EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 3.0

Predictive machine learning model in intensive care unit patients with acute-on-chronic liver failure and two or more organ failures

Yee Hui Yeo, Mengyi Zhang, Martin S McCoy, Jian Zu, Yingli He, Yi Liu, Juan Li, Taotao Yan, Yuan Wang, Hirsh D Trivedi, Ju Dong Yang, Vinay Sundaram und 5 weitere

Clinical and Molecular Hepatology · 2025

DOI: 10.3350/cmh.2025.0573 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Clinical and Molecular Hepatology, 2025. Verfasst von Yee Hui Yeo und 16 weiteren Autor:innen. Beteiligte Einrichtung: Karsh Division of Gastroenterology and Hepatology, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA. Hauptthemen laut MEDLINE: Acute-On-Chronic Liver Failure, Machine Learning, Multiple Organ Failure. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 3.0). Gefördert von: National Natural Science Foundation of China, Shaanxi Province "Three Qin Scholars" Innovation Team Project, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Aims: Prediction of short-term mortality in patients with acute-on-chronic liver failure (ACLF) admitted to the intensive care unit (ICU) may enhance effective management.

Methods

To develop, explain, and validate a predictive machine learning (ML) model for short-term mortality in patients with ACLF with two or more organ failures (OFs). Utilizing a large ICU cohort with detailed clinical information, we identified ACLF patients with two or more OFs according to the EASL-CLIF and NACSELD definitions. ML model was developed for each definition to predict 30-day mortality. The Shapley value was estimated to explain the models. Validation and calibration of these models were performed.

Results

Of 5,994 patients with cirrhosis admitted to ICU, 1,511 met NACSELD criteria, and 1,692 met EASL-CLIF grade II or higher criteria. The CatBoost ACLF (CBA) model had the greatest accuracy in the NACSELD cohort (area under curve [AUC] of 0.87), while the Random Forest ACLF (RFA) model performed best in the EASL-CLIF cohort (AUC of 0.83). Both models showed robust calibration. The models were explained by SHAP score analysis, yielding a rank list, and the top twelve predictors were selected. Both simplified models demonstrated similar performance (CBA model: AUC 0.89, RFA model: AUC 0.81) and significantly outperformed contemporary scoring systems, including CLIF-C ACLF and MELD 3.0. The models were validated in both internal and external cohorts. A simple-to-use online tool was created to predict mortality rates.

Conclusions

We presented explainable, well-validated, and calibrated predictive models for ACLF patients with two or more OFs, which outperformed existing predictive scores.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Acute-On-Chronic Liver FailureMachine LearningMultiple Organ FailureHumansIntensive Care UnitsFemaleMiddle AgedMaleAgedROC CurveArea Under CurveAdultLiver CirrhosisCohort Studies

Stichwörter der Autor:innen

CirrhosisEASL-CLIF criteriaIntensive careNACSELD criteriaOrgan failure

Autor:innen und Institutionen

  • Karsh Division of Gastroenterology and Hepatology, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
  • School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China.
  • Department of Internal Medicine B, University of Münster, Münster, Germany.
  • Department of Infectious Diseases, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
  • Department of Hepatology and Infectious Diseases, The Second Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
  • Comprehensive Transplant Center, Cedars-Sinai Medical Center, Los Angeles, CA, USA.

Förderung

  • National Natural Science Foundation of China
  • Shaanxi Province "Three Qin Scholars" Innovation Team Project
  • Fundamental Research Funds for the Central Universities
  • Health and Wellness Scientific Research and Innovation Project of Shaanxi Province
  • Shaanxi Province “Three Qin Scholars” Innovation Team Project

Zitieren

APA

Yeo, Y. H., Zhang, M., McCoy, M. S., Zu, J., He, Y., Liu, Y., Li, J., Yan, T., Wang, Y., Trivedi, H. D., Yang, J. D., Sundaram, V., Sun, X., Cao, Z., Wu, C. Y., Trebicka, J., & Ji, F. (2025). Predictive machine learning model in intensive care unit patients with acute-on-chronic liver failure and two or more organ failures. Clinical and Molecular Hepatology. https://doi.org/10.3350/cmh.2025.0573

Vancouver

Yeo YH, Zhang M, McCoy MS, Zu J, He Y, Liu Y, et al. Predictive machine learning model in intensive care unit patients with acute-on-chronic liver failure and two or more organ failures. Clinical and Molecular Hepatology. 2025. doi:10.3350/cmh.2025.0573

BibTeX
@article{Yeo2025,
  author = {Yeo, Yee Hui and Zhang, Mengyi and McCoy, Martin S and Zu, Jian and He, Yingli and Liu, Yi and Li, Juan and Yan, Taotao and Wang, Yuan and Trivedi, Hirsh D and Yang, Ju Dong and Sundaram, Vinay and Sun, Xiaodan and Cao, Zhujun and Wu, Chun-Ying and Trebicka, Jonel and Ji, Fanpu},
  title = {Predictive machine learning model in intensive care unit patients with acute-on-chronic liver failure and two or more organ failures},
  journal = {Clinical and Molecular Hepatology},
  year = {2025},
  doi = {10.3350/cmh.2025.0573}
}
Kostenlos starten →