NLM-Scrubber is a freely available clinical text deidentification tool designed and developed at the National Library of Medicine. Our aim is to enable clinical scientists to access clinical health information that is not associated with the patient by following the Safe Harbor principles as outlined in the HIPAA Privacy Rule.
The goal of NLM-Scrubber is to produce HIPAA compliant deidentified health information for scientific use; however, the success rate of this goal depends on the input data. It is the data manager's responsibility to evaluate NLM-Scrubber on their datasets and make an informed decision whether NLM-Scrubber is the right tool for their purpose.
Since it may be possible to reidentify individuals from deidentified data with the use of additional information linked to the same individuals, we strongly recommend our users not to share deidentified data without a strong data use agreement.
Please contact us if the described steps for using NLM-Scrubber are unclear or if you encounter problems when you try to run NLM-Scrubber on your test files.
We also invite you to join NLM-Scrubber Announcements list, which will keep you updated as new versions of NLM-Scrubber are released.