Simulating complex patient populations with hierarchical learning effects to support methods development for post-market surveillance.

Journal: BMC medical research methodology
Published Date:

Abstract

BACKGROUND: Validating new algorithms, such as methods to disentangle intrinsic treatment risk from risk associated with experiential learning of novel treatments, often requires knowing the ground truth for data characteristics under investigation. Since the ground truth is inaccessible in real world data, simulation studies using synthetic datasets that mimic complex clinical environments are essential. We describe and evaluate a generalizable framework for injecting hierarchical learning effects within a robust data generation process that incorporates the magnitude of intrinsic risk and accounts for known critical elements in clinical data relationships.

Authors

  • Sharon E Davis
    Vanderbilt University School of Medicine, Nashville, TN.
  • Henry Ssemaganda
    Comparative Effectiveness Research Institute, Lahey Hospital and Medical Center, 41 Mall Road, Burlington, MA, 01803, USA.
  • Jejo D Koola
    UC Health Department of Biomedical Informatics, University of California San Diego, 9500 Gilman Dr. MC 0728, La Jolla, San Diego, CA, 92093-0728, USA.
  • Jialin Mao
    Department of Population Health Sciences, Weill Cornell Medicine, New York, NY, United States.
  • Dax Westerman
    Department of Biomedical Informatics, Vanderbilt University Medical Center, 2525 West End Ave, Suite 1475, Nashville, TN, 37203, USA.
  • Theodore Speroff
    Departments of Medicine and Biostatistics, Vanderbilt University Medical Center, 1313 21St Avenue South, Oxford House, Room 209, Nashville, TN, 37232, USA.
  • Usha S Govindarajulu
    Center for Biostatistics, Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, Box 1077, New York, NY, 10029, USA.
  • Craig R Ramsay
    Health Services Research Unit, University of Aberdeen, Health Sciences Building, Foresterhill, 3rd Floor, Aberdeen, AB25 2ZD, UK.
  • Art Sedrakyan
    Populational Health Sciences, Weill Cornell Medicine, New York City, New York.
  • Lucila Ohno-Machado
    University of California San Diego, La Jolla, CA.
  • Frederic S Resnic
    Division of Cardiovascular Medicine and Comparative Effectiveness Research Institute, Lahey Hospital and Medical Center, Tufts University School of Medicine, 41 Burlington Mall Road, Burlington, MA, 01805, USA.
  • Michael E Matheny
    Vanderbilt University School of Medicine, Nashville, TN.