Software
We release our research as open-source tools so others can reproduce it, compare against it and build on it.
PyHealth
An open-source Python toolkit for clinical deep learning. PyHealth unifies datasets (MIMIC-III, MIMIC-IV, eICU, OMOP-CDM and more), task definitions, models, training and evaluation, so a healthcare prediction pipeline takes a few lines of code.
$ pip install pyhealth
from pyhealth.datasets import MIMIC3Dataset, split_by_patient, get_dataloader
from pyhealth.tasks import ReadmissionPredictionMIMIC3
from pyhealth.models import Transformer
from pyhealth.trainer import Trainer
dataset = MIMIC3Dataset(
root="https://storage.googleapis.com/pyhealth/Synthetic_MIMIC-III/",
tables=["DIAGNOSES_ICD", "PROCEDURES_ICD", "PRESCRIPTIONS"],
)
samples = dataset.set_task(ReadmissionPredictionMIMIC3())
train, val, test = split_by_patient(samples, [0.8, 0.1, 0.1])
model = Transformer(dataset=samples)
trainer = Trainer(model=model)
trainer.train(
train_dataloader=get_dataloader(train, batch_size=32, shuffle=True),
val_dataloader=get_dataloader(val, batch_size=32, shuffle=False),
epochs=5,
)
trainer.evaluate(get_dataloader(test, batch_size=32, shuffle=False))More from the lab
Therapeutics Data Commons
Open datasets, tasks, benchmarks and leaderboards for machine learning across therapeutic science.
DeepPurpose
Deep learning toolkit for drug-target interaction, drug property and drug repurposing prediction.
BIOT
Biosignal transformer with pre-trained EEG models for learning across datasets and devices.
PyTrial
Python library and benchmark of machine learning methods and datasets for clinical trial tasks.
TrialPanorama
Database and benchmark of 1.6M clinical trial records for training and evaluating clinical research LLMs.
TrialMind
LLM pipeline for systematic literature review and clinical evidence synthesis.
BioDSA
Framework for prototyping biomedical AI agents, including the DeepEvidence research agent.
LEADS
Open model for medical literature search, study screening and data extraction.
Citing PyHealth
@inproceedings{wu2026pyhealth,
title={{PyHealth} 2.0: A Comprehensive Open-Source Toolkit for Accessible and Reproducible Clinical Deep Learning},
author={Wu, John and Fan, Yongda and Wu, Zhenbang and Landes, Paul and Schrock, Eric and Razin, Sayeed Sajjad and Chatterjee, Arjun and Baskaran, Naveen and Steier, Joshua and Fitzpatrick, Andrea and Arif, Bilal and Atri, Rian and Pradeepkumar, Jathurshan and Laghuvarapu, Siddhartha and Gao, Junyi and Cross, Adam and Sun, Jimeng},
booktitle={Proceedings of the 43rd International Conference on Machine Learning (ICML)},
year={2026},
url={https://openreview.net/forum?id=gMLVFN9hl8}
}