{
  "abstract": "Healthcare delivery is being transformed by the rapid growth of data, advancements in artificial intelligence (AI) and other technologies. In healthcare, obtaining real-world data can be time-consuming and limited to those with approved access to protected health information (PHI) due to ethical, legal and regulatory considerations. As patient care becomes increasingly data driven, the need for faster access to data, better ability to protect the identities of patients, and overcoming technical and regulatory barriers to assembling sufficiently large datasets for modern AI methods is paramount. Conventional data access strategies are no longer sufficient to enable evidence generation at scale.",
  "authors": [
    {
      "affiliations": [
        "Department of Biomedical Informatics, Biostatistics, and Medical Epidemiology, University of Missouri, Columbia, Missouri, USA"
      ],
      "name": "Randi Foraker"
    },
    {
      "affiliations": [
        "Department of Obstetrics and Gynecology, New York University School of Medicine, New York, New York, USA"
      ],
      "name": "Jon D Morrow"
    },
    {
      "affiliations": [
        "Biological Sciences Division, The University of Chicago, Chicago, Illinois, USA"
      ],
      "name": "Julie A Johnson"
    },
    {
      "affiliations": [
        "Department of Medicine, Washington University in St. Louis School of Medicine, St. Louis, Missouri, USA"
      ],
      "name": "Adam B Wilcox"
    },
    {
      "affiliations": [
        "Department of Medicine, McGill University, Montréal, Québec, Canada"
      ],
      "name": "Alan J Forster"
    },
    {
      "affiliations": [
        "Department of Medicine, Washington University in St. Louis School of Medicine, St. Louis, Missouri, USA"
      ],
      "name": "Philip R O Payne"
    }
  ],
  "title": "Understanding synthetic data: artificial datasets for real-world evidence",
  "uid": "718e01eb-c296-5b4d-8f42-a76dbbd3a312"
}