery. Ann Thorac Surg 95(6):2194–2201. https://doi.org/10.1016/j.athoracsur.2012.11.078

    Article  Google Scholar 

  2. Kaur D, Sobiesk M, Patil S, Liu J, Bhagat P, Gupta A, Markuzon N (2021) Application of Bayesian networks to generate synthetic health data. J Am Med Inform Assoc 28(4):801–811. https://doi.org/10.1093/jamia/ocaa303

    Article  Google Scholar 

  3. Li Q, Lv H, Chen Y, Shen J, Shi J, Zhou C (2024) Development and validation of a machine learning prediction model for perioperative red blood cell transfusions in cardiac surgery. Int J Med Inform 184:105343. https://doi.org/10.1016/j.ijmedinf.2024.105343

    Article  Google Scholar 

  4. Mufarrih S, Mahmood F, Qureshi N, Yunus R, Matyal R et al (2023) Timing of blood transfusions and 30-days patient outcomes after coronary artery bypass graft surgery. J Cardiothorac Vasc Anesth 37(3):382–391. https://doi.org/10.1053/j.jvca.2022.11.029

    Article  Google Scholar 

  5. Gao Y, Liu X, Wang L, Wang S, Yu Y, Ding Y, Wang J, Ao H (2022) Machine learning algorithms to predict major bleeding after isolated coronary artery bypass grafting. Front Cardiovasc Med 9:881881. https://doi.org/10.3389/fcvm.2022.881881

    Article  Google Scholar 

  6. Tschoellitsch T, Bock C, Mahecic T, Hofmann A, Meier J (2022) Machine learning-based prediction of massive perioperative allogeneic blood transfusion in cardiac surgery. Eur J Anaesthesiol 39(9):766–773. https://doi.org/10.1097/EJA.0000000000001721

    Article  Google Scholar 

  7. Hagan MT, Demuth HB, Beale MH, De Jesús O (2014) Neural network design (2nd Edition). https://hagan.okstate.edu/NNDesign.pdf

  8. Wu YC, Feng JW (2018) Development and application of artificial neural network. Wirel Pers Commun 102:1645–1656. https://doi.org/10.1007/s11277-017-5224-x

    Article  Google Scholar 

  9. McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biol 5:115–133. https://doi.org/10.1007/BF02478259

    Article  MathSciNet  Google Scholar 

  10. Macukow B (2016) Neural networks – state of art, brief history, basic models and architecture. CISIM 9:3–14. https://doi.org/10.1007/978-3-319-45378-1_1

    Article  Google Scholar 

  11. Carpenter GA, Grossberg S (1987) A massively parallel architecture for a self-organizing neural pattern recognition machine. Comput Vis Image Proc 37(1):54–115. https://doi.org/10.1016/S0734-189X(87)80014-2

    Article  Google Scholar 

  12. Schmidhuber S, Hochreiter J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735

    Article  Google Scholar 

  13. Borisov V, Leemann T, Seßler K, Haug J, Pawelczyk M, Kasneci G (2022) Deep neural networks and tabular data: a survey. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/TNNLS.2022.3229161

    Article  Google Scholar 

  14. Gorishniy Y, Rubachev I, Khrulkov V, Babenko A (2021) Revisiting deep learning models for tabular data. arXiv. https://doi.org/10.48550/arXiv.2106.11959

  15. Shwartz-Ziv R, Armon A (2021) Tabular data: deep learning is not all you need. arXiv. https://doi.org/10.48550/arXiv.2106.03253

  16. Sánchez-Morales A, Sancho-Gómez JL, Martínez-García JA et al (2020) Improving deep learning performance with missing values via deletion and compensation. Neural Comput Applic 32:13233–13244. https://doi.org/10.1007/s00521-019-04013-2

    Article  Google Scholar 

  17. Xu L, Veeramachaneni K (2018) Synthesizing tabular data using generative adversarial networks. arXiv. https://doi.org/10.48550/arXiv.1811.11264

  18. Zhu Y, Brettin T, Xia F, Partin A, Shukla M, Yoo H, Evrard YA (2021) Converting tabular data into images for deep learning with convolutional neural networks. Sci Rep 11(1):14036. https://doi.org/10.1038/s41598-021-93376-5

    Article  Google Scholar 

  19. Hancock JT, Khoshgoftaar TM (2020) Survey on categorical data for neural networks. J Big Data 7:28. https://doi.org/10.1186/s40537-020-00305-w

    Article  Google Scholar 

  20. Fitkov-Norris E, Vahid S, Hand C (2012) Evaluating the impact of categorical data encoding and scaling on neural network classification performance: the case of repeat consumption of identical cultural goods. Eng Appl Neural Netw. https://doi.org/10.1007/978-3-642-32909-8_35

    Article  Google Scholar 

  21. Shavitt I, Segal E (2018) Regularization learning networks deep learning for tabular datasets. Neural Inform Process Syst https://doi.org/10.48550/arXiv.1805.06440

  22. Katzir L, Elidan G, El-Yaniv R (2021) Net-DNF: effective deep modeling of tabular data. Int Conf Learn Rep

  23. Popov S, Morozov S, Babenko A (2019) Neural oblivious decision ensembles for deep learning on tabular data. arXiv. https://doi.org/10.48550/arXiv.1909.06312

  24. Somepalli G, Goldblum M, Schwarzschild A, Bruss CB, Goldstein T (2021) SAINT: Improved neural networks for tabular data via row attention and contrastive pre-training. arXiv. https://doi.org/10.48550/arXiv.2106.01342

  25. Clements JM, Xu D, Yousefi N, Efimov D (2020) Sequential deep learning for credit risk monitoring with tabular financial data. arXiv. https://doi.org/10.48550/arXiv.2012.15330

  26. Young J, Graham P, Penny R (2009) Using Bayesian networks to create synthetic data. J Off Stat 25(4):549–567

    Google Scholar 

  27. Di Zio M, Scanu M, Coppola L, Luzi O, Ponti A (2004) Bayesian networks for imputation. J R Stat Soc 167:309–322

    Article  MathSciNet  Google Scholar 

  28. Baowaly M, Lin C, Liu C, Chen K (2019) Synthesizing electronic health records using improved generative adversarial networks. J Am Med Inform Assoc 26(3):228–241. https://doi.org/10.1093/jamia/ocy142

    Article  Google Scholar 

  29. Ping H, Stoyanovich J, Howe B (2017) DataSynthesizer: privacy-preserving synthetic datasets. Int Conf Sci Stat Database Manage. https://doi.org/10.1145/3085504.3091117

    Article  Google Scholar 

  30. Zhang J, Cormode G, Procopiuc C, Strivastava D, Xiao X (2014) PrivBayes: private data release via bayesian networks. SIGMOD Int Conf Manage Data 42(4):1–41

    MathSciNet  Google Scholar 

  31. Solatorio A, Dupriez O (2023) REaLTabFormer: Generating realistic and tabular data using Transformers. arXiv. https://doi.org/10.48550/arxiv.2302.02041

  32. Padhi I, Schiff Y, Melnyk I, Rigotti M, Mroueh Y, Dognin P, Ross J, Nair R, Altman E (2021) Tabular transformers for modeling multivariate time series. IEEE. https://doi.org/10.1109/ICASSP39728.2021.9414142

    Article  Google Scholar 

Download references

Acknowledgments

Special thanks to the Data Science program at George Washington University, who provided the Capstone project opportunity and brought all the authors together to work on this research.

Funding

No funding was received to assist with the preparation of this manuscript.

Author information

Authors and Affiliations

  1. Data Science, George Washington University, Washington, DC, USA

    Hsiao-Tien Tsai, Jichong Wu & Amir Jafari

  2. Department of Anesthesiology and Critical Care Medicine, George Washington University School of Medicine and Health Sciences, Washington, DC, USA

    Puneet Gupta & Eric R. Heinz

Authors
  1. Hsiao-Tien Tsai
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Jichong Wu
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Puneet Gupta
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Eric R. Heinz
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Amir Jafari
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Professor Amir Jafari is the advisor of this research project, overseeing the entire project and providing guidance in data science/neural networks. Hsiao-Tien Tsai conducted data preprocessing, EDA, synthetic data generation, FNN modeling, and the related write-ups, as well as discussions and conclusion. Jichong Wu conducted the literature review in neural networks and performed CNN modeling and the related write-ups. Dr. Puneet Gupta and Dr. Eric R Heinz contributed to the literature review in cardiac surgery and blood transfusions and also served as the subject matter experts on the medical aspect of the project.

Corresponding author

Correspondence to Hsiao-Tien Tsai.

Ethics declarations

Conflict of interest

The authors have declared no conflicts of interest in this work.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tsai, HT., Wu, J., Gupta, P. et al. Predicting blood transfusions for coronary artery bypass graft patients using deep neural networks and synthetic data. Neural Comput & Applic 36, 21153–21162 (2024). https://doi.org/10.1007/s00521-024-10309-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-024-10309-9

Keywords