EHRMamba Implementation Into PyHealth #809
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
jhnwu3
requested changes
Feb 3, 2026
Collaborator
jhnwu3
left a comment
jhnwu3
left a comment
There was a problem hiding this comment.
Can we add this to the docs/ as well?
models.rst
and the api/models/ehr_mamba.rst here?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Arjun Chatterjee
Model implementation
Adds EHRMamba, a Mamba model for electronic health records.
Closely modeled off of the paper - EHRMAMBA: Towards Generalizable and Scalable Foundation Models for Electronic Health Records
Main work:
pyhealth/models/ehrmamba.py: New module with
RMSNorm,MambaBlock(SSM with causal conv), andEHRMamba(BaseModel). Uses existingEmbeddingModel, per-feature Mamba stacks, andget_last_visitfor the classification head. Compatible with current PyHealth tasks and Trainer.Testing and example notebook will also be included. I also included an icustays csv file because the mimic4ehrdataset class has default table icustays which is not present anywhere in the codebase.