Deep learning can predict cardiovascular events from liver imaging

JHEP Reports, vol. 7, pp. 101427

Abstract

Background & Aims: Cardiovascular mortality remains the leading cause of death and a significant source of morbidity, with metabolic alterations being key etiological factors. As the main metabolic organ, the liver could predict prodromal changes associated with increased cardiovascular risk. However, quantifying this risk remains challenging. This study explores the use of transformer neural networks on liver magnetic resonance imaging (MRI) data to enhance cardiovascular risk prediction. Methods: Using the extensive collection of liver MRIs in the UK Biobank, we developed a feature extractor with a vision transformer backbone trained in a self-supervised manner. This encoder was then used to predict cardiovascular outcomes from liver MRI scans. Unlike traditional methods, no manual feature selection was required, minimizing bias. Performance was assessed via fivefold cross validation, where predicted risk scores were compared against actual cardiovascular outcomes. Results: <0.001. Conclusions: Vision transformer-based models demonstrate promise as quantifiable biomarkers for cardiovascular risk assessment by capturing subtle metabolic and vascular information from liver MRI scans. These findings highlight their strong predictive performance and potential value in risk stratification. Further prospective studies and external validation will be required to establish their clinical utility. Impact and implications: Our study demonstrates that deep learning applied to liver MRI can predict cardiovascular risk, highlighting the role of the liver as a metabolic indicator of early cardiovascular disease. These findings are significant for clinicians and researchers seeking non-invasive, imaging-based biomarkers for cardiovascular risk stratification, particularly in patients who might not yet exhibit overt symptoms. If validated in prospective studies, this approach could enhance current risk assessment models, allowing for earlier and more personalized interventions in high-risk individuals. However, further validation is necessary before clinical implementation, ensuring broad applicability and integration into existing prevention frameworks.

Authors 12

1. Gregory Patrick Veldhuizen

   University of Chicago · Else Kröner Fresenius Center for Digital Health

   Affiliation as printed

   Department of Medicine, Section of Hematology/Oncology, The University of Chicago, Chicago, IL, USA

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

2. Tim Lenz

   Else Kröner Fresenius Center for Digital Health

   Affiliation as printed

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

3. Didem Çifçi Aachen Department of Medicine III

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

   Affiliation as printed

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

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

4. Marko van Treeck Aachen Department of Medicine III

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

   Affiliation as printed

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

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

5. Jan Clusmann Aachen Department of Medicine III

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

   Affiliation as printed

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

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

6. Yazhou Chen Aachen Department of Medicine III

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

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

7. Carolin Victoria Schneider Aachen Department of Medicine III

   Universitätsklinikum Aachen · RWTH Aachen University

   Affiliation as printed

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

8. Tom Luedde

   Düsseldorf University Hospital · Heinrich Heine University Düsseldorf

   Affiliation as printed

   Clinic for Gastroenterology, Hepatology and Infectious Diseases, University Hospital Duesseldorf, Medical Faculty of Heinrich-Heine-University Dusseldorf, Dusseldorf, Germany

9. Peter W. de Leeuw

   Maastricht University Medical Centre · Maastricht University

   Affiliation as printed

   Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht The Netherlands

   Department of Internal Medicine, Maastricht University Medical Center, Maastricht, The Netherlands

10. Ali El‐Armouche

    Technische Universität Dresden

    Affiliation as printed

    Institute of Pharmacology and Toxicology, Faculty of Medicine Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany

11. Daniel Truhn Aachen Department of Diagnostic and Interventional Radiology

    RWTH Aachen University

    Affiliation as printed

    Department of Diagnostic and Interventional Radiology, RWTH Aachen University Aachen, Germany

12. Jakob Nikolas Kather Aachen Department of Medicine III

    University Hospital Heidelberg · National Center for Tumor Diseases · Universitätsklinikum Aachen · University Hospital Carl Gustav Carus · Else Kröner Fresenius Center for Digital Health · RWTH Aachen University

    Affiliation as printed

    Department of Medicine I, University Hospital Dresden, Dresden, Germany

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

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

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