MIT-LCP / MIT-LCP/mimic-code

Parenteral Nutrition

Open
#1,076 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Prerequisites
Description

Hi, our research group is very interested in hypoglycemia. For this reason, we are looking into parenteral nutrition, which reduces the risk of adverse hypo events. On MIMIC-III Carevue, the following items can be found for TPN:

item name table count
30032 TPN inputevents_cv 204714
30196 TPN D10.0 inputevents_cv 129029
30096 TPN w/Lipids inputevents_cv 50191
30197 TPN D11.0 inputevents_cv 29966
30199 TPN D12.5 inputevents_cv 27589
30198 TPN D12.0 inputevents_cv 21246
30200 TPN D15.0 inputevents_cv 21023
30325 TPN D13.0 inputevents_cv 16269
30194 TPN D9.0 inputevents_cv 12788
30313 TPN D14 inputevents_cv 12481
30301 TPN D8 inputevents_cv 11934
30191 TPN D5.0 inputevents_cv 10195
30193 TPN D7.5 inputevents_cv 8204

Putting all the items together, there are around 600k entries.

However, TPN appears in far fewer item names in Metavision:

item name table count
225916 TPN w/ Lipids inputevents_mv 6009
225917 TPN without Lipids inputevents_mv 3843

Do you perhaps know where parenteral nutrition is hiding on MIMIC-III Metavision / MIMIC-IV? Would be incredibly helpful.

Best,
Drago

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 online documentation and the Carevue and Metavision inputevents_cv/inputevents_mv tables named in the issue. Compare the listed TPN item identifiers across MIMIC-III Metavision and MIMIC-IV, and document where parenteral nutrition entries can be found. Done means a maintainer-confirmed mapping or explanation of the relevant items and tables.

Written by the indexing model from the issue text.

Assessment

Domain
data, databases
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.