Detection of esophageal varices and prediction of hepatic decompensation in unresectable hepatocellular carcinoma using AI

The present study demonstrates that foundation models applied to routine CT imaging, when combined with routinely collected features such as the presence of portosystemic shunts, can accurately predict the presence of esophageal varices and the risk of first or further hepatic decompensation in patients with AtezoBev-treated unresectable hepatocellular carcinoma. These findings are particularly relevant for hepatologists and oncologists, as they highlight a promising non-invasive tool for timely risk assessment in a time-sensitive patient population. While prospective validation is warranted, this approach could support more personalized management and care of patients with unresectable hepatocellular carcinoma.

Authors

Institutions

Publication Details

Journal
Journal of Hepatology
Published
2026-02-01
DOI
https://doi.org/10.1016/j.jhep.2026.01.021
Citations
1
Primary Topic
Hepatocellular Carcinoma Treatment and Prognosis
Type
article
Field-Weighted Citation Impact
23.38

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Detection of esophageal varices and prediction of hepatic decompensation in unresectable hepatocellular carcinoma using AI

Olivier Sutter, Mathilde Wagner, Eléonore Spitzer, Clémence Hollande et al.
1 citations
Journal of Hepatology
Hepatocellular Carcinoma Treatment and Prognosis
23.38
article

Detection of esophageal varices and prediction of hepatic decompensation in unresectable hepatocellular carcinoma using AI

Olivier Sutter, Mathilde Wagner, Eléonore Spitzer, Clémence Hollande, Sabrina Sidali, Asier Rabasco Meneghetti, Marika Rudler, Manon Allaire, Jean Charles Nault, Hélène Regnault, Claudia Campani, Charles Roux, Dominique Thabut, Jakob Nikolas Kather, Sanaâ El Mouhadi, Maxime Ronot, Violaine Ozenne, Dan-Adrian Popica, Nathalie Ganne-Carrié, Sarah Mouri, Vincent Plaforet, Mohamed Bouattour, Zunamys Itzel Carrero, Giuliana Amaddeo, Marie Lequoy, Alain Luciani
article en
1 citations

Abstract

The present study demonstrates that foundation models applied to routine CT imaging, when combined with routinely collected features such as the presence of portosystemic shunts, can accurately predict the presence of esophageal varices and the risk of first or further hepatic decompensation in patients with AtezoBev-treated unresectable hepatocellular carcinoma. These findings are particularly relevant for hepatologists and oncologists, as they highlight a promising non-invasive tool for timely risk assessment in a time-sensitive patient population. While prospective validation is warranted, this approach could support more personalized management and care of patients with unresectable hepatocellular carcinoma.

Journal of Hepatology
Inserm (FR), German Cancer Research Center (DE), Heidelberg University (DE), Hôpital Beaujon (FR), University Hospital Heidelberg (DE), Sorbonne Université (FR), Université Sorbonne Paris Nord (FR), Centre de Recherche des Cordeliers (FR), Assistance Publique – Hôpitaux de Paris (FR), Hôpital Saint-Antoine (FR), National Center for Tumor Diseases (DE), Hôpitaux Universitaires Paris-Ouest (FR), Pitié-Salpêtrière Hospital (FR), Hôpital Avicenne (FR), Hôpitaux Universitaires Henri-Mondor (FR), Centre de Recherche Saint-Antoine (FR), Fondation pour l’innovation en Cadiométabolisme et Nutrition (FR), Hôpital Albert-Chenevier (FR), University Hospital Carl Gustav Carus (DE), University of Florence (IT)
Pfizer, AstraZeneca, Gilead Sciences, National Institute for Health and Care Research, Department of Health and Social Care, European Commission, Deutscher Akademischer Austauschdienst, Deutsche Forschungsgemeinschaft, Eisai, Deutsche Krebshilfe, Gemeinsame Bundesausschuss, Sirtex Medical, National Institutes of Health, HORIZON EUROPE Framework Programme, Leeds Biomedical Research Centre, Daiichi Sankyo Europe
Good health and well-being
Openalex Percentile: Top 2%
Hepatocellular Carcinoma Treatment and Prognosis
23.38
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.