• Skip to main content
  • Skip to primary sidebar
Transfusion News
  • About Us
  • Topics
    • Adverse Events (non-infectious)
    • Blood Donation
    • Cell Therapy
    • Coagulation & Plasma Transfusion
    • Platelet Transfusion
    • Policy and Guidelines
    • Quality Control and Regulatory
    • RBC Transfusion
    • Serology/Genotyping
    • Special Transfusion Situations
    • Transfusion Transmitted Infections
  • Continuing Education
  • Archives
  • Podcasts
  • Question of the Day
  • Search
  • Subscribe to Email Alerts
  • Follow us on
  • Search
  • Subscribe to Email Alerts

Machine Learning-Based Algorithm to Predict Intraoperative RBC Use during Cardiothoracic Surgery

February 9, 2022

Cardiothoracic surgery patients have a high risk for hemorrhage and occasionally require massive transfusions, though most patients require 0 to 3 units of red blood cells (RBCs).  Patient blood management models commonly rely on maximum surgical blood order schedules to avoid excessive blood waste, but a more personalized prediction on the risk of surgical hemorrhage and blood use would be useful to help conserve blood resources.  To this end, researchers at the University of Utah developed a hybrid machine-learning based algorithm to predict blood usage based on data from 2410 cardiothoracic surgery patients at their institution from 2014 to 2019.  A random forest non-linear algorithm was used to determine important patient variables (extracorporeal membrane oxygenation initiation, usage, and cannulation were the top three), and then a Gaussian process regression model was used to determine the relationship between the patient variables and RBC blood usage.  This machine learning-based algorithm was validated on an additional 437 cardiothoracic surgery patients and was able to predict intraoperative RBC use with high accuracy, especially when 0 and 1-3 units of RBCs were transfused.  Additional fine tuning for higher units of RBCs and validation at other institutions is needed, but a personalized algorithm to predict blood usage during surgery may help to avoid blood wastage.

Reference:

Wang Z, Zhe S, Zimmerman J, Morrisey C, Tonna JE, Sharma V, and RA Metcalf.  Development and validation of a machine learning method to predict intraoperative red blood cell transfusions in cardiothoracic surgery.  Scientific Reports 2022; 12:  1355. 

 

Filed Under

  • News
  • RBC Transfusion

Recommended

  • Whole Blood Derived Platelet vs. Apheresis Platelets

  • RBC and Plasma Transfusions Decreased in the U.S. (2015-2018)

  • mRNA-1273 Vaccine Safe and Induces anti-SARS-CoV-2 Immune Responses

Show Comments

Comments on this article are closed.

Get the latest news. Subscribe to our mailing list. Sign Up

Primary Sidebar

Latest News

  • Artificial Intelligence to Predict Immunogenicity of Amino Acid Substitutions of Blood Group Antigens

  • Transfusion-related Alpha-Gal Syndrome

  • 2024 Serious Hazards of Transfusions (SHOT) Report in the U.K.

  • Machine Learning Model for Estimating Perioperative Transfusion Risks

    Question of the Day

    Copyright © 2025 John Wiley & Sons, Inc. All Rights Reserved.
    Privacy Policy

    Association for the Advancement of Blood and Biotherapies Wiley