EUVIMEDEUVIMED entdecken
Crossref

Machine Learning Based Prediction of 28-Day Mortality in ECMO Patients: A Pilot Study Using MIMIC-IV Database

Li Zhe iD, Qiu Guozheng, Duan Wenlong, Shi Lei, Chen Shengxin, Lyu Liwen

The American Surgeon™ · 2026

DOI: 10.1177/00031348251394273 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The American Surgeon™, 2026. Verfasst von Li Zhe und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Emergency, Guangxi Academy of Medical Sciences, The People's Hospital of Guangxi Zhuang Autonomous Region, Nanning, China. Hauptthemen laut MEDLINE: Extracorporeal Membrane Oxygenation, Machine Learning, Respiratory Insufficiency. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Natural Science Foundation of Guangxi Zhuang Autonomous Region, Guangxi Medical Health Appropriate Technology Development Promotion Application Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Extracorporeal membrane oxygenation (ECMO) is a critical life-sustaining intervention for patients with severe cardiac or respiratory failure. Predicting outcomes for ECMO patients remains challenging due to the dynamic and complex nature of ECMO therapy. Machine learning (ML) has emerged as a powerful tool for improving prognostication in critical care by integrating large volumes of clinical data to identify complex, nonlinear relationships between variables. Its ability to model complex interactions holds promise for more accurate and personalized risk assessments in ECMO patients.

Methods

This retrospective study utilized data from the MIMIC-IV v3.1 database, including 162 ECMO-treated patients, to develop machine learning models for predicting 28-day mortality. LASSO regression was first used for feature selection, after which machine learning algorithms, such as logistic regression, Random Forest, XGBoost, decision tree, and support vector machine (SVM), were applied. Model performance was evaluated using area under the curve (AUC), calibration curves, and decision curve analysis (DCA).

Results

The Random Forest model achieved the highest performance with an AUC of 0.852 (95% CI: 0.745-0.959), outperforming other models. Key predictors identified through LASSO included ACT, age, and MAP, all of which were significantly associated with 28-day mortality. DCA indicated that the Random Forest model provided substantial net clinical benefit, supporting its utility in real-world decision-making.

Conclusion

Machine learning models, particularly Random Forest, demonstrate substantial potential for improving the prediction of mortality in ECMO patients. By integrating dynamic clinical variables, ML offers a more accurate and individualized approach to risk stratification in this critically ill population. Future research should focus on multi-center validation, the inclusion of genomic data, and the development of time-series models to further enhance predictive performance and clinical applicability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Extracorporeal Membrane OxygenationMachine LearningRespiratory InsufficiencyHumansRetrospective StudiesFemaleMaleMiddle AgedPilot ProjectsDatabases, FactualRisk AssessmentAdultAgedPrognosis

Stichwörter der Autor:innen

28-day mortalityMIMIC-IV databaseextracorporeal membrane oxygenation (ECMO)machine learningrandom forest

Autor:innen und Institutionen

  • Department of Emergency, Guangxi Academy of Medical Sciences, The People's Hospital of Guangxi Zhuang Autonomous Region, Nanning, China.

ORCID-Profile: Li Zhe

Förderung

  • Natural Science Foundation of Guangxi Zhuang Autonomous Region
  • Guangxi Medical Health Appropriate Technology Development Promotion Application Project

Zitieren

APA

Zhe, L., Guozheng, Q., Wenlong, D., Lei, S., Shengxin, C., & Liwen, L. (2026). Machine Learning Based Prediction of 28-Day Mortality in ECMO Patients: A Pilot Study Using MIMIC-IV Database. The American Surgeon™. https://doi.org/10.1177/00031348251394273

Vancouver

Zhe L, Guozheng Q, Wenlong D, Lei S, Shengxin C, Liwen L. Machine Learning Based Prediction of 28-Day Mortality in ECMO Patients: A Pilot Study Using MIMIC-IV Database. The American Surgeon™. 2026. doi:10.1177/00031348251394273

BibTeX
@article{Zhe2026,
  author = {Zhe, Li and Guozheng, Qiu and Wenlong, Duan and Lei, Shi and Shengxin, Chen and Liwen, Lyu},
  title = {Machine Learning Based Prediction of 28-Day Mortality in ECMO Patients: A Pilot Study Using MIMIC-IV Database},
  journal = {The American Surgeon™},
  year = {2026},
  doi = {10.1177/00031348251394273}
}
Kostenlos starten →