EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Early prediction of transfusion requirements in trauma patients using explainable machine learning

Michael R De La Rosa iD, Alexander Bowers, Brian Eastridge, Min Wang, Donald Jenkins

Transfusion · 2026

DOI: 10.1111/trf.70106 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transfusion, 2026. Verfasst von Michael R De La Rosa und 4 weiteren Autor:innen. Beteiligte Einrichtung: Joe R. & Teresa Lozano Long School of Medicine, University of Texas San Antonio, San Antonio, Texas, USA. Hauptthemen laut MEDLINE: Blood Transfusion, Wounds and Injuries, Machine Learning, Shock, Hemorrhagic. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Hemorrhagic shock is the most common preventable cause of death in trauma patients. Early transfusion significantly improves survivability in patients suffering from hemorrhagic shock. We hypothesized that machine learning models could reduce time to initial transfusion by more rapidly identifying patients likely to require blood products. Study Design and Methods We conducted a retrospective model‐development and internal‐validation study using the Trauma Quality Improvement Program (TQIP) dataset from 2019 to 2022. Adult patients aged 18 years or older were included; the only exclusion criterion was missing transfusion outcome data. Models evaluated included logistic regression, ridge regression, Least Absolute Shrinkage and Selection Operator (LASSO), Random Forest, and extreme gradient boosting (XGBoost) assessed using an 80/20 train–test split. Five‐fold cross‐validation was used for hyperparameter tuning. Area under the receiver operating characteristic curve (AUROC) was used for model optimization.

Results

A total of 1,232,956 patients were included, of whom 109,819 (8.9%) received transfusions. XGBoost achieved the highest AUROC (0.8452). With a decision threshold of 0.0816 selected by maximizing balanced accuracy on the test set, accuracy was 0.7298, sensitivity was 0.7927, and specificity was 0.7236. SHapley Additive exPlanations (SHAP) values showed that Injury Severity Score, systolic blood pressure, activation level, pulse rate, and age were the most influential predictors.

Discussion

XGBoost demonstrated strong predictive performance using only arrival‐time variables, and SHAP explanations offered clinically intuitive reasoning. These characteristics highlight the model's potential as a rapid decision‐support tool, although external validation remains an important next step.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Blood TransfusionWounds and InjuriesMachine LearningShock, HemorrhagicHumansFemaleRetrospective StudiesAdultMaleMiddle AgedBoosting Machine Learning AlgorithmsPredictive Learning ModelsRandom ForestROC Curve

Stichwörter der Autor:innen

XGBoostclinical decision supportexplainable artificial intelligencemachine learningtransfusiontrauma

Autor:innen und Institutionen

  • Joe R. & Teresa Lozano Long School of Medicine, University of Texas San Antonio, San Antonio, Texas, USA.
  • Department of Surgery, University of Texas at San Antonio, San Antonio, Texas, USA.
  • Department of Statistics and Data Science, The University of Texas at San Antonio, San Antonio, Texas, USA.

ORCID-Profile: Michael R De La Rosa

Zitieren

APA

De La Rosa, M. R., Bowers, A., Eastridge, B., Wang, M., & Jenkins, D. (2026). Early prediction of transfusion requirements in trauma patients using explainable machine learning. Transfusion. https://doi.org/10.1111/trf.70106

Vancouver

De La Rosa MR, Bowers A, Eastridge B, Wang M, Jenkins D. Early prediction of transfusion requirements in trauma patients using explainable machine learning. Transfusion. 2026. doi:10.1111/trf.70106

BibTeX
@article{DeLaRosa2026,
  author = {De La Rosa, Michael R and Bowers, Alexander and Eastridge, Brian and Wang, Min and Jenkins, Donald},
  title = {Early prediction of transfusion requirements in trauma patients using explainable machine learning},
  journal = {Transfusion},
  year = {2026},
  doi = {10.1111/trf.70106}
}
Kostenlos starten →