{
  "abstract": "Artificial intelligence (AI) is developing rapidly. In particular, in the area of machine learning (ML), significant progress has been made, and large language models (LLMs) have become widely available (for definitions see box 1). This sparks significant interest in the potential application of this technology across various sectors, including healthcare. One area where LLMs promise substantial benefits is evidence synthesis.1 This article discusses the opportunities, challenges and risks associated with using AI, and LLMs in particular, for this purpose, drawing on insights from the third Methods Forum of Cochrane Germany, held in Freiburg, Germany, on 14 June 2024.",
  "authors": [
    {
      "affiliations": [
        "Institute for Evidence in Medicine, Medical Center - University of Freiburg, Faculty of Medicine, Freiburg, Germany"
      ],
      "name": "Waldemar Siemens"
    },
    {
      "affiliations": [
        "Cochrane Germany, Cochrane Germany Foundation, Freiburg, Germany",
        "Cochrane Switzerland, Lausanne, Switzerland"
      ],
      "name": "Erik von Elm"
    },
    {
      "affiliations": [
        "Institute of Medical Biometry and Statistics (IMBI), Medical Center – University of Freiburg, Faculty of Medicine, Freiburg, Germany"
      ],
      "name": "Harald Binder"
    },
    {
      "affiliations": [
        "Eye Center, Medical Center, Faculty of Medicine, University of Freiburg, Freiburg, Germany"
      ],
      "name": "Daniel Böhringer"
    },
    {
      "affiliations": [
        "Institute for Evidence in Medicine, Medical Center - University of Freiburg, Faculty of Medicine, Freiburg, Germany",
        "Cochrane Germany, Cochrane Germany Foundation, Freiburg, Germany"
      ],
      "name": "Angelika Eisele-Metzger"
    },
    {
      "affiliations": [
        "Department for Evidence-based Medicine and Evaluation, University for Continuing Education, Krems, Austria",
        "RTI International, Center for Public Health Methods, Durham, North Carolina, USA"
      ],
      "name": "Gerald Gartlehner"
    },
    {
      "affiliations": [
        "Pitts.ai, Zeist, Netherlands"
      ],
      "name": "Piet Hanegraaf"
    },
    {
      "affiliations": [
        "Cochrane Evidence Synthesis Unit Germany/UK, Institute of General Practice, Heinrich-Heine-Universitat, Düsseldorf, Germany"
      ],
      "name": "Maria-Inti Metzendorf"
    },
    {
      "affiliations": [
        "Pitts.ai, Zeist, Netherlands"
      ],
      "name": "Jacob-Jan Mosselman"
    },
    {
      "affiliations": [
        "Evidence Prime, Krakow, Poland"
      ],
      "name": "Artur Nowak"
    },
    {
      "affiliations": [
        "Cochrane Eyes and Vision, Dept. of Ophthalmology, University of Colorado Anschutz Medical Campus, Aurora, Colorado, USA"
      ],
      "name": "Riaz Qureshi"
    },
    {
      "affiliations": [
        "EPPI Centre, UCL Social Research Unit, University College London, London, UK"
      ],
      "name": "James Thomas"
    },
    {
      "affiliations": [
        "Institute for Quality and Efficiency in Healthcare, Cologne, Germany"
      ],
      "name": "Siw Waffenschmidt"
    },
    {
      "affiliations": [
        "Institute for Evidence in Medicine, Medical Center - University of Freiburg, Faculty of Medicine, Freiburg, Germany",
        "Cochrane Germany, Cochrane Germany Foundation, Freiburg, Germany"
      ],
      "name": "Valérie Labonté"
    },
    {
      "affiliations": [
        "Institute for Evidence in Medicine, Medical Center - University of Freiburg, Faculty of Medicine, Freiburg, Germany",
        "Cochrane Germany, Cochrane Germany Foundation, Freiburg, Germany"
      ],
      "name": "Joerg J Meerpohl"
    }
  ],
  "title": "Opportunities, challenges and risks of using artificial intelligence for evidence synthesis",
  "uid": "d6e912af-e1bc-5bc3-9218-6f27d9019c91"
}