Machine learning-based algorithms for the prediction of 90-day survival in patients with liver failure receiving artificial liver therapy

Aug 5, 2026

Liver failure carries high short-term mortality, while the predictive value of clinical factors for patients treated with artificial liver therapy remains uncertain. This original research develops prognostic models using multiple machine learning methods to estimate 90-day survival. Hospitalized patients treated with artificial liver support between December 2017 and December 2021 were analyzed, using LASSO for feature selection and stepwise logistic regression for independent predictors. Performance was evaluated with AUC, accuracy, sensitivity, specificity, and predictive values, showing logistic regression as the top-performing approach.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Background

Methods

Participants and data collection

Feature selection and modeling

Model evaluation

Results

Conclusion

TYPE Original Research PUBLISHED 27 October 2025 DOI 10.3389/fphys.2025.1687860 OPEN ACCESS EDITED BY Hongxiang Hui, Monterrey Park, United States REVIEWED BY Suyavaran Arumugam, Yale University, United States Hirotaka Tashiro, National Hospital Organization Kure Medical Center, Japan *CORRESPONDENCE Bo Deng, [bod29493@gmail.com](bod29493@gmail.com)[ ](bod29493@gmail.com)Ying Deng, [626491340@qq.com](626491340@qq.com)[ ](626491340@qq.com)RECEIVED 18 August 2025 ACCEPTED 30 September 2025 PUBLISHED 27 October 2025 CITATION Deng B, Bai C, Xu H, Zhang X and Deng Y (2025) Machine learning-based algorithms for the prediction of 90-day survival in patients with liver failure receiving artificial liver therapy. Front. Physiol. 16:1687860 . doi: 10.3389/fphys.2025.1687860 COPYRIGHT © 2025 Deng, Bai, Xu, Zhang and Deng. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Machine learning-based algorithms for the prediction of 90-day survival in patients with liver failure receiving artificial liver therapy Bo Deng 1,2*, Chengzhi Bai 1, Huaqian Xu 1, Xue Zhang 1 and Ying Deng 3* 1 Department of Gastroenterology, The General Hospital of Western Theater Command, Chengdu, Sichuan, China, 2Graduate School of Chengdu Medical University, Chengdu, Sichuan, China, 3 Integrated Care Management Center, Institute of Respiratory Health, West China Hospital, Sichuan University, Chengdu, China Background: Liver failure is associated with high short-term mortality, and the predictive value of clinical factors for patients undergoing artificial liver therapy is uncertain. We aim to develop prognostic models using several machine learning algorithms to predict 90-day survival in patients with liver failure undergoing artificial liver therapy. Methods: We retrospectively enrolled hospitalized patients with liver failure who received artificial liver therapy in our center between December 2017 and December 2021. Prognostic characteristics were chosen by the least absolute shrinkage and selection operator (LASSO) regression and independent predictors by stepwise logistic regression analysis. Five machine learning algorithms—logistic regression (LR), random forest (RF), support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), and k-nearest neighbor (KNN)—were used to build and validate models to predict 90-day survival following Artificial liver support systems. The model performance was assessed by the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. Results: A total of 197 patients were included in this study. LASSO regression, based on patient admission data, identified the top 15 prognostic features, and stepwise LR analysis determined that the age, direct bilirubin, retinol, alphafetoprotein, and thrombin time were independent predictors. Among the five machine learning models, LR achieved the highest predictive performance with an AUC of 0.884 and accuracy of 75.0%, followed by RF (AUC = 0.797), KNN (AUC = 0.788), XGBoost (AUC = 0.769), and SVM (AUC = 0.732) . The predictive performance of LR models based on longitudinal data using patient characteristics from the day before treatment had an AUC of 0. 869, and from the day after treatment, it had an AUC of 0.859. Conclusion: Machine learning models showed promising performance in predicting 90-day survival in liver failure patients receiving artificial Frontiers in Physiology 01 [frontiersin.org](frontiersin.org) liver support therapy, p

FAQs

What is the objective of the machine learning models in this study?

To develop prognostic models that predict 90-day survival for patients with liver failure receiving artificial liver therapy.

How were prognostic features selected and independent predictors identified?

LASSO regression selected the top 15 prognostic features, and stepwise logistic regression determined independent predictors.

Which machine learning algorithm performed best for 90-day survival prediction?

Logistic regression achieved the highest performance, with an AUC of 0.884 and accuracy of 75.0%.

Aug 5, 2026

Upload by Clementine