Machine learning‐based prediction of bleeding risk in extracorporeal membrane oxygenation patients using transfusion as a surrogate marker
Transfusion · 2025-06 · 65 (6) · 1051-1060
DOI: 10.1111/trf.18261 ↗At a glance
Journal article in Transfusion, 2025-06. Written by Tadashi Kamio and 6 co-authors. Institution: Department of Anesthesiology and Critical Care Medicine, Jichi Medical University Saitama Medical Center, Saitama, Japan. Major MEDLINE topics: Extracorporeal Membrane Oxygenation, Machine Learning, Hemorrhage, Erythrocyte Transfusion. Cited 6 times so far (Crossref); 27 references. The full text is freely available (open access, CC BY-NC-ND 4.0).
Abstract (original language)
Background
The increasing use of extracorporeal membrane oxygenation (ECMO) has highlighted challenges in managing bleeding complications. Optimal transfusion strategies remain uncertain for this diverse patient group, necessitating accurate predictive tools. This study developed and validated a machine learning (ML) algorithm to predict bleeding complications in patients with ECMO, using red blood cell (RBC) transfusion as a surrogate marker.
Methods
Data from the Tokushukai Medical Database (2018–2022), covering 71 hospitals, were used. An ML approach was employed to predict bleeding complications, using RBC transfusion events as a surrogate marker. Model performance was evaluated using precision, recall, F1 score, and accuracy. SHapley Additive exPlanations (SHAP) analysis was conducted to identify key factors influencing model predictions.
Results
Out of 470 ECMO‐treated intensive care unit patients, 357 were included for model development. Forty‐seven variables were used, with the light gradient boosting machine (LightGBM) and random forest models performing better than the other models, with receiver operating characteristic (ROC) area under the curve (AUC) above 0.7 for both (accuracy: 70.5%, ROC AUC: 0.703, recall: 0.784, and ROC AUC: 0.705, respectively). Models such as extreme gradient boosting performed similarly, while support vector classification had the lowest performance. SHAP analysis identified circulating blood volume, hemoglobin, and weight as the most important predictive factors.
Discussion
The LightGBM and Random Forest models effectively predict bleeding complications in patients with ECMO, using RBC transfusion as a surrogate marker. This tool can support early identification of high‐risk patients and improve overall transfusion management.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Department of Anesthesiology and Critical Care Medicine, Jichi Medical University Saitama Medical Center, Saitama, Japan.
- Division of Critical Care, Shonan Kamakura General Hospital, Kamakura, Kanagawa, Japan.
- Terumo Corporation, Shonan Center, Nakai-machi, Kanagawa, Japan.
ORCID profiles: Tadashi Kamio, Kiyomitsu Fukaguchi
Cite
APA
Kamio, T., Ikegami, M., Mizuno, M., Ishii, S., Tajima, H., Machida, Y., & Fukaguchi, K. (2025). Machine learning‐based prediction of bleeding risk in extracorporeal membrane oxygenation patients using transfusion as a surrogate marker. Transfusion. https://doi.org/10.1111/trf.18261
Vancouver
Kamio T, Ikegami M, Mizuno M, Ishii S, Tajima H, Machida Y, et al. Machine learning‐based prediction of bleeding risk in extracorporeal membrane oxygenation patients using transfusion as a surrogate marker. Transfusion. 2025. doi:10.1111/trf.18261
BibTeX
@article{Kamio2025,
author = {Kamio, Tadashi and Ikegami, Masaru and Mizuno, Megumi and Ishii, Seiichiro and Tajima, Hayato and Machida, Yoshihito and Fukaguchi, Kiyomitsu},
title = {Machine learning‐based prediction of bleeding risk in extracorporeal membrane oxygenation patients using transfusion as a surrogate marker},
journal = {Transfusion},
year = {2025},
doi = {10.1111/trf.18261}
}
EUVIMED