Decoding pan-cancer treatment outcomes using multimodal real-world data and explainable artificial intelligence.

Journal: Nature cancer
PMID: 39885364

Abstract

Despite advances in precision oncology, clinical decision-making still relies on limited variables and expert knowledge. To address this limitation, we combined multimodal real-world data and explainable artificial intelligence (xAI) to introduce AI-derived (AID) markers for clinical decision support. We used xAI to decode the outcome of 15,726 patients across 38 solid cancer entities based on 350 markers, including clinical records, image-derived body compositions, and mutational tumor profiles. xAI determined the prognostic contribution of each clinical marker at the patient level and identified 114 key markers that accounted for 90% of the neural network's decision process. Moreover, xAI enabled us to uncover 1,373 prognostic interactions between markers. Our approach was validated in an independent cohort of 3,288 patients with lung cancer from a US nationwide electronic health record-derived database. These results show the potential of xAI to transform the assessment of clinical variables and enable personalized, data-driven cancer care.

Authors

  • Julius Keyl
    Institute of AI in Medicine (IKIM), University Hospital Essen, Girardetstraße 2, 45131, Essen, Germany.
  • Philipp Keyl
    Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität Berlin, Charitéplatz 1, 10117 Berlin, Germany.
  • Grégoire Montavon
    Machine Learning Group, Technische Universität Berlin, Berlin, Germany.
  • René Hosch
    Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Germany.
  • Alexander Brehmer
    Institute for Artificial Intelligence in Medicine, University Hospital Essen (AöR), Essen, Germany.
  • Liliana Mochmann
    Institute of Pathology, Ludwig-Maximilians-University Munich, Munich, Germany.
  • Philipp Jurmeister
    Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany.
  • Gabriel Dernbach
    Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität Berlin, Charitéplatz 1, 10117 Berlin, Germany.
  • Moon Kim
    USDA-ARS Environmental Microbial and Food Safety Laboratory, Beltsville Agricultural Research Center, 10300 Baltimore Ave., Beltsville, MD 20705, USA.
  • Sven Koitka
    Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Essen, Germany.
  • Sebastian Bauer
    PRIVATE, Münsterlandstr. 8, Berlin, 10317, Germany.
  • Nikolaos Bechrakis
    Medical Faculty, University of Duisburg-Essen, Essen, Germany.
  • Michael Forsting
    Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany.
  • Dagmar Führer-Sakel
    Medical Faculty, University of Duisburg-Essen, Essen, Germany.
  • Martin Glas
    Division of Clinical Neurooncology, Department of Neurology, University of Bonn Medical Center, Germany.
  • Viktor Grünwald
    Department of Medical Oncology, University Hospital Essen (AöR), Essen, Germany.
  • Boris Hadaschik
    Department of Urology, University Hospital Essen, Essen, Germany.
  • Johannes Haubold
    Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany. Johannes.haubold@uk-essen.de.
  • Ken Herrmann
    Department of Nuclear Medicine, Universitätsklinikum Essen, Essen, Germany.
  • Stefan Kasper
    Department of Medical Oncology, West German Cancer Center, University Hospital Essen (AöR), Essen, Germany.
  • Rainer Kimmig
    West German Cancer Center, Department for Gynecology and Obstetrics, University Hospital Essen, University of Duisburg-Essen, Hufelandstr. 55, 45147, Essen, Germany.
  • Stephan Lang
    Department of Oto-Rhino-Laryngology, Head and Neck Surgery, University Hospital Essen, Essen, Germany.
  • Tienush Rassaf
    Medical Faculty, University of Duisburg-Essen, Essen, Germany.
  • Alexander Roesch
    Medical Faculty, University of Duisburg-Essen, Essen, Germany.
  • Dirk Schadendorf
    Department of Dermatology, University Hospital Essen, 45147 Essen, Germany.
  • Jens T Siveke
    Division of Solid Tumor Translational Oncology, West German Cancer Center, University Hospital Essen, Essen, Germany.
  • Martin Stuschke
    Radiotherapy, and.
  • Ulrich Sure
  • Matthias Totzeck
    Medical Faculty, University of Duisburg-Essen, Essen, Germany.
  • Anja Welt
    Department of Medical Oncology, University Hospital Essen (AöR), Essen, Germany.
  • Marcel Wiesweg
    Department of Medical Oncology, West German Cancer Center, University Hospital Essen (AöR), Essen, Germany.
  • Hideo A Baba
    Institute for Pathology, University Hospital, University Duisburg-Essen, Essen, Germany.
  • Felix Nensa
    Institute for AI in Medicine (IKIM), University Hospital Essen, 45131 Essen, Germany.
  • Jan Egger
    Institute for Computer Graphics and Vision, Faculty of Computer Science and Biomedical Engineering, Graz University of Technology, Graz, Austria.
  • Klaus-Robert Müller
    Berlin Institute for the Foundations of Learning and Data (BIFOLD), Berlin, Deutschland.
  • Martin Schuler
    Department of Medical Oncology, West German Cancer Center, University Hospital Essen (AöR), Essen, Germany.
  • Frederick Klauschen
    Pathologisches Institut, Ludwig-Maximilians-Universität München, Thalkirchner Str. 36, 80337, München, Deutschland. f.klauschen@lmu.de.
  • Jens Kleesiek
    AG Computational Radiology, Abteilung Radiologie, Deutsches Krebsforschungszentrum (DKFZ), Im Neuenheimer Feld 280, 69120, Heidelberg, Deutschland. j.kleesiek@dkfz-heidelberg.de.

Keywords

External Resources

Popular Topics
Recent Journals