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

Development and external validation of a machine learning model for predicting in-hospital mortality in acute liver failure

Xuanlin Wu, Qingzhou Song, Delin Li, Zixuan Liu, Xinyu Wang, Ruiwei Yang, Yukun He, Huawei Yang

Digestive and Liver Disease · 2026-05 · 58 (5) · 644-653

DOI: 10.1016/j.dld.2026.01.226 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Digestive and Liver Disease, 2026-05. Verfasst von Xuanlin Wu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Breast Surgery, Guangxi Medical University Cancer Hospital, Nanning 530021, Guangxi Zhuang Autonomous Region, China. Hauptthemen laut MEDLINE: Hospital Mortality, Liver Failure, Acute, Machine Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: the Guangxi Natrual Science Foundation, the National Natural Science Foundation of China, the Wu Jieping medical foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Acute liver failure (ALF) is a rapidly progressive and life-threatening condition that requires accurate risk stratification. Existing prognostic tools have limited sensitivity and generalizability. This study aimed to develop and externally validate a machine learning-based modeling framework for early in-hospital dynamic prediction of in-hospital mortality in patients with acute liver failure. METHODS: Patients with ALF were identified from the MIMIC-IV database, with an independent external cohort from Guangxi Medical University Cancer Hospital for validation. Eleven predictors were selected using LASSO regression and the Boruta algorithm. Seven ML models were trained and optimized through cross-validation and grid search. Model performance was assessed using discrimination, calibration, and decision curve analysis, with interpretability evaluated by SHAP. RESULTS: A total of 1,228 patients from MIMIC-IV and 108 external patients were included. Among all evaluated models, logistic regression demonstrated the most robust and stable performance, with AUCs of 0.802 in internal validation and 0.774 in external validation. Calibration and decision curve analyses demonstrated good clinical utility. SHAP identified temperature, vasopressor use, age, CRRT, and sedative/analgesic use as key predictors. A nomogram and online tool were developed for individualized risk prediction. CONCLUSION: This study presents an interpretable and externally validated ML model for predicting in-hospital mortality in ALF, providing a practical tool for early in-hospital dynamic risk stratification and clinical decision support.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Hospital MortalityLiver Failure, AcuteMachine LearningHumansFemalePredictive Learning ModelsMaleNomogramsMiddle AgedLogistic ModelsAdultPrognosisRisk AssessmentChinaPrediction Algorithms

Stichwörter der Autor:innen

Acute liver failureMIMIC-IVMachine learningMortalityNomogram

Autor:innen und Institutionen

  • Department of Breast Surgery, Guangxi Medical University Cancer Hospital, Nanning 530021, Guangxi Zhuang Autonomous Region, China.
  • Division of Colorectal & Anal Surgery, Department of Gastrointestinal Surgery, Guangxi Medical University Cancer Hospital, Nanning 530021, Guangxi Zhuang Autonomous Region, China.
  • Department of Breast Surgery, Guangxi Medical University Cancer Hospital, Nanning 530021, Guangxi Zhuang Autonomous Region, China. Electronic address: yanghuawei@stu.gxmu.edu.cn.

Förderung

  • the Guangxi Natrual Science Foundation
  • the National Natural Science Foundation of China
  • the Wu Jieping medical foundation
  • National Natural Science Foundation of China
  • Guangxi Natural Science Foundation
  • Wu Jieping Medical Foundation

Zitieren

APA

Wu, X., Song, Q., Li, D., Liu, Z., Wang, X., Yang, R., He, Y., & Yang, H. (2026). Development and external validation of a machine learning model for predicting in-hospital mortality in acute liver failure. Digestive and Liver Disease, 58(5), 644-653. https://doi.org/10.1016/j.dld.2026.01.226

Vancouver

Wu X, Song Q, Li D, Liu Z, Wang X, Yang R, et al. Development and external validation of a machine learning model for predicting in-hospital mortality in acute liver failure. Digestive and Liver Disease. 2026;58(5):644-653. doi:10.1016/j.dld.2026.01.226

BibTeX
@article{Wu2026,
  author = {Wu, Xuanlin and Song, Qingzhou and Li, Delin and Liu, Zixuan and Wang, Xinyu and Yang, Ruiwei and He, Yukun and Yang, Huawei},
  title = {Development and external validation of a machine learning model for predicting in-hospital mortality in acute liver failure},
  journal = {Digestive and Liver Disease},
  year = {2026},
  volume = {58},
  number = {5},
  pages = {644--653},
  doi = {10.1016/j.dld.2026.01.226}
}
Kostenlos starten →