Detection of esophageal varices and prediction of hepatic decompensation in unresectable hepatocellular carcinoma using AI
Year: 2026
Type: article
Study design: Observational Study
Abstract: BACKGROUND & AIMS: In hepatocellular carcinoma (HCC) with cirrhosis, portal hypertension worsens outcomes. Esophagogastroduodenoscopy (EGD), the current screening method for esophageal varices (EVs), is invasive and may delay therapy. We aimed to develop and externally validate non-invasive models to detect EVs and predict hepatic decompensation (bleeding, ascites or hepatic encephalopathy), a major cause of mortality in patients with HCC, using routine contrast-enhanced CT and clinical data. METHODS: This multicenter retrospective study included 489 patients with unresectable HCC treated with atezolizumab-bevacizumab (AtezoBev) from five French centers, divided into a development cohort (n = 279) and an external validation cohort (n = 210). Arterial-phase contrast-enhanced CTs were processed through a Deep Learning pipeline using a foundation model (HepatoSageCT). Logistic and Cox models generated clinical models and combined models integrating the HepatoSageCT scores with key clinical variables for EVs and hepatic decompensation. Performance was assessed using AUROC, sensitivity, specificity, C-index and cause-specific hazard ratios. RESULTS: Portosystemic shunts (PSS) at imaging identified EVs with an AUROC of 0.78, increasing to 0.84 when combined with HepatoSageCT. A decision algorithm incorporating PSS and HepatoSageCT missed 4.2% of varices needing treatment, compared to 8.4% when using only PSS, while missing 0% of large EVs. HepatoSageCT predicted hepatic decompensation in the validation cohort (C-index: 0.73, hazard ratio: 3.17) with significant stratification (p <0.001), comparable to a composite score of ascites, splenomegaly and HepatoSageCT risk (C-index: 0.73, hazard ratio: 3.48). Patients stratified at higher risk of decompensation by HepatoSageCT also exhibited significantly lower overall survival (p <0.001). CONCLUSIONS: HepatoSageCT scores, supplemented with clinical data, enable accurate non-invasive detection of EV in AtezoBev-treated unresectable HCC and stratify patients according to their risk of hepatic decompensation. This approach may reduce unnecessary endoscopies and improve prognostic assessment. IMPACT AND IMPLICATIONS: 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.
Source: Journal of Hepatology
Authors: Asier Rabasco Meneghetti, Claudia Campani, Charles Roux, Zunamys I. Carrero, Dan-Adrian Popica, Giuliana Amaddeo, Marie Lequoy, Clémence Hollande, Sarah Mouri, Mathilde Wagner, Vincent Plaforet, Sabrina Sidali, Maxime Ronot, Marika Rudler, Alain Luciani, Olivier Sutter, Eleonore Spitzer, Hélène Regnault, Sanaâ El Mouhadi, Violaine Ozenne, Nathalie Ganne-Carrié, Mohamed Bouattour, Jean Charles Nault, Dominique Thabut, Jakob Nikolas Kather, Manon Allaire
Institutions: German Cancer Research Center, University Hospital Carl Gustav Carus, Else Kröner Fresenius Center for Digital Health, German Cancer Consortium (DKTK) Dresden, Technische Universität Dresden, Inserm, Centre de Recherche des Cordeliers, University of Florence, Sorbonne Université, Assistance Publique – Hôpitaux de Paris, Pitié-Salpêtrière Hospital, Centre Hospitalier Universitaire Henri-Mondor, Hôpitaux Universitaires Henri-Mondor, Hôpital Saint-Antoine, Hôpital Beaujon, Hôpital Albert-Chenevier, Hôpital Avicenne, Centre de Recherche Saint-Antoine, Fondation pour l’innovation en Cadiométabolisme et Nutrition, Heidelberg University, University Hospital Heidelberg, National Center for Tumor Diseases
Language: English
Subfield: Hepatology
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
Estimated APC paid: $5,500
Funders: Pfizer, AstraZeneca, Gilead Sciences, National Institute for Health and Care Research, Department of Health and Social Care, European Commission, Deutscher Akademischer Austauschdienst, Deutsche Forschungsgemeinschaft, Bundesministerium für Bildung und Forschung, Eisai, Deutsche Krebshilfe, Gemeinsame Bundesausschuss, Sirtex Medical, National Institutes of Health, HORIZON EUROPE Framework Programme, European Research Council, Leeds Biomedical Research Centre, Daiichi Sankyo Europe, German Academic Exchange Service
Awards: G1249041673, G162135912, G1949475607, G2654538971, G2820917408, Understanding Gene ENvironment Interaction in ALcohol-related hepatocellular carcinoma, G3848825097, G4407328535, Open Consortium for Decentralized Medical Artificial Intelligence, G4712284355, G4996692071, G6697820746, Verbund PEARL - Prävention von Darmkrebs im jungen und mittleren Erwachsenenalter - Standort Dresden, G8770829881, G9000156230
OpenAlex ID: W7128497812