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
Integrates with PyTorch Lightning 2.0+ for model training and supports four major ICU datasets (MIMIC-III/IV, eICU-CRD, HiRID, AUMCdb) with varying temporal resolutions from 1-minute to hourly sampling. The framework operates on preprocessed parquet files and provides extensible abstractions for adding custom datasets, tasks, and preprocessing pipelines through companion packages (YAIB-cohorts, YAIB-models, ReciPys).
Available on PyPI.
Stars
93
Forks
28
Language
Python
License
MIT
Category
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.
Related frameworks
YerevaNN/mimic3-benchmarks
Python suite to construct benchmark machine learning datasets from the MIMIC-III 💊 clinical database.
Mubarraqqq/gnn-challenge
This project focuses on predicting maternal-fetal health outcomes, specifically early detection...
justin13601/ACES
[ICLR 2025] ACES: Automatic Cohort Extraction System for Event-Streams
myADLM/ADLM-2025-Data-Challenge
Build an AI Tool for Extracting Information from Laboratory Documentation
cconsta1/SexEst
SexEst is an open-source Streamlit web application for predicting biological sex from skeletal...