MIT-LCP / MIT-LCP/mimic-code

Delirium Assessment wrong itemids?

Open
#1,542 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
3.4k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

I am trying to extract delirium cases from the MIMIC-III Database. One very prominent delirium assessment method is the confusion assessment method (CAM). I have found CAM as items in chartevents. There are 8 related chartevents. CAM consists of 4 feature and every feature is listed twice for some reason.

However there is also an ITEM with ITEMID 228332 that just says "delirium assessment". Can somebody tell me what assessment method was used here?

Update: After taking a closer look at the results of the CAM-ICU assessment I ran into some issues.
CAM-ICU consists of 4 features that are assessed:

  • Feature 1: Mental Status (MS) Change (ITEMIDs: 228300, 228337)
  • Feature 2: Inattention (ITEMIDs: 228301, 228336)
  • Feature 3: Altered Level of Consciousness (LOC)/ RASS (ITEMIDs: 228302, 228334)
  • Feature 4: Disorganized Thinking (ITEMIDs: 228303, 228335)
    If Features 1 and 2 and additionally either 3 or 4 are answered with yes the result is positive (delirium present). I have checked some patients where the ITEMIDs 228334-228337 were used and this seems normal. However for patients where 228300-228303 were used the assessment results make no sense. For example for subject_id 40083 a lot of times only feature 4 was checked. If it was "no" nothing else was checked. However if features 1-3 were positive then there could still be a delirium case. Feature 2 was checked only in one of the assessments, but it is a necessary condition for the result being positive. Checking 1,3 and 4 how it was done several times for this patient hence makes no sense.

I assume that the labels and ITEMIDs for the ITEMIDs 228300-228303 do not match. Can somebody confirm that?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the MIMIC-III online documentation and the chartevents entries for ITEMIDs 228300-228303 and 228332, then compare them with the CAM-ICU mappings listed in the issue, including subject_id 40083. Done means determining whether the labels and ITEMIDs are mismatched and documenting which assessment method ITEMID 228332 represents.

Written by the indexing model from the issue text.

Assessment

Domain
data, databases
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.