Machine Learning Predicts Hepatocellular Carcinoma Risk from Routine Clinical Data: A Large Population-Based Multicentric Study
Year: 2026
Type: article
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.
Source: Cancer Discovery
Institutions: 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, University of Pennsylvania, Prince of Songkla University, 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, Charité - Universitätsmedizin Berlin, Düsseldorf University Hospital, Center for Regenerative Therapies Dresden, Heidelberg University, University Hospital Heidelberg, National Center for Tumor Diseases
Language: English
Subfield: Hepatology
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
Funders: Breast Cancer Research Foundation, National Institute for Health and Care Research, Deutsche Forschungsgemeinschaft, Bundesministerium für Bildung und Forschung, Bundesministerium für Gesundheit, Deutsche Krebshilfe, RWTH Aachen University, Ministerium für Kultur und Wissenschaft des Landes Nordrhein-Westfalen, Gemeinsame Bundesausschuss, National Institutes of Health, HORIZON EUROPE Framework Programme, European Research Council, National Heart, Lung, and Blood Institute, German Academic Exchange Service
Awards: ERA-NET Transcan - Tangerine - Künstliche Intelligenz-basierte End-to-End-Vorhersage des Ansprechens auf Krebsimmuntherapie, G1431763348, G1711612453, CAMINO - Programm zur Karriereentwicklung für forschende Ärztinnen und Ärzte in der multidimensionalen Tumorforschung, G2352592553, G3570765224, G3641866126, G3815489264, G3848825097, LiSyM-Krebs - Phase II - Verbundprojekt: DEEP-HCC - Vertieftes Systemverständnis der Entstehung des hepatozellulären Karzinoms als Grundlage für neue Früherkennungsmethoden - Teilprojekt A, Insights_eHealth - Interaktive Einblicke in Daten, Prozesse und Wissen im Bereich eHealth - Partner Kiel, G468699552, G490518035, G5621058518, Verbundprojekt: Competence Center for Interdisciplinary Data Sciences - Come2Data, Teilvorhaben: Lern, Unterstützungs- und Forschungsort TU Dresden, Investigating ancestry-specific genetic variation associated with HLBS phenotypes in diverse patient biobanks, DECIPHER-M - Entschlüsselung von Metastasierung mit multimodalen Modellen der Künstlichen Intelligenz - Technische Universität Dresden, G616889348, G6697820746, G6861115116, CompLS - Runde 5 - Verbundprojekt: TRANSFORM LIVER - Weiterentwicklung von Vision Transformern zur Entdeckung von Biomarkern bei Lebererkrankungen - Teilprojekt B, G80034160, SFB 1382: Die DarmLeber Achse – Funktionelle Zusammenhänge und therapeutische Strategien, Verbund PEARL - Prävention von Darmkrebs im jungen und mittleren Erwachsenenalter - Standort Dresden
OpenAlex ID: W7140743061