Skip to content

fixed the package name cehrbert -> cehrbert_data for hf_readmission t… #106

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ChaoPang merged 2 commits into from
May 4, 2025
Merged

fixed the package name cehrbert -> cehrbert_data for hf_readmission t… #106

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
80a70de
fixed the package name cehrbert -> cehrbert_data for hf_readmission t…
ChaoPang May 4, 2025
8ba9538
created a section to warn users about the incompatibility between OMO…
ChaoPang May 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,12 @@ Build the project
pip install -e .[dev]
```

## OMOP vs. MEDS Format Considerations
CEHR-BERT can be trained using either the OMOP or MEDS data formats; however, models trained on one format are not compatible with those trained on the other.
This incompatibility arises because CEHR-BERT uses different concept identifiers depending on the format: standard concept IDs (e.g., SNOMED for conditions) in OMOP,
and source concept IDs (e.g., ICD-9/10) in MEDS. The mappings between these terminologies are many-to-many, making direct alignment between formats unreliable.
It is therefore crucial to use a consistent data format across pretraining, fine-tuning, and downstream tasks such as linear probing.

## Instructions for Use with [MEDS](https://github.com/Medical-Event-Data-Standard/meds)
Step 1. Convert MEDS to the [meds_reader](https://github.com/som-shahlab/meds_reader) database
---------------------------
Expand Down Expand Up @@ -222,7 +228,7 @@ export SPARK_EXECUTOR_MEMORY="12g"
```
Generate the HF readmission prediction task
```console
python -u -m cehrbert.prediction_cohorts.hf_readmission \
python -u -m cehrbert_data.prediction_cohorts.hf_readmission \
-c hf_readmission -i ~/Documents/omop_test/ -o ~/Documents/omop_test/cehr-bert \
-dl 1985-01-01 -du 2020-12-31 \
-l 18 -u 100 -ow 360 -ps 0 -pw 30 \
Expand Down