MIT-LCP / MIT-LCP/mimic-code

Questions about Ectopy

Open
#776 1 comment 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

Description

For the Ectopy Type 1 and Type 2, the majority of the input to value is 'None'. Can you clarify whether this is because no irregularity was detected or did they simply not record the type of irregularity?

SELECT A.itemid, label, total_obs, recorded_none 
FROM  
(SELECT itemid, COUNT(*) AS total_obs FROM CHARTEVENTS 
WHERE ITEMID in (161, 162, 224650, 226479)
GROUP BY ITEMID) A
INNER JOIN
(SELECT itemid, COUNT(*) as recorded_none FROM CHARTEVENTS 
WHERE ITEMID in (161, 162, 224650, 226479) AND value='None'  
GROUP BY ITEMID) B
ON A.itemid = B.itemid
INNER JOIN
d_items d ON A.itemid = d.itemid
itemid label total_obs recorded_none
161 Ectopy Type 3236350 2743187
162 Ectopy Type 2 10954 3391
224650 Ectopy Type 1 1849287 1511993
226479 Ectopy Type 2 15563 4233

Over 80% of the entries for Type 1 was recorded as 'None', which seems very high. Is this something that is regularly checked but rarely detected?

Secondly, what is the difference between Ectopy Type 1 and Type 2? I had a look at the distinct values recorded in these categories along with their frequency using

SELECT DISTINCT value, itemid, COUNT(value)
FROM CHARTEVENTS WHERE ITEMID IN (161, 162, 224650, 226479)
GROUP BY itemid, value
ORDER BY itemid, value

It appears that aside from 'None', the most popular entries are "PVC's" (premature ventricular contraction) and "PAC's" (premature atrial contraction) for both Type 1 and Type 2 Ectopy. I'd be grateful if you can shed some light on what the distinction between the Ectopy Types are.

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 Ectopy item IDs and the supplied CHARTEVENTS queries, then consult the linked MIMIC online documentation. Done means clarifying what “None” represents and documenting the distinction between Ectopy Type 1 and Type 2.

Written by the indexing model from the issue text.

Assessment

Tech stack
sql
Domain
databases
Issue type
Documentation
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.