OHDSI / OHDSI/FeatureExtraction

Covariates from in-cohort period?

Open
#105 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
R
Stars
74
Forks
63
PR merge metrics
No merged PRs in 30d

Description

Hi,

I use the FeatureExtraction package (especially temporal feature function) for constructing covariates not only before the index date but after the index date. The covariates with the timeID are useful for tracking how many patients were using that covariate.

but I can't find the options restricting the covariate period in each patient.
How can I restrict the covariates from only the in-cohort period (from cohort_start_date to cohort_end_date)?

For example, I want to get the drug_expousure covariates from each patient's inpatient period. To my knowledge, in createTemporalCovariateSettings, I can define the same end day only adding to cohort_start_date for all patients.

As you know, we can restrict the time period for each patient after getting the whole covariates in R. However, I think it is inefficient.

If I have something missed or if you have any other options or comments, please let me know.

Best wishes,
Chungsoo

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 reading createTemporalCovariateSettings and the temporal feature-function implementation to understand how cohort start and end dates are currently applied. Check whether patient-specific cohort periods can be passed through the covariate generation flow; done means covariates can be restricted to each patient's cohort_start_date through cohort_end_date without post-processing in R.

Written by the indexing model from the issue text.

Assessment

Tech stack
r
Domain
data
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.