Artificial intelligence predicts recurrent autoimmune hepatitis after liver transplantation in a multicenter cohort study

Background: Autoimmune hepatitis (AIH) is an important indication for liver transplantation (LT), but recurrence affects over 30% of recipients, threatening long-term survival. Current strategies to prevent recurrence and progressive graft fibrosis remain suboptimal, with limited evidence to guide selection of immunosuppressive regimens. We aimed to develop a dynamic, individualized, artificial intelligence–powered model for post-transplant recurrent AIH. Methods: We conducted a multicenter, retrospective cohort study of 706 patients who underwent LT for AIH between January 1987 and June 2020 at 33 centers in North America, South America, Europe, and Asia. We trained 4 predictive machine learning models—Logistic Regression, Random Forest, XGBoost, and Gradient Boost—to predict recurrent AIH (rAIH) using 62 clinical and laboratory variables, including demographic, biochemical features, and immunosuppressive drugs up to 1-year post-transplant. Feature importance was assessed using SHapley Additive exPlanations (SHAP) to enable interpretability at both individual and population levels. Results: AIH recurred in 16.5% of patients after LT. SHAP analysis identified younger age at LT, higher necroinflammatory activity in the explanted liver, and elevated MELD score at LT as key predictors of rAIH in the overall population. Tacrolimus-based therapy was associated with a lower risk of recurrence, while cyclosporine use conferred a higher risk. The addition of long-term prednisone to a regimen of tacrolimus and mycophenolate mofetil did not provide additional protective effect against rAIH. Conclusions: Our AI-powered clinical decision model provides personalized prediction of post-transplant rAIH. While it offers insight into modifiable and non-modifiable predictors, prospective validation is required before informing immunosuppressive decisions.

Authors

Institutions

Publication Details

Journal
Hepatology Communications
Published
2026-07-27
DOI
https://doi.org/10.1097/hc9.0000000000001004
Primary Topic
Liver Diseases and Immunity
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Artificial intelligence predicts recurrent autoimmune hepatitis after liver transplantation in a multicenter cohort study

Yoshihide Ueda, Marlyn J. Mayo, Maaike Biewenga, Patrizia Burra et al.
Hepatology Communications
Liver Diseases and Immunity
article

Artificial intelligence predicts recurrent autoimmune hepatitis after liver transplantation in a multicenter cohort study

Yoshihide Ueda, Marlyn J. Mayo, Maaike Biewenga, Patrizia Burra, Richard Taubert, Mai Sedki, Christoph Schramm, Maria Antonella Burza, Bettina E. Hansen, Maria Francesca Donato, Vincenzo Ronca, Vilas Patwardhan, Nazia Selzner, Marco Sciveres, Annarosa Floreani, Ana Lleò, Dominique Debray, Anna-Lena Weber, Cynthia Levy, Natalia Ołdak, Ali Rıza Çalışkan, Atsushi Tanaka, Piotr Czubkowski, Ynto S. de Boer, Alan Bonder, Cumali Efe, Florence Lacaille, Andrew L. Mason, Irena Jankowska, M Girard, Hanns–Ulrich Marschall, Piotr Milkiewicz, Bart van Hoek, Maria Francesca Secchi, Syed‐Mohammed Jafri, Giuseppe Maggiore, Murat Harputluoğlu, Mohamad Alsaed, Yingji Sun, Raúl J Andrade, María Rodríguez, Fernanda de Quadros Onófrio, Albert Pares, Débora Terrabuio, Praveen Manickavel, Ye Htun Oo, Ansgar Lohse, Martina Sterneck, Mark Pedersen, Cigdem Arikan, Mark Deneau, Eric F. Martin, Saleh Elwir, Michael P. Manns, Saba Maleki, Laura Llovet, on behalf of the International AIH Study Group, Mamatha Bhat, Ellina Lytvyak, Toru Ikegami, Murat Akyıldız, Nobuhisa Akamatsu, Christina Weiler-Normann, Benedetta Terziroli Beretta-Piccoli, Piotr Socha, Aldo J. Montano-Loza, Michael Heneghan, Gökhan Kabaçam, Thomas D. Schiano, Brandy Haydel, Aparna Goel, Gideon Hirschfield, Andreas E. Kremer, Maciej K. Janik
article en

Abstract

Background: Autoimmune hepatitis (AIH) is an important indication for liver transplantation (LT), but recurrence affects over 30% of recipients, threatening long-term survival. Current strategies to prevent recurrence and progressive graft fibrosis remain suboptimal, with limited evidence to guide selection of immunosuppressive regimens. We aimed to develop a dynamic, individualized, artificial intelligence–powered model for post-transplant recurrent AIH. Methods: We conducted a multicenter, retrospective cohort study of 706 patients who underwent LT for AIH between January 1987 and June 2020 at 33 centers in North America, South America, Europe, and Asia. We trained 4 predictive machine learning models—Logistic Regression, Random Forest, XGBoost, and Gradient Boost—to predict recurrent AIH (rAIH) using 62 clinical and laboratory variables, including demographic, biochemical features, and immunosuppressive drugs up to 1-year post-transplant. Feature importance was assessed using SHapley Additive exPlanations (SHAP) to enable interpretability at both individual and population levels. Results: AIH recurred in 16.5% of patients after LT. SHAP analysis identified younger age at LT, higher necroinflammatory activity in the explanted liver, and elevated MELD score at LT as key predictors of rAIH in the overall population. Tacrolimus-based therapy was associated with a lower risk of recurrence, while cyclosporine use conferred a higher risk. The addition of long-term prednisone to a regimen of tacrolimus and mycophenolate mofetil did not provide additional protective effect against rAIH. Conclusions: Our AI-powered clinical decision model provides personalized prediction of post-transplant rAIH. While it offers insight into modifiable and non-modifiable predictors, prospective validation is required before informing immunosuppressive decisions.

Hepatology CommunicationsVol. 10(8)
Hôpital Necker-Enfants Malades (FR), Beth Israel Deaconess Medical Center (US), Mount Sinai Hospital (US), University Health Network (CA), Humanitas University (IT), Koç University (TR), Kyushu University (JP), Harvard University (US), University of Padua (IT), University of Miami (US), Henry Ford Health System (US), University of Alberta (CA), Universität Hamburg (DE), Universidade de São Paulo (BR), Friedrich-Alexander-Universität Erlangen-Nürnberg (DE), University of Toronto (CA), Adıyaman University (TR), Inonu University (TR), University of Zurich (CH), Kyoto University (JP), University of Utah (US), Medical University of Warsaw (PL), Leiden University Medical Center (NL), Sahlgrenska University Hospital (SE), Toronto General Hospital (CA), Erasmus MC (NL), Baylor University Medical Center (US), Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico (IT), Medizinische Hochschule Hannover (DE), Ospedale Maggiore (IT), Universitätsklinikum Erlangen (DE), Mount Sinai Medical Center (US), NIHR Birmingham Liver Biomedical Research Unit (GB), University Hospital of Zurich (CH), University Medical Center Hamburg-Eppendorf (DE), King's College Hospital NHS Foundation Trust (GB), Güven Hospital (TR), Children's Memorial Health Institute (PL), Hospital Clínic de Barcelona (ES), Bambino Gesù Children's Hospital (IT), Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (ES), Comprehensive Cancer Center Erlangen (DE), Amsterdam University Medical Centers (NL), Consorci Institut D'Investigacions Biomediques August Pi I Sunyer (ES), NIHR Birmingham Biomedical Research Centre (GB), IRCCS Humanitas Research Hospital (IT), Instituto de Investigación Biomédica de Málaga (ES), Università della Svizzera italiana (CH), Universitat de Barcelona (ES), The University of Tokyo (JP), Harran University (TR), Universidad de Málaga (ES), Vrije Universiteit Amsterdam (NL), The University of Texas Southwestern Medical Center (US), Teikyo University (JP), University of Palermo (IT), Stanford University (US)
Openalex Percentile: Top 11%
Liver Diseases and Immunity
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.