Machine Learning Predicts Hepatocellular Carcinoma Risk from Routine Clinical Data: A Large Population-Based Multicentric Study

Cancer Discovery, vol. 16, pp. 1304–1322

Abstract

Hepatocellular carcinoma (HCC) is a highly fatal tumor, for which risk stratification is crucial yet remains challenging. In this study, we develop an interpretable machine learning (ML) framework for HCC risk stratification based on routinely collected clinical data. We utilize prospectively collected multimodal data from more than 900,000 individuals and 983 cases of HCC across two population-scale cohorts: the UK Biobank study (development) and the All of Us Research Program (external testing). We assess individual and cumulative contributions of data modalities, including demographics, lifestyle, health records, blood, genomics, and metabolomics. Our final random forest-based models significantly outperform all publicly available state-of-the-art risk scores on both internal and external test sets. We demonstrate robustness across ethnic subgroups, provide comprehensive interpretability, and release all code, model weights, and a web calculator for external validation and agentic integration. Our study presents PRE-Screen-HCC, a robust and interpretable ML framework for HCC risk stratification and early detection. SIGNIFICANCE: Using data from population-scale cohorts, we develop and externally validate an ML framework for HCC risk stratification. Models trained on routine clinical data outperform published scores, perform on par with metabolomics and genomics, generalize across subgroups, and remain interpretable. See related commentary by Foda, p. 1252.

Authors 16

1. Jan Clusmann Aachen 1Department of Medicine III

   German Cancer Research Center · Universitätsklinikum Aachen · University Hospital Carl Gustav Carus · Deutsches Konsortium für Translationale Krebsforschung · German Cancer Research Center (DKFZ) Dresden · Else Kröner Fresenius Center for Digital Health · German Cancer Consortium (DKTK) Dresden · Technische Universität Dresden · RWTH Aachen University

   Affiliation as printed

   1Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany

   3Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany

   4German Cancer Consortium (DKTK), Partner Site Dresden and German Cancer Research Center (DKFZ), Heidelberg, Germany

   Technical University Dresden 2 Else Kroener Fresenius Center for Digital Health, , Dresden, Germany

2. Paul‐Henry Koop Aachen 1Department of Medicine III

   German Cancer Research Center · Universitätsklinikum Aachen · University Hospital Carl Gustav Carus · Deutsches Konsortium für Translationale Krebsforschung · German Cancer Research Center (DKFZ) Dresden · Else Kröner Fresenius Center for Digital Health · German Cancer Consortium (DKTK) Dresden · Technische Universität Dresden · RWTH Aachen University

   Affiliation as printed

   1Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany

   3Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany

   4German Cancer Consortium (DKTK), Partner Site Dresden and German Cancer Research Center (DKFZ), Heidelberg, Germany

   Technical University Dresden 2 Else Kroener Fresenius Center for Digital Health, , Dresden, Germany

3. David Y. Zhang

   University of Pennsylvania

   Affiliation as printed

   University of Pennsylvania 5 Department of Genetics, Perelman School of Medicine, , Philadelphia, Pennsylvania

   University of Pennsylvania 6 Department of Medicine, Perelman School of Medicine, , Philadelphia, Pennsylvania

4. Felix van Haag Aachen 1Department of Medicine III

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   1Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany

5. Omar S. M. El Nahhas

   Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden

   Affiliation as printed

   7StratifAI GmbH, Dresden, Germany

   Technical University Dresden 2 Else Kroener Fresenius Center for Digital Health, , Dresden, Germany

6. Tobias Seibel Aachen 1Department of Medicine III

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

   1Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany

7. Laura Žigutytė

   Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden

   Affiliation as printed

   Technical University Dresden 2 Else Kroener Fresenius Center for Digital Health, , Dresden, Germany

8. Apichat Kaewdech

   Prince of Songkla University

   Affiliation as printed

   Prince of Songkla University 8 Gastroenterology and Hepatology Unit, Division of Internal Medicine, Faculty of Medicine, , Songkhla, Thailand

9. Julien Caldéraro

   Inserm · Université Paris-Est Créteil · Centre Hospitalier Universitaire Henri-Mondor · Assistance Publique – Hôpitaux de Paris · Hôpitaux Universitaires Henri-Mondor · Hôpital Albert-Chenevier · Institut Mondor de Recherche Biomédicale

   Affiliation as printed

   10Department of Pathology, Assistance Publique-Hôpitaux de Paris, Henri Mondor-Albert Chenevier University Hospital, Créteil, France

   11Inserm, U955, Team 18, Créteil, France

   12European Reference Network (ERN) RARE-LIVER, Créteil, France

   9INSERM, IMRB, Université Paris Est Créteil, Créteil, France

10. Frank Tacke

    Charité - Universitätsmedizin Berlin

    Affiliation as printed

    13Department of Hepatology and Gastroenterology, Charité - Universitätsmedizin Berlin, Campus Virchow-Klinikum and Campus Charité Mitte, Berlin, Germany

11. Tom Luedde

    Düsseldorf University Hospital

    Affiliation as printed

    14Department for Gastroenterology, Hepatology and Infectiology, University Hospital Düsseldorf, Düsseldorf, Germany

12. Daniel Truhn Aachen 15Department of Diagnostic and Interventional Radiology

    Universitätsklinikum Aachen

    Affiliation as printed

    15Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany

13. Tony Bruns Aachen 1Department of Medicine III

    Universitätsklinikum Aachen · RWTH Aachen University

    Affiliation as printed

    1Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany

14. Kai Markus Schneider Aachen 1Department of Medicine III

    Universitätsklinikum Aachen · University Hospital Carl Gustav Carus · Center for Regenerative Therapies Dresden · Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden · RWTH Aachen University

    Affiliation as printed

    16Center for Regenerative Therapies Dresden (CRTD), Technische Universität (TU), Dresden, Germany

    1Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany

    3Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany

    Technical University Dresden 2 Else Kroener Fresenius Center for Digital Health, , Dresden, Germany

15. Jakob Nikolas Kather

    Heidelberg University · University Hospital Heidelberg · National Center for Tumor Diseases · University Hospital Carl Gustav Carus · Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden

    Affiliation as printed

    17Department of Medical Oncology, National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany

    3Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany

    Technical University Dresden 2 Else Kroener Fresenius Center for Digital Health, , Dresden, Germany

16. Carolin Victoria Schneider Aachen 1Department of Medicine III

    Universitätsklinikum Aachen · Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden · RWTH Aachen University

    Affiliation as printed

    1Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany

    Technical University Dresden 2 Else Kroener Fresenius Center for Digital Health, , Dresden, Germany