Looking for sources of available de-identified EHR/EMR datasets that would be suitable as a benchmark to compare against existing datasets.

This would be similar to what is available from QResearch: https://www.qresearch.org

This is for a US-based project though, so US sources would be ideal.



First check out https://healthdata.gov/. The US government has a lot of targeted data sets that may be exactly what you need or at least get you started.

As far as accessing "non-gov" data, I've been implementing EHRs for a decade and I've yet to see organizations make that available other than through an HIE. There are a lot of regulations in the industry and security tends to be very tight.

That being said, I do have a couple of ideas that may help. If you were able to volunteer at a healthcare organization as an analyst (e.g. Volunteers in Medicine) you'd be able to get access to their data.

Moreover, if your research will help a hospital or large medical group solve a pressing problem, data access may not be an issue and they'd be willing to help you out.

  • Thanks very much for your answer. healthdata.gov looks to be a great resource. Yes, indeed, this question is in relation to a project within a healthcare system. Sep 13 '18 at 15:43

Physionet is an online repository of EHR databases.

For example, here are some (credentialed access) deidentified ICU datasets:


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.