rvandewater/YAIB

🧪Yet Another ICU Benchmark: a holistic framework for the standardization of clinical prediction model experiments. Provide custom datasets, cohorts, prediction tasks, endpoints, preprocessing, and models. Paper: https://arxiv.org/abs/2306.05109

64
/ 100
Established

This project helps clinical researchers and data scientists standardize machine learning experiments using Intensive Care Unit (ICU) electronic health record data. You can input raw or preprocessed ICU patient data and define specific prediction tasks like mortality or kidney injury to get benchmarked model results. It's designed for medical researchers, biostatisticians, and clinical data scientists evaluating and comparing predictive models in critical care.

Available on PyPI.

Use this if you need a consistent and reproducible way to test and compare different machine learning models on ICU patient data for clinical prediction tasks.

Not ideal if you are a clinician looking for a ready-to-use diagnostic tool, as this is a research framework for model development and evaluation, not a deployed clinical application.

critical-care-research clinical-prediction healthcare-machine-learning electronic-health-records medical-data-science
Maintenance 10 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

93

Forks

28

Language

Python

License

MIT

Last pushed

Mar 13, 2026

Commits (30d)

0

Dependencies

22

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rvandewater/YAIB"

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