Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Dec;23(12):1908-1921.
doi: 10.1016/j.ajt.2023.08.022. Epub 2023 Aug 30.

Predicting post-liver transplant outcomes in patients with acute-on-chronic liver failure using Expert-Augmented Machine Learning

Jin Ge  1 , Jean C Digitale  2 , Cynthia Fenton  3 , Charles E McCulloch  2 , Jennifer C Lai  4 , Mark J Pletcher  2 , Efstathios D Gennatas  2
Affiliations

Predicting post-liver transplant outcomes in patients with acute-on-chronic liver failure using Expert-Augmented Machine Learning

Jin Ge et al. Am J Transplant. 2023 Dec.

Abstract

Liver transplantation (LT) is a treatment for acute-on-chronic liver failure (ACLF), but high post-LT mortality has been reported. Existing post-LT models in ACLF have been limited. We developed an Expert-Augmented Machine Learning (EAML) model to predict post-LT outcomes. We identified ACLF patients who underwent LT in the University of California Health Data Warehouse. We applied the RuleFit machine learning (ML) algorithm to extract rules from decision trees and create intermediate models. We asked human experts to rate the rules generated by RuleFit and incorporated these ratings to generate final EAML models. We identified 1384 ACLF patients. For death at 1 year, areas under the receiver-operating characteristic curve were 0.707 (confidence interval [CI] 0.625-0.793) for EAML and 0.719 (CI 0.640-0.800) for RuleFit. For death at 90 days, areas under the receiver-operating characteristic curve were 0.678 (CI 0.581-0.776) for EAML and 0.707 (CI 0.615-0.800) for RuleFit. In pairwise comparisons, both EAML and RuleFit models outperformed cross-sectional models. Significant discrepancies between experts and ML occurred in rankings of biomarkers used in clinical practice. EAML may serve as a method for ML-guided hypothesis generation in further ACLF research.

Keywords: ACLF; UCHDW; big data; machine learning; posttransplant outcomes.

PubMed Disclaimer

Conflict of interest statement

Disclosure The authors of this manuscript have conflicts of interest to disclose as described by the American Journal of Transplantation. J. Ge receives research support from Merck and Co, and consults for Astellas Pharmaceuticals.

Figures

Figure 1.
Figure 1.
Study design flowchart.
Figure 2.
Figure 2.
Example survey questions utilized to obtain expert input.
Figure 3.
Figure 3.
Disagreements between experts and RuleFit may reflect biases, artifacts, and areas for further research.
See this image and copyright information in PMC

References

    1. Bajaj JS, O’Leary JG, Reddy KR, et al. Survival in infection-related acute-on-chronic liver failure is defined by extrahepatic organ failures. Hepatology. 2014;60(1):250–256. 10.1002/hep.27077. - DOI - PMC - PubMed
    1. O’Leary JG, Reddy KR, Garcia-Tsao G, et al. NACSELD acute-on-chronic liver failure (NACSELD-ACLF) score predicts 30-day survival in hospitalized patients with cirrhosis. Hepatology. 2018;67(6):2367–2374. 10.1002/hep.29773. - DOI - PubMed
    1. Jalan R, Saliba F, Pavesi M, et al. Development and validation of a-prognostic score to predict mortality in patients with acute-on-chronic liver failure. J Hepatol. 2014;61(5):1038–1047. 10.1016/j.jhep.2014.06.012. - DOI - PubMed
    1. Gustot T, Moreau R. Acute-on-chronic liver failure vs. traditional acute-decompensation of cirrhosis. J Hepatol. 2018;69(6):1384–1393. 10.1016/j.jhep.2018.08.024. - DOI - PubMed
    1. Hernaez R, Solà E, Moreau R, Ginès P. Acute-on-chronic liver failure: an update. Gut. 2017;66(3):541–553. 10.1136/gutjnl-2016-312670. - DOI - PMC - PubMed

Publication types