{
  "abstract": "The rapid integration of large language models (LLMs) into clinical practice offers promising benefits, including assistance with documentation, decision support and patient communication. However, these advantages are tempered by concerns around model accuracy, data privacy, clinician trust and regulatory responsibility. In this comment, we propose a clinician-led, risk-stratified framework to guide responsible adoption of LLMs in healthcare. The framework categorises applications into four risk tiers: low risk, moderate risk, high risk and critical risk. Each tier demands tailored oversight, validation and governance, with increasing levels of statutory regulatory scrutiny (eg., European Union Artificial Intelligence Act and U.S. Food and Drug Administration) and clinical supervision. We argue that proactive self-regulation combined with ongoing quality management and clinician education is essential to safely integrate LLMs into ongoing care.",
  "authors": [
    {
      "affiliations": [
        "Centre for Physical Activity Research, Copenhagen University Hospital - Rigshospitalet, Copenhagen, Denmark",
        "Department of Cellular and Molecular Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark",
        "Department of Plastic and Breast Surgery, Zealand University Hospital, Roskilde, Denmark"
      ],
      "name": "Milan Mohammad"
    },
    {
      "affiliations": [
        "Department of Clinical Pharmacology, Bispebjerg and Frederiksberg Hospital, Copenhagen, Denmark",
        "Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark",
        "Copenhagen Phase IV Unit (Phase4CPH), Department of Clinical Pharmacology, Center for Clinical Research and Prevention, Bispebjerg and Frederiksberg Hospital, Copenhagen, Denmark"
      ],
      "name": "Espen Jimenez-Solem"
    },
    {
      "affiliations": [
        "Lægehuset Ferritslev, Funen, Denmark",
        "Research Unit for General Practice and Centre for Digital Health Research, University of Southern Denmark, Odense, Denmark"
      ],
      "name": "Michael Hejmadi"
    },
    {
      "affiliations": [
        "Roche Diagnostics AS, Copenhagen, Denmark"
      ],
      "name": "Andreas Pihl"
    }
  ],
  "title": "Self-regulating the use of large language models in clinical practice: a risk-stratified approach",
  "uid": "b32ddf14-4932-5b29-9053-c990375e778f"
}