MIMIC4 Readmission Prediction#815
Merged
jhnwu3 merged 2 commits intosunlabuiuc:masterfrom Feb 4, 2026
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Overview
This PR updates the
readmission_prediction_mimic4_fnfor PyHealth 2.0.In addition to supporting PyHealth 2.0, the new
ReadmissionPredictionMIMIC4task has the following improvements. First, it takes adatetime.timedeltainstead of anintfor the readmission window, making the input parameter clearer and more flexible. Second, it can optionally exclude patients whoseanchor_ageis under 18 (a previously unimplemented#todo).Besides the items listed above,
ReadmissionPredictionMIMIC4should be logically equivalent toreadmission_prediction_mimic4_fn.Testing
I added unit tests for
ReadmissionPredictionMIMIC4and created and ranexamples/readmission/readmission_mimic4_rnn.py.Additional Notes
I also removed the
Readmission30DaysMIMIC4task, since it is pretty much a duplicate ofReadmissionPredictionMIMIC4. The one difference in logic is thatReadmission30DaysMIMIC4excluded visits that lasted 12 hours or less.I kept this deletion in a separate commit, so if you'd rather keep both, I can easily revert the deletion. If we do keep
Readmission30DaysMIMIC4, I'll add some unit tests.