Peer-Reviewed Publication
Nature2026;656(8128):577-589.August 1, 2026Journal Article
Safety and security of large language models in healthcare.
Jan Clusmann1,2,3,4, Oscar Freyer1, Max Ostermann1, Dyke Ferber1,5, Narmin Ghaffari Laleh1,5, Lars Hilgers1,2, Fiona R Kolbinger6,7, Carolin V Schneider1,3,8, Andrea Downing9, Magdalena Katharina Wekenborg1, Stephen Gilbert1,10, Sebastian Foersch11, Daniel Truhn12, Isabella C Wiest1,4,13, Jakob Nikolas Kather14,15,16
1Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany.
2Department of Medicine I, Faculty of Medicine, TUD Dresden University of Technology, Dresden, Germany.
3Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany.
4German Cancer Consortium (DKTK) partner site Dresden and German Cancer Research Center (DKFZ), Heidelberg, Germany.
5Department of Medical Oncology, National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany.
6Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, USA.
7Department of Visceral, Thoracic and Vascular Surgery, University Hospital and Faculty of Medicine Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany.
8The Institute for Translational Medicine and Therapeutics, the Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
9The Light Collective, Eugene, OR, USA.
10Faculty of Business and Economics, TUD Dresden University of Technology, Dresden, Germany.
11Institute of Pathology, University Medical Center Mainz, Mainz, Germany.
12Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany.
13Department of Medicine II, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany.
14Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany. kather.jn@tu-dresden.de.
15Department of Medicine I, Faculty of Medicine, TUD Dresden University of Technology, Dresden, Germany. kather.jn@tu-dresden.de.
16Department of Medical Oncology, National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany. kather.jn@tu-dresden.de.
Abstract
Integration of artificial intelligence methods into clinical care is proceeding rapidly, driven by advances in generative artificial intelligence, most notably large language models. Large language models trained on large amounts of text have shown potential across nearly every domain of healthcare. However, their broad applicability also comes with new responsibilities, vulnerabilities and threat…
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