The {medicaldata} package is purely a data package, for the purpose of collecting well-documented medical datasets in one package for teaching to medical students, residents, fellows, nurses, pharmacists, physician assistants, and anyone else who wants to learn R for use with medical data.

The de-identified datasets included in this package come from a variety of sources, including:

  • donations by generous authors
  • sourcing from other R packages
  • the TSHS (Teaching Statistics in the Health Sciences) project, which can be found at link, and is sponsored by the American Statistical Association.
  • reconstruction of datasets from historically important clinical studies, like the scurvy study by James Lind, and the first clinical trial of Streptomycin in Pulmonary Tuberculosis.

Each dataset is documented in three ways:

  • a help file, which can be accessed with help('dataset_name') from the Console pane
  • a pdf document describing the study, found at the Github README page here
  • a pdf codebook, found at the Github README page here

Currently, the datasets included are:

  • Streptomycin in Tuberculosis (strep_tb)
  • Scurvy RCT (scurvy)
  • Indomethacin RCT to Prevent Post-ERCP Pancreatitis (indo_rct)
  • Sulindac RCT for polyps (polyps)
  • Covid Testing (covid_testing)
  • Blood Storage (prostate cancer) (blood_storage)
  • Cytomegalovirus in BMT (cytomegalovirus)
  • Esophageal cancer (esoph_ca)
  • Laryngoscope (laryngoscope)
  • Licorice gargle (licorice_gargle)
  • Obstetric Periodontal Therapy (opt)
  • Smartpill (smartpill)
  • Supraclavicular (supraclavicular)
  • Indomethacin Pharmacokinetics (indometh)
  • Theophylline Pharmacokinetics (theoph)