MIMIC-IV Notes: Censoring of echo observations as PHI
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 3.4k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
Prerequisites
- Put an X between the brackets on this line if you have done all of the following:
[X] Checked the online documentation: https://mimic.mit.edu/
[X] Checked that your issue isn't already addressed: https://github.com/MIT-LCP/mimic-code/issues?utf8=%E2%9C%93&q=
Description
Hi,
thank you very much for providing and maintaining this database!
I would like to point to an issue that appears to be present only in MIMIC-IV, that was not a problem in MIMIC-III.
In our project we are operating on the free-text clinical notes. In MIMIC-III these used to include information regarding atrial dilation, which could easily be string matched. The notes were written in the form:
LEFT ATRIUM: Mild LA enlargement
LEFT ATRIUM: Moderate LA elongation
In MIMIC-IV, it appears that such information was flagged as PHI, and replaced with three underscores in the discharge reports. At least this is my understanding. What is now present in the notes is:
LEFT ATRIUM: Mild ___
LEFT ATRIUM: Moderate ___
Is this a known issue? Is there a possibility you may bring this information back?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by comparing the cited MIMIC-III and MIMIC-IV discharge-note examples and reviewing the online MIMIC documentation. Determine whether the missing echocardiography observations were intentionally censored as PHI and whether the maintainers can restore them; done means a documented resolution or decision on restoration.
Written by the indexing model from the issue text.
Assessment
- Domain
- data, security
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100