English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Objective: Blood transfusions, crucial in managing anemia and coagulopathy inICU settings, require accurate prediction for effective resource allocation andpatient risk assessment. However, existing clinical decision support systemshave primarily targeted a particular patient demographic with unique medicalconditions and focused on a single type of blood transfusion. This study aimsto develop an advanced machine learning-based model to predict the probabilityof transfusion necessity over the next 24 hours for a diverse range ofnon-traumatic ICU patients.  Methods: We conducted a retrospective cohort study on 72,072 adultnon-traumatic ICU patients admitted to a high-volume US metropolitan academichospital between 2016 and 2020. We developed a meta-learner and various machinelearning models to serve as predictors, training them annually with four-yeardata and evaluating on the fifth, unseen year, iteratively over five years.  Results: The experimental results revealed that the meta-model surpasses theother models in different development scenarios. It achieved notableperformance metrics, including an Area Under the Receiver OperatingCharacteristic (AUROC) curve of 0.97, an accuracy rate of 0.93, and an F1-scoreof 0.89 in the best scenario.  Conclusion: This study pioneers the use of machine learning models forpredicting blood transfusion needs in a diverse cohort of critically illpatients. The findings of this evaluation confirm that our model not onlypredicts transfusion requirements effectively but also identifies keybiomarkers for making transfusion decisions.

Robust Meta-Model for Predicting the Need for Blood Transfusion in Non-traumatic ICU Patients