MIT-LCP / MIT-LCP/mimic-code

Question on Diagnosis Timing in the MIMIC Database for Research on Sepsis and AKI

Open
#1,843 1 comment 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

In the MIMIC database, ICD codes are used to identify patients with specific diagnoses. In the context of my research on building a predictive model for acute kidney injury (AKI) in sepsis patients during their ICU stay, it is crucial to clarify the timing of diagnosis, particularly with respect to ICU admission. Specifically, I need to determine whether the diagnosis of sepsis and AKI was made before, during, or after the patient was admitted to the intensive care unit.
Could you please advise on the best approach to ensure that: 1. Sepsis Diagnosis: How can I confirm that the sepsis diagnosis occurred at the time of ICU admission? 2. AKI Diagnosis: How can I ensure that AKI was diagnosed during the hospitalization in the ICU, after the patient’s ICU admission, rather than before the period leading up to the ICU stay? Any guidance or suggestions on how to best address these timing issues would be greatly appreciated, as they are critical for the accuracy of my predictive model.
Let me know if you'd like further revisions or additions!

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 how MIMIC records ICD diagnoses and ICU admission timing. Determine whether sepsis and AKI diagnosis times can be compared with ICU admission to establish the requested cohort and prediction window. Done means documenting a clear approach for distinguishing diagnoses made before, during, or after the ICU stay.

Written by the indexing model from the issue text.

Assessment

Domain
databases, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.