cumc-dbmi/cehrbert

CEHR-BERT: Incorporating temporal information from structured EHR data to improve prediction tasks

49
/ 100
Emerging

This project helps healthcare researchers and data scientists use electronic health record (EHR) data to predict patient outcomes or understand disease progression. It takes structured EHR data, such as medical codes, diagnoses, and procedures, typically in OMOP or MEDS format, and generates specialized patient representations. These representations are then used to train and evaluate predictive models for various clinical tasks.

Use this if you are working with structured electronic health record (EHR) data and need to build predictive models that account for the chronological order and timing of patient visits and medical events.

Not ideal if your data is not in OMOP or MEDS format, or if you are working with unstructured clinical notes or images rather than structured medical codes.

EHR analysis clinical prediction observational studies patient risk stratification medical informatics
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

45

Forks

18

Language

Python

License

MIT

Last pushed

Dec 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/cumc-dbmi/cehrbert"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.