Antimicrobial Resistance (AMR) Dataset Release

Sign up for Updates

In collaboration with Mass General Brigham and PhysioNet, we plan to release a de-identified dataset for Antimicrobial Resistance (AMR) in Urinary Tract Infections (UTIs). The data is derived from electronic health record (EHR) information on over 100,000 infections treated at Massachusetts General Hospital and Brigham & Women’s Hospital in Boston, MA, USA between 2007 and 2016. The data includes

  • Ground-truth labels for antibiotic resistance to all common antibiotics used to treat UTIs, derived from laboratory testing
  • Antibiotic treatment decisions, which were made without knowledge of the test results
  • Patient and specimen features useful for prediction of resistance and treatment decisions

If you would like to be notified when the dataset is available on PhysioNet, please click the button and provide your email address. If you are not comfortable using a Google Form, you may email us directly at moberst {@ | at} mit.edu