3778/icd-prediction-mimic

Predicting ICD Codes from Clinical Notes

44
/ 100
Emerging

This project helps medical coders and health information managers automatically assign medical diagnosis codes to patient records. It takes a patient's discharge summary (clinical notes) as input and outputs a list of relevant ICD-9 diagnosis codes. The primary users are professionals responsible for medical billing, health record management, and epidemiological research.

No commits in the last 6 months.

Use this if you need to automate the process of assigning ICD codes from unstructured clinical text, reducing manual effort and improving coding efficiency.

Not ideal if you need to work with a different coding standard (e.g., ICD-10 directly) or if your clinical notes are in a language other than English (as trained on MIMIC-III data).

medical-coding health-information-management clinical-documentation diagnosis-coding healthcare-analytics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

64

Forks

24

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Sep 11, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/3778/icd-prediction-mimic"

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