Peer-Reviewed Publication
EBioMedicine2026;131106433.August 12, 2026Journal Article
Machine learning for population-level risk prediction of future cholangiocarcinoma.
Felix van Haag1, Jan Clusmann2, Paul-Henry Koop3, Ryan Goodson4, Ilya Tryakin5, Shun-Ichi Wakabayashi6, Tobias Seibel1, Niharika Jakhar1, Helen Ye Rim Huang7, David Y Zhang8, Inuk Zandvakili9, Takefumi Kimura6, Nobuharu Tamaki10, Arunkumar Krishnan11, Pedro Miguel Rodrigues12, Jesus Maria Banales13, Alessio Gerussi14, Anna Saborowski15, Daniel Rader16, Jakob Nikolas Kather17, Kai Markus Schneider18, Carolin Victoria Schneider19
1Department of Internal Medicine III, Gastroenterology, Metabolic Diseases and Intensive Care, University Hospital RWTH Aachen, Aachen, Germany.
2Department of Internal Medicine III, Gastroenterology, Metabolic Diseases and Intensive Care, University Hospital RWTH Aachen, Aachen, Germany; Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany; Else Kroener Fresenius Centre for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany; German Cancer Consortium (DKTK) partner site Dresden and German Cancer Research Centre (DKFZ), Heidelberg, Germany.
3Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany; Else Kroener Fresenius Centre for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany; German Cancer Consortium (DKTK) partner site Dresden and German Cancer Research Centre (DKFZ), Heidelberg, Germany.
4College of Medicine, University of Cincinnati, Cincinnati, OH, 45267, USA.
5Else Kroener Fresenius Centre for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany.
6Division of Gastroenterology, Department of Medicine, Shinshu University School of Medicine, Nagano, Japan.
7Department of Internal Medicine III, Gastroenterology, Metabolic Diseases and Intensive Care, University Hospital RWTH Aachen, Aachen, Germany; The Perelman School of Medicine, The Institute for Translational Medicine and Therapeutics, University of Pennsylvania, Philadelphia, PA, USA.
8Department of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, 19104, USA; Department of Genetics, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, 19104, USA.
9Department of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, 19104, USA; Division of Gastroenterology and Hepatology, Department of Internal Medicine, College of Medicine, University of Cincinnati, Cincinnati, OH, USA; Division of Gastroenterology and Hepatology, Department of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
10Department of Gastroenterology and Hepatology, Musashino Red Cross Hospital, Tokyo, Japan.
11Department of Supportive Oncology, Atrium Health Levine Cancer, Charlotte, NC, 28204, USA.
12Department of Liver and Gastrointestinal Diseases, Biogipuzkoa Health Research Institute, Donostia University Hospital, University of the Basque Country (UPV/EHU), Ikerbasque, CIBERehd, San Sebastian, Spain.
13Department of Liver and Gastrointestinal Diseases, Biogipuzkoa Health Research Institute, Donostia University Hospital, University of the Basque Country (UPV/EHU), Ikerbasque, CIBERehd, San Sebastian, Spain; Department of Biochemistry and Genetics, School of Sciences, University of Navarra, Pamplona, Spain.
14Department of Medicine and Surgery, University of Milano-Bicocca, Monza, Italy; Centre for Autoimmune Liver Diseases & Division of Gastroenterology, Fondazione IRCCS San Gerardo dei Tintori, ERN RARE LIVER, Monza, Italy.
15Department of Gastroenterology, Hepatology, Infectious Diseases and Endocrinology, Hannover Medical School, Hannover, Germany.
16The Perelman School of Medicine, The Institute for Translational Medicine and Therapeutics, University of Pennsylvania, Philadelphia, PA, USA; Department of Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, 19104, USA.
17Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany; Else Kroener Fresenius Centre for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany; Medical Oncology, National Centre for Tumor Diseases (NCT), University Hospital Heidelberg, Heidelberg, Germany; Pathology & Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, United Kingdom.
18Department of Internal Medicine III, Gastroenterology, Metabolic Diseases and Intensive Care, University Hospital RWTH Aachen, Aachen, Germany; Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany; Else Kroener Fresenius Centre for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany; Centre for Regenerative Therapies Dresden (CRTD), Technische Universität (TU), Dresden, Germany.
19Department of Internal Medicine III, Gastroenterology, Metabolic Diseases and Intensive Care, University Hospital RWTH Aachen, Aachen, Germany; Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany; Else Kroener Fresenius Centre for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany. Electronic address: cschneider@ukaachen.de.
Abstract
BACKGROUND: The poor prognosis of cholangiocarcinoma (CCA) is largely driven by rapid, asymptomatic disease progression, which usually results in a late diagnosis in the absence of established screening strategies. An early, cost-effective, and universally applicable risk assessment strategy would therefore be valuable.
METHODS: We developed machine learning (ML) models on prospective, multimodal…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans