MIT-LCP / MIT-LCP/mimic-code

mortality and mortality day

Open
#789 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Prerequisites

https://github.com/MIT-LCP/mimic-code/blob/master/concepts/cookbook/mortality.sql

Description

admittime is accurate to the minute but dod is not.
subject_id = '8547' and hadm_id = '131849' and icustay_id = '200119'
admissions table admittime: 2173-06-29 01:50:00 dischtime: 2173-06-30 07:58:00 deathtime: 2173-06-30 07:58:00
icustays table intime: 2173-06-29 01:50:00 outtime: 2173-06-30 07:58:00
patients table dod/dod_hosp/dod_ssn: 2173-06-30 00:00:00
round(((date_part('epoch'::text, (ie.outtime - ie.intime)) / (((60 * 60) * 24))::double precision))::numeric, 4) AS los_icu,
round(((date_part('epoch'::text, (adm.dischtime - adm.admittime)) / (((60 * 60) * 24))::double precision))::numeric, 4) AS los_hospital,

when we use los_icu>2 exclude deceased patient,but patients table‘ dod/dod_hosp/dod_ssn may not accurate. How to exclude those people.

  • what you have tried
  • references to similar issues
  • queries demonstrating your question (if applicable)

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 concepts/cookbook/mortality.sql and inspect how the admissions, icustays, and patients tables are used for mortality and length-of-stay calculations. Reproduce the subject_id 8547, hadm_id 131849, and icustay_id 200119 timestamps, then establish a documented, reproducible rule for handling deceased patients whose date-of-death values lack time precision.

Written by the indexing model from the issue text.

Assessment

Tech stack
sql
Domain
databases
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.