Disease names are anonymised

[JoakimEdin]

Prerequisites

• [X ] Put an X between the brackets on this line if you have done all of the following:
  • Checked the online documentation: https://mimic.mit.edu/
  • Checked that your issue isn't already addressed: https://github.com/MIT-LCP/mimic-code/issues?utf8=%E2%9C%93&q=

Description

I believe this is a difficult error to fix as it's related to the algorithm to de-identify the clinical notes. I've seen multiple examples of disease names being anonymized since they contain a name in them—for example, Lewis Body Dementia, Creutzfeldt-Jakob disease, etc. This makes the data noisy for automated medical coding, which many are using it for. Will it be possible to fix this issue?

Example:

hadm_id: 23052089 from MIMIC-IV

ACUTE/ACTIVE ISSUES:

disease Body Dementia

Visual Hallucinations

The patient appears to have acute on chronic progression of his ___ disease. Unclear if this is disease progression or

[alistairewj]

I do have some ideas for how to improve this. Nothing immediately available but it's good to have reports so we can build up our set of test cases, thanks. Didn't expect Lewy Body Dementia to be deid but it does make sense in hind sight!