MIT-LCP / MIT-LCP/mimic-code

Were the current Concepts codes compatible with MIMIC-IV V3.0?

Open
#1,772 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

Prerequisites
Description

I've noticed that MIMIC-IV V3.0 has been released, and there has been discussion about installation codes. However, I've found that the item_id in MIMIC-IV V3.0 has significantly changed compared to MIMIC-IV V2.0 and V2.2. For example, the item_id for lymphocyte count is not entirely consistent between MIMIC-IV V3.0 and MIMIC-IV V2.2 (Figure was as shown below, in MIMIC-IV V2.2, the item_id for lymphocyte percentage were 51333, 52769, and 53152, while in MIMIC-IV V3.0, they were 51333, 52769, and 53132). This means that the current official Concepts codes might produce errors in accuracy when applied to MIMIC-IV V3.0 due to these item_id changes, even though the codes had no running errors.

Is it necessary to revise all the Concepts code involving the relevant item_id when installing Concepts for MIMIC-IV V3.0, or can the existing Concepts codes be used directly without revised? I would appreciate clarification on this matter. Thank you! @alistairewj

MIMIC-IV V3 0

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 by reviewing the MIMIC-IV documentation and issue #1770, then compare the cited item_id values between MIMIC-IV V2.2 and V3.0. Inspect the current Concepts code that uses those identifiers. Done means documenting whether the existing codes remain compatible or identifying the Concepts code changes required for V3.0.

Written by the indexing model from the issue text.

Assessment

Domain
databases
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.